Search

Recent studies on logical reasoning in auto-regressive Language Models (LMs) have sparked a debate on whether such models can learn systematic reasoning principles during pre-training or merely exploit superficial patterns in the training data. This paper presents a mechanistic interpretation of syllogistic reasoning in LMs to further enhance our understanding of internal dynamics. Specifically, we present a methodology for circuit discovery aimed at disentangling content-independent reasoning mechanisms from world knowledge acquired during pre-training. Through two distinct intervention methods, we uncover a sufficient and necessary circuit involving middle-term suppression that elucidates how LMs transfer information to derive valid conclusions from premises. Furthermore, we investigate how belief biases manifest in syllogistic reasoning, finding evidence of partial contamination from additional attention heads responsible for encoding commonsense and contextualized knowledge. Finally, we explore the generalization of the discovered mechanisms across various syllogistic schemes and model sizes, finding that the identified circuit is sufficient and necessary for all the schemes on which the model achieves high downstream accuracy ($\geq$ 60\%). Overall, our findings suggest that LMs indeed learn transferable content-independent reasoning mechanisms, but that, at the same time, such mechanisms do not involve generalisable and abstract logical primitives, being susceptible to contamination by the same world knowledge acquired during pre-training.

This work presents a novel systematic methodology to analyse the capabilities and limitations of Large Language Models (LLMs) with feedback from a formal inference engine, on logic theory induction. The analysis is complexity-graded w.r.t. rule dependency structure, allowing quantification of specific inference challenges on LLM performance. Integrating LLMs with formal methods is a promising frontier in the Natural Language Processing field, as an important avenue for improving model inference control and explainability. In particular, inductive learning over complex sets of facts and rules, poses unique challenges for current autoregressive models, as they lack explicit symbolic grounding. While they can be complemented by formal systems, the properties delivered by LLMs regarding inductive learning, are not well understood and quantified. Empirical results indicate that the largest LLMs can achieve competitive results against a SOTA Inductive Logic Programming (ILP) system baseline, but also that tracking long predicate relationship chains is a more difficult obstacle than theory complexity for the LLMs.

Locating and editing knowledge in large language models (LLMs) is crucial for enhancing their accuracy, safety, and inference rationale. We introduce ``concept editing'', an innovative variation of knowledge editing that uncovers conceptualisation mechanisms within these models. Using the reverse dictionary task, inference tracing, and input abstraction, we analyse the Multi-Layer Perceptron (MLP), Multi-Head Attention (MHA), and hidden state components of transformer models. Our results reveal distinct patterns: MLP layers employ key-value retrieval mechanism and context-dependent processing, which are highly associated with relative input tokens. MHA layers demonstrate a distributed nature with significant higher-level activations, suggesting sophisticated semantic integration. Hidden states emphasise the importance of the last token and top layers in the inference process. We observe evidence of gradual information building and distributed representation. These observations elucidate how transformer models process semantic information, paving the way for targeted interventions and improved interpretability techniques. Our work highlights the complex, layered nature of semantic processing in LLMs and the challenges of isolating and modifying specific concepts within these models., Comment: 23 pages, 25 figures

We present BioLunar, developed using the Lunar framework, as a tool for supporting biological analyses, with a particular emphasis on molecular-level evidence enrichment for biomarker discovery in oncology. The platform integrates Large Language Models (LLMs) to facilitate complex scientific reasoning across distributed evidence spaces, enhancing the capability for harmonizing and reasoning over heterogeneous data sources. Demonstrating its utility in cancer research, BioLunar leverages modular design, reusable data access and data analysis components, and a low-code user interface, enabling researchers of all programming levels to construct LLM-enabled scientific workflows. By facilitating automatic scientific discovery and inference from heterogeneous evidence, BioLunar exemplifies the potential of the integration between LLMs, specialised databases and biomedical tools to support expert-level knowledge synthesis and discovery., Comment: accepted for ACL 2024 System Demonstration Track

Recent works have shown that transformers can solve contextual reasoning tasks by internally executing computational graphs called circuits. Circuits often use attention to logically match information from subspaces of the representation, e.g. using position-in-sequence to identify the previous token. In this work, we consider a semantic subspace to be any independent subspace of the latent representation that can fully determine an attention distribution. We show that Pre-Norm, the placement of normalisation layer used by state-of-the-art transformers, violates this ability unless the model learns a strict representation structure of orthogonal spheres. This is because it causes linear subspaces to interfere through their common normalisation factor. Theoretically, we analyse circuit stability by modelling this interference as random noise on the $L_2$-norms of the query/key/value vectors, predicting a phenomenon of circuit collapse when sparse-attention shifts to a different token. Empirically, we investigate the sensitivity of real-world models trained for mathematical addition, observing a 1% rate of circuit collapse when the norms are artificially perturbed by $\lesssim$10%. We contrast Pre-Norm with QKV-Norm, which places normalisation after the attention head's linear operators. Theoretically this relaxes the representational constraints. Empirically we observe comparable in-distribution but worse out-of-distribution performance.

Deep clustering (DC), a fusion of deep representation learning and clustering, has recently demonstrated positive results in data science, particularly text processing and computer vision. However, joint optimization of feature learning and data distribution in the multi-dimensional space is domain-specific, so existing DC methods struggle to generalize to other application domains (such as data integration and cleaning). In data management tasks, where high-density embeddings and overlapping clusters dominate, a data management-specific DC algorithm should be able to interact better with the data properties for supporting data cleaning and integration tasks. This paper presents a deep clustering algorithm for tabular data (TableDC) that reflects the properties of data management applications, particularly schema inference, entity resolution, and domain discovery. To address overlapping clusters, TableDC integrates Mahalanobis distance, which considers variance and correlation within the data, offering a similarity method suitable for tables, rows, or columns in high-dimensional latent spaces. TableDC provides flexibility for the final clustering assignment and shows higher tolerance to outliers through its heavy-tailed Cauchy distribution as the similarity kernel. The proposed similarity measure is particularly beneficial where the embeddings of raw data are densely packed and exhibit high degrees of overlap. Data cleaning tasks may involve a large number of clusters, which affects the scalability of existing DC methods. TableDC's self-supervised module efficiently learns data embeddings with a large number of clusters compared to existing benchmarks, which scale in quadratic time. We evaluated TableDC with several existing DC, Standard Clustering (SC), and state-of-the-art bespoke methods over benchmark datasets. TableDC consistently outperforms existing DC, SC, and bespoke methods.

Natural language explanations have become a proxy for evaluating explainable and multi-step Natural Language Inference (NLI) models. However, assessing the validity of explanations for NLI is challenging as it typically involves the crowd-sourcing of apposite datasets, a process that is time-consuming and prone to logical errors. To address existing limitations, this paper investigates the verification and refinement of natural language explanations through the integration of Large Language Models (LLMs) and Theorem Provers (TPs). Specifically, we present a neuro-symbolic framework, named Explanation-Refiner, that augments a TP with LLMs to generate and formalise explanatory sentences and suggest potential inference strategies for NLI. In turn, the TP is employed to provide formal guarantees on the logical validity of the explanations and to generate feedback for subsequent improvements. We demonstrate how Explanation-Refiner can be jointly used to evaluate explanatory reasoning, autoformalisation, and error correction mechanisms of state-of-the-art LLMs as well as to automatically enhance the quality of human-annotated explanations of variable complexity in different domains.

The alignments of reasoning abilities between smaller and larger Language Models are largely conducted via Supervised Fine-Tuning (SFT) using demonstrations generated from robust Large Language Models (LLMs). Although these approaches deliver more performant models, they do not show sufficiently strong generalization ability as the training only relies on the provided demonstrations. In this paper, we propose the Self-refine Instruction-tuning method that elicits Smaller Language Models to self-refine their abilities. Our approach is based on a two-stage process, where reasoning abilities are first transferred between LLMs and Small Language Models (SLMs) via Instruction-tuning on demonstrations provided by LLMs, and then the instructed models Self-refine their abilities through preference optimization strategies. In particular, the second phase operates refinement heuristics based on the Direct Preference Optimization algorithm, where the SLMs are elicited to deliver a series of reasoning paths by automatically sampling the generated responses and providing rewards using ground truths from the LLMs. Results obtained on commonsense and math reasoning tasks show that this approach significantly outperforms Instruction-tuning in both in-domain and out-domain scenarios, aligning the reasoning abilities of Smaller and Larger Language Models.

Language models can hallucinate when performing complex and detailed mathematical reasoning. Physics provides a rich domain for assessing mathematical reasoning capabilities where physical context imbues the use of symbols which needs to satisfy complex semantics (\textit{e.g.,} units, tensorial order), leading to instances where inference may be algebraically coherent, yet unphysical. In this work, we assess the ability of Language Models (LMs) to perform fine-grained mathematical and physical reasoning using a curated dataset encompassing multiple notations and Physics subdomains. We improve zero-shot scores using synthetic in-context examples, and demonstrate non-linear degradation of derivation quality with perturbation strength via the progressive omission of supporting premises. We find that the models' mathematical reasoning is not physics-informed in this setting, where physical context is predominantly ignored in favour of reverse-engineering solutions.

Large Language Models (LLMs) are at the forefront of NLP achievements but fall short in dealing with shortcut learning, factual inconsistency, and vulnerability to adversarial inputs.These shortcomings are especially critical in medical contexts, where they can misrepresent actual model capabilities. Addressing this, we present SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for ClinicalTrials. Our contributions include the refined NLI4CT-P dataset (i.e., Natural Language Inference for Clinical Trials - Perturbed), designed to challenge LLMs with interventional and causal reasoning tasks, along with a comprehensive evaluation of methods and results for participant submissions. A total of 106 participants registered for the task contributing to over 1200 individual submissions and 25 system overview papers. This initiative aims to advance the robustness and applicability of NLI models in healthcare, ensuring safer and more dependable AI assistance in clinical decision-making. We anticipate that the dataset, models, and outcomes of this task can support future research in the field of biomedical NLI. The dataset, competition leaderboard, and website are publicly available.

Integer Linear Programming (ILP) has been proposed as a formalism for encoding precise structural and semantic constraints for Natural Language Inference (NLI). However, traditional ILP frameworks are non-differentiable, posing critical challenges for the integration of continuous language representations based on deep learning. In this paper, we introduce a novel approach, named Diff-Comb Explainer, a neuro-symbolic architecture for explanation-based NLI based on Differentiable BlackBox Combinatorial Solvers (DBCS). Differently from existing neuro-symbolic solvers, Diff-Comb Explainer does not necessitate a continuous relaxation of the semantic constraints, enabling a direct, more precise, and efficient incorporation of neural representations into the ILP formulation. Our experiments demonstrate that Diff-Comb Explainer achieves superior performance when compared to conventional ILP solvers, neuro-symbolic black-box solvers, and Transformer-based encoders. Moreover, a deeper analysis reveals that Diff-Comb Explainer can significantly improve the precision, consistency, and faithfulness of the constructed explanations, opening new opportunities for research on neuro-symbolic architectures for explainable and transparent NLI in complex domains., Comment: Accepted to LREC-COLING 2024 - Camera Ready. arXiv admin note: substantial text overlap with arXiv:2208.03339

Rigorous evaluation of the causal effects of semantic features on language model predictions can be hard to achieve for natural language reasoning problems. However, this is such a desirable form of analysis from both an interpretability and model evaluation perspective, that it is valuable to investigate specific patterns of reasoning with enough structure and regularity to identify and quantify systematic reasoning failures in widely-used models. In this vein, we pick a portion of the NLI task for which an explicit causal diagram can be systematically constructed: the case where across two sentences (the premise and hypothesis), two related words/terms occur in a shared context. In this work, we apply causal effect estimation strategies to measure the effect of context interventions (whose effect on the entailment label is mediated by the semantic monotonicity characteristic) and interventions on the inserted word-pair (whose effect on the entailment label is mediated by the relation between these words). Extending related work on causal analysis of NLP models in different settings, we perform an extensive interventional study on the NLI task to investigate robustness to irrelevant changes and sensitivity to impactful changes of Transformers. The results strongly bolster the fact that similar benchmark accuracy scores may be observed for models that exhibit very different behaviour. Moreover, our methodology reinforces previously suspected biases from a causal perspective, including biases in favour of upward-monotone contexts and ignoring the effects of negation markers., Comment: Accepted to LREC-COLING 2024 - Camera Ready. arXiv admin note: substantial text overlap with arXiv:2305.08572

While Large Language Models (LLMs) have found success in real-world applications, their underlying explanatory process is still poorly understood. This paper proposes IBE-Eval, a framework inspired by philosophical accounts on Inference to the Best Explanation (IBE) to advance the interpretation and evaluation of LLMs' explanations. IBE-Eval estimates the plausibility of natural language explanations through a combination of explicit logical and linguistic features including: consistency, parsimony, coherence, and uncertainty. Extensive experiments are conducted on Causal Question Answering (CQA), where \textit{IBE-Eval} is tasked to select the most plausible causal explanation amongst competing ones generated by LLMs (i.e., GPT 3.5 and Llama 2). The experiments reveal that IBE-Eval can successfully identify the best explanation with up to 77\% accuracy ($\approx 27\%$ above random), improving upon a GPT 3.5-as-a-Judge baseline ($\approx+17\%$) while being intrinsically more efficient and interpretable. Additional analyses suggest that, despite model-specific variances, LLM-generated explanations tend to conform to IBE criteria and that IBE-Eval is significantly correlated with human judgment, opening up opportunities for future development of automated explanation verification tools.

An increasing amount of research in Natural Language Inference (NLI) focuses on the application and evaluation of Large Language Models (LLMs) and their reasoning capabilities. Despite their success, however, LLMs are still prone to factual errors and inconsistencies in their explanations, offering limited control and interpretability for inference in complex domains. In this paper, we focus on ethical NLI, investigating how hybrid neuro-symbolic techniques can enhance the logical validity and alignment of ethical explanations produced by LLMs. Specifically, we present an abductive-deductive framework named Logic-Explainer, which integrates LLMs with an external backward-chaining solver to refine step-wise natural language explanations and jointly verify their correctness, reduce incompleteness and minimise redundancy. An extensive empirical analysis demonstrates that Logic-Explainer can improve explanations generated via in-context learning methods and Chain-of-Thought (CoT) on challenging ethical NLI tasks, while, at the same time, producing formal proofs describing and supporting models' reasoning. As ethical NLI requires commonsense reasoning to identify underlying moral violations, our results suggest the effectiveness of neuro-symbolic methods for multi-step NLI more broadly, opening new opportunities to enhance the logical consistency, reliability, and alignment of LLMs., Comment: Camera-ready for EACL 2024

Achieving precise semantic control over the latent spaces of Variational AutoEncoders (VAEs) holds significant value for downstream tasks in NLP as the underlying generative mechanisms could be better localised, explained and improved upon. Recent research, however, has struggled to achieve consistent results, primarily due to the inevitable loss of semantic information in the variational bottleneck and limited control over the decoding mechanism. To overcome these challenges, we investigate discrete latent spaces in Vector Quantized Variational AutoEncoders (VQVAEs) to improve semantic control and generation in Transformer-based VAEs. In particular, We propose T5VQVAE, a novel model that leverages the controllability of VQVAEs to guide the self-attention mechanism in T5 at the token-level, exploiting its full generalization capabilities. Experimental results indicate that T5VQVAE outperforms existing state-of-the-art VAE models, including Optimus, in terms of controllability and preservation of semantic information across different tasks such as auto-encoding of sentences and mathematical expressions, text transfer, and inference. Moreover, T5VQVAE exhibits improved inference capabilities, suggesting potential applications for downstream natural language and symbolic reasoning tasks.

Deep generative neural networks, such as Variational AutoEncoders (VAEs), offer an opportunity to better understand and control language models from the perspective of sentence-level latent spaces. To combine the controllability of VAE latent spaces with the state-of-the-art performance of recent large language models (LLMs), we present in this work LlaMaVAE, which combines expressive encoder and decoder models (sentenceT5 and LlaMA) with a VAE architecture, aiming to provide better text generation control to LLMs. In addition, to conditionally guide the VAE generation, we investigate a new approach based on flow-based invertible neural networks (INNs) named Invertible CVAE. Experimental results reveal that LlaMaVAE can outperform the previous state-of-the-art VAE language model, Optimus, across various tasks, including language modelling, semantic textual similarity and definition modelling. Qualitative analysis on interpolation and traversal experiments also indicates an increased degree of semantic clustering and geometric consistency, which enables better generation control.

The injection of syntactic information in Variational AutoEncoders (VAEs) has been shown to result in an overall improvement of performances and generalisation. An effective strategy to achieve such a goal is to separate the encoding of distributional semantic features and syntactic structures into heterogeneous latent spaces via multi-task learning or dual encoder architectures. However, existing works employing such techniques are limited to LSTM-based VAEs. In this paper, we investigate latent space separation methods for structural syntactic injection in Transformer-based VAE architectures (i.e., Optimus). Specifically, we explore how syntactic structures can be leveraged in the encoding stage through the integration of graph-based and sequential models, and how multiple, specialised latent representations can be injected into the decoder's attention mechanism via low-rank operators. Our empirical evaluation, carried out on natural language sentences and mathematical expressions, reveals that the proposed end-to-end VAE architecture can result in a better overall organisation of the latent space, alleviating the information loss occurring in standard VAE setups, resulting in enhanced performances on language modelling and downstream generation tasks.

The sparsity of labelled data is an obstacle to the development of Relation Extraction models and the completion of databases in various biomedical areas. While being of high interest in drug-discovery, the natural-products literature, reporting the identification of potential bioactive compounds from organisms, is a concrete example of such an overlooked topic. To mark the start of this new task, we created the first curated evaluation dataset and extracted literature items from the LOTUS database to build training sets. To this end, we developed a new sampler inspired by diversity metrics in ecology, named Greedy Maximum Entropy sampler, or GME-sampler (https://github.com/idiap/gme-sampler). The strategic optimization of both balance and diversity of the selected items in the evaluation set is important given the resource-intensive nature of manual curation. After quantifying the noise in the training set, in the form of discrepancies between the input abstracts text and the expected output labels, we explored different strategies accordingly. Framing the task as an end-to-end Relation Extraction, we evaluated the performance of standard fine-tuning as a generative task and few-shot learning with open Large Language Models (LLaMA 7B-65B). In addition to their evaluation in few-shot settings, we explore the potential of open Large Language Models (Vicuna-13B) as synthetic data generator and propose a new workflow for this purpose. All evaluated models exhibited substantial improvements when fine-tuned on synthetic abstracts rather than the original noisy data. We provide our best performing (f1-score=59.0) BioGPT-Large model for end-to-end RE of natural-products relationships along with all the generated synthetic data and the evaluation dataset. See more details at https://github.com/idiap/abroad-re.

This paper investigates the possibility of approximating multiple mathematical operations in latent space for expression derivation. To this end, we introduce different multi-operational representation paradigms, modelling mathematical operations as explicit geometric transformations. By leveraging a symbolic engine, we construct a large-scale dataset comprising 1.7M derivation steps stemming from 61K premises and 6 operators, analysing the properties of each paradigm when instantiated with state-of-the-art neural encoders. Specifically, we investigate how different encoding mechanisms can approximate expression manipulation in latent space, exploring the trade-off between learning different operators and specialising within single operations, as well as the ability to support multi-step derivations and out-of-distribution generalisation. Our empirical analysis reveals that the multi-operational paradigm is crucial for disentangling different operators, while discriminating the conclusions for a single operation is achievable in the original expression encoder. Moreover, we show that architectural choices can heavily affect the training dynamics, structural organisation, and generalisation of the latent space, resulting in significant variations across paradigms and classes of encoders., Comment: Accepted to NAACL 2024 - Camera Ready

The language ability of Large Language Models (LLMs) is often unbalanced towards English because of the imbalance in the distribution of the pre-training data. This disparity is demanded in further fine-tuning and affecting the cross-lingual abilities of LLMs. In this paper, we propose to empower Instructiontuned LLMs (It-LLMs) in languages other than English by building semantic alignment between them. Hence, we propose CrossAlpaca, an It-LLM with cross-lingual instruction-following and Translation-following demonstrations to improve semantic alignment between languages. We validate our approach on the multilingual Question Answering (QA) benchmarks XQUAD and MLQA and adapted versions of MMLU and BBH. Our models, tested over six different languages, outperform the It-LLMs tuned on monolingual data. The final results show that instruction tuning on non-English data is not enough and that semantic alignment can be further improved by Translation-following demonstrations.

Explainable natural language inference aims to provide a mechanism to produce explanatory (abductive) inference chains which ground claims to their supporting premises. A recent corpus called EntailmentBank strives to advance this task by explaining the answer to a question using an entailment tree \cite{dalvi2021explaining}. They employ the T5 model to directly generate the tree, which can explain how the answer is inferred. However, it lacks the ability to explain and control the generation of intermediate steps, which is crucial for the multi-hop inference process. % One recent corpus, EntailmentBank, aims to push this task forward by explaining an answer to a question according to an entailment tree \cite{dalvi2021explaining}. They employ T5 to generate the tree directly, which can explain how the answer is inferred but cannot explain how the intermediate is generated, which is essential to the multi-hop inference process. In this work, we focus on proposing a controlled natural language inference architecture for multi-premise explanatory inference. To improve control and enable explanatory analysis over the generation, we define lexical inference types based on Abstract Meaning Representation (AMR) graph and modify the architecture of T5 to learn a latent sentence representation (T5 bottleneck) conditioned on said type information. We also deliver a dataset of approximately 5000 annotated explanatory inference steps, with well-grounded lexical-symbolic operations. Experimental results indicate that the inference typing induced at the T5 bottleneck can help T5 to generate a conclusion under explicit control.

Sentences that present a complex syntax act as a major stumbling block for downstream Natural Language Processing applications whose predictive quality deteriorates with sentence length and complexity. The task of Text Simplification (TS) may remedy this situation. It aims to modify sentences in order to make them easier to process, using a set of rewriting operations, such as reordering, deletion, or splitting. State-of-the-art syntactic TS approaches suffer from two major drawbacks: first, they follow a very conservative approach in that they tend to retain the input rather than transforming it, and second, they ignore the cohesive nature of texts, where context spread across clauses or sentences is needed to infer the true meaning of a statement. To address these problems, we present a discourse-aware TS approach that splits and rephrases complex English sentences within the semantic context in which they occur. Based on a linguistically grounded transformation stage that uses clausal and phrasal disembedding mechanisms, complex sentences are transformed into shorter utterances with a simple canonical structure that can be easily analyzed by downstream applications. With sentence splitting, we thus address a TS task that has hardly been explored so far. Moreover, we introduce the notion of minimality in this context, as we aim to decompose source sentences into a set of self-contained minimal semantic units. To avoid breaking down the input into a disjointed sequence of statements that is difficult to interpret because important contextual information is missing, we incorporate the semantic context between the split propositions in the form of hierarchical structures and semantic relationships. In that way, we generate a semantic hierarchy of minimal propositions that leads to a novel representation of complex assertions that puts a semantic layer on top of the simplified sentences.

The derivation of mathematical results in specialised fields, using Large Language Models (LLMs), is an emerging research direction that can help identify models' limitations, and potentially support mathematical discovery. In this paper, we leverage a symbolic engine to generate derivations of equations at scale, and investigate the capabilities of LLMs when deriving goal equations from premises. Specifically, we employ in-context learning for GPT and fine-tune a range of T5 models to compare the robustness and generalisation of pre-training strategies to specialised models. Empirical results show that fine-tuned FLAN-T5-large (MathT5) outperforms GPT models on all static and out-of-distribution test sets in conventional scores. However, an in-depth analysis reveals that the fine-tuned models are more sensitive to perturbations involving unseen symbols and (to a lesser extent) changes to equation structure. In addition, we analyse 1.7K equations, and over 200 derivations, to highlight common reasoning errors such as the inclusion of incorrect, irrelevant, and redundant equations. Finally, we explore the suitability of existing metrics for evaluating mathematical derivations and find evidence that, while they can capture general properties such as sensitivity to perturbations, they fail to highlight fine-grained reasoning errors and essential differences between models. Overall, this work demonstrates that training models on synthetic data may improve their math capabilities beyond much larger LLMs, but current metrics are not appropriately assessing the quality of generated mathematical text., Comment: 10 pages

Inferring over and extracting information from Large Language Models (LLMs) trained on a large corpus of scientific literature can potentially drive a new era in biomedical research, reducing the barriers for accessing existing medical evidence. This work examines the potential of LLMs for dialoguing with biomedical background knowledge, using the context of antibiotic discovery. The systematic analysis is applied to ten state-of-the-art models, from models specialised on biomedical scientific corpora to general models such as ChatGPT, GPT-4 and Llama 2 in two prompting-based tasks: chemical compound definition generation and chemical compound-fungus relation determination. The work provides a systematic assessment on the ability of LLMs to encode and express these relations, verifying for fluency, prompt-alignment, semantic coherence, factual knowledge and specificity of generated responses. Results show that while recent models have improved in fluency, factual accuracy is still low and models are biased towards over-represented entities. The ability of LLMs to serve as biomedical knowledge bases is questioned, and the need for additional systematic evaluation frameworks is highlighted. The best performing GPT-4 produced a factual definition for 70% of chemical compounds and 43.6% factual relations to fungi, whereas the best open source model BioGPT-large 30% of the compounds and 30% of the relations for the best-performing prompt. The results show that while LLMs are currently not fit for purpose to be used as biomedical factual knowledge bases, there is a promising emerging property in the direction of factuality as the models become domain specialised, scale-up in size and level of human feedback., Comment: 28 pages, 3 figures

Deep Learning (DL) techniques now constitute the state-of-the-art for important problems in areas such as text and image processing, and there have been impactful results that deploy DL in several data management tasks. Deep Clustering (DC) has recently emerged as a sub-discipline of DL, in which data representations are learned in tandem with clustering, with a view to automatically identifying the features of the data that lead to improved clustering results. While DC has been used to good effect in several domains, particularly in image processing, the impact of DC on mainstream data management tasks remains unexplored. In this paper, we address this gap by investigating the impact of DC in data cleaning and integration tasks, specifically schema inference, entity resolution, and domain discovery, tasks that represent clustering from the perspective of tables, rows, and columns, respectively. In this setting, we compare and contrast several DC and non-DC clustering algorithms using standard benchmarks. The results show, among other things, that the most effective DC algorithms consistently outperform non-DC clustering algorithms for data integration tasks. However, we observed a significant correlation between the DC method and embedding approaches for rows, columns, and tables, highlighting that the suitable combination can enhance the efficiency of DC methods., Comment: The following enhancements have been carried out in the updated version of the manuscript: *Evaluated each data integration problem on additional datasets. *Added more DC and SC methods to the evaluation *Discussed algorithmic-specific observations

This paper proposes a methodology for generating and perturbing detailed derivations of equations at scale, aided by a symbolic engine, to evaluate the generalisability of Transformers to out-of-distribution mathematical reasoning problems. Instantiating the framework in the context of sequence classification tasks, we compare the capabilities of GPT-4, GPT-3.5, and a canon of fine-tuned BERT models, exploring the relationship between specific operators and generalisation failure via the perturbation of reasoning aspects such as symmetry and variable surface forms. Surprisingly, our empirical evaluation reveals that the average in-distribution performance of fine-tuned models surpasses GPT-3.5, and rivals GPT-4. However, perturbations to input reasoning can reduce their performance by up to 80 F1 points. Overall, the results suggest that the in-distribution performance of smaller open-source models may potentially rival GPT by incorporating appropriately structured derivation dependencies during training, and highlight a shared weakness between BERT and GPT involving a relative inability to decode indirect references to mathematical entities. We release the full codebase, constructed datasets, and fine-tuned models to encourage future progress in the field., Comment: NAACL 2024

Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains. In response to their fast adoption in many industrial applications, this survey concerns their safety and trustworthiness. First, we review known vulnerabilities and limitations of the LLMs, categorising them into inherent issues, attacks, and unintended bugs. Then, we consider if and how the Verification and Validation (V&V) techniques, which have been widely developed for traditional software and deep learning models such as convolutional neural networks as independent processes to check the alignment of their implementations against the specifications, can be integrated and further extended throughout the lifecycle of the LLMs to provide rigorous analysis to the safety and trustworthiness of LLMs and their applications. Specifically, we consider four complementary techniques: falsification and evaluation, verification, runtime monitoring, and regulations and ethical use. In total, 370+ references are considered to support the quick understanding of the safety and trustworthiness issues from the perspective of V&V. While intensive research has been conducted to identify the safety and trustworthiness issues, rigorous yet practical methods are called for to ensure the alignment of LLMs with safety and trustworthiness requirements.

Rigorous evaluation of the causal effects of semantic features on language model predictions can be hard to achieve for natural language reasoning problems. However, this is such a desirable form of analysis from both an interpretability and model evaluation perspective, that it is valuable to zone in on specific patterns of reasoning with enough structure and regularity to be able to identify and quantify systematic reasoning failures in widely-used models. In this vein, we pick a portion of the NLI task for which an explicit causal diagram can be systematically constructed: in particular, the case where across two sentences (the premise and hypothesis), two related words/terms occur in a shared context. In this work, we apply causal effect estimation strategies to measure the effect of context interventions (whose effect on the entailment label is mediated by the semantic monotonicity characteristic) and interventions on the inserted word-pair (whose effect on the entailment label is mediated by the relation between these words.). Following related work on causal analysis of NLP models in different settings, we adapt the methodology for the NLI task to construct comparative model profiles in terms of robustness to irrelevant changes and sensitivity to impactful changes.

Natural language definitions possess a recursive, self-explanatory semantic structure that can support representation learning methods able to preserve explicit conceptual relations and constraints in the latent space. This paper presents a multi-relational model that explicitly leverages such a structure to derive word embeddings from definitions. By automatically extracting the relations linking defined and defining terms from dictionaries, we demonstrate how the problem of learning word embeddings can be formalised via a translational framework in Hyperbolic space and used as a proxy to capture the global semantic structure of definitions. An extensive empirical analysis demonstrates that the framework can help imposing the desired structural constraints while preserving the semantic mapping required for controllable and interpretable traversal. Moreover, the experiments reveal the superiority of the Hyperbolic word embeddings over the Euclidean counterparts and demonstrate that the multi-relational approach can obtain competitive results when compared to state-of-the-art neural models, with the advantage of being intrinsically more efficient and interpretable., Comment: Accepted at the 18th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2024), camera-ready

How can we interpret and retrieve medical evidence to support clinical decisions? Clinical trial reports (CTR) amassed over the years contain indispensable information for the development of personalized medicine. However, it is practically infeasible to manually inspect over 400,000+ clinical trial reports in order to find the best evidence for experimental treatments. Natural Language Inference (NLI) offers a potential solution to this problem, by allowing the scalable computation of textual entailment. However, existing NLI models perform poorly on biomedical corpora, and previously published datasets fail to capture the full complexity of inference over CTRs. In this work, we present a novel resource to advance research on NLI for reasoning on CTRs. The resource includes two main tasks. Firstly, to determine the inference relation between a natural language statement, and a CTR. Secondly, to retrieve supporting facts to justify the predicted relation. We provide NLI4CT, a corpus of 2400 statements and CTRs, annotated for these tasks. Baselines on this corpus expose the limitations of existing NLI models, with 6 state-of-the-art NLI models achieving a maximum F1 score of 0.627. To the best of our knowledge, we are the first to design a task that covers the interpretation of full CTRs. To encourage further work on this challenging dataset, we make the corpus, competition leaderboard, website and code to replicate the baseline experiments available at: https://github.com/ai-systems/nli4ct, Comment: EMNLP 2023 Camera-ready, 15 pages

This paper describes the results of SemEval 2023 task 7 -- Multi-Evidence Natural Language Inference for Clinical Trial Data (NLI4CT) -- consisting of 2 tasks, a Natural Language Inference (NLI) task, and an evidence selection task on clinical trial data. The proposed challenges require multi-hop biomedical and numerical reasoning, which are of significant importance to the development of systems capable of large-scale interpretation and retrieval of medical evidence, to provide personalized evidence-based care. Task 1, the entailment task, received 643 submissions from 40 participants, and Task 2, the evidence selection task, received 364 submissions from 23 participants. The tasks are challenging, with the majority of submitted systems failing to significantly outperform the majority class baseline on the entailment task, and we observe significantly better performance on the evidence selection task than on the entailment task. Increasing the number of model parameters leads to a direct increase in performance, far more significant than the effect of biomedical pre-training. Future works could explore the limitations of large models for generalization and numerical inference, and investigate methods to augment clinical datasets to allow for more rigorous testing and to facilitate fine-tuning. We envisage that the dataset, models, and results of this task will be useful to the biomedical NLI and evidence retrieval communities. The dataset, competition leaderboard, and website are publicly available.

Disentangled latent spaces usually have better semantic separability and geometrical properties, which leads to better interpretability and more controllable data generation. While this has been well investigated in Computer Vision, in tasks such as image disentanglement, in the NLP domain sentence disentanglement is still comparatively under-investigated. Most previous work have concentrated on disentangling task-specific generative factors, such as sentiment, within the context of style transfer. In this work, we focus on a more general form of sentence disentanglement, targeting the localised modification and control of more general sentence semantic features. To achieve this, we contribute to a novel notion of sentence semantic disentanglement and introduce a flow-based invertible neural network (INN) mechanism integrated with a transformer-based language Autoencoder (AE) in order to deliver latent spaces with better separability properties. Experimental results demonstrate that the model can conform the distributed latent space into a better semantically disentangled sentence space, leading to improved language interpretability and controlled generation when compared to the recent state-of-the-art language VAE models., Comment: ACL 2024

Probing strategies have been shown to detect the presence of various linguistic features in large language models; in particular, semantic features intermediate to the "natural logic" fragment of the Natural Language Inference task (NLI). In the case of natural logic, the relation between the intermediate features and the entailment label is explicitly known: as such, this provides a ripe setting for interventional studies on the NLI models' representations, allowing for stronger causal conjectures and a deeper critical analysis of interventional probing methods. In this work, we carry out new and existing representation-level interventions to investigate the effect of these semantic features on NLI classification: we perform amnesic probing (which removes features as directed by learned linear probes) and introduce the mnestic probing variation (which forgets all dimensions except the probe-selected ones). Furthermore, we delve into the limitations of these methods and outline some pitfalls have been obscuring the effectivity of interventional probing studies.

The recent evolution in Natural Language Processing (NLP) methods, in particular in the field of argumentation mining, has the potential to transform the way we interact with text, supporting the interpretation and analysis of complex discourse and debates. Can a graphic visualisation of complex argumentation enable a more critical interpretation of the arguments? This study focuses on analysing the impact of argumentation graphs (AGs) compared with regular texts for supporting argument interpretation. We found that AGs outperformed the extrinsic metrics throughout most UEQ scales as well as the NASA-TLX workload in all the terms but not in temporal or physical demand. The AG model was liked by a more significant number of participants, despite the fact that both the text-based and AG models yielded comparable outcomes in the critical interpretation in terms of working memory and altering participants decisions. The interpretation process involves reference to argumentation schemes (linked to critical questions (CQs)) in AGs. Interestingly, we found that the participants chose more CQs (using argument schemes in AGs) when they were less familiar with the argument topics, making AG schemes on some scales (relatively) supportive of the interpretation process. Therefore, AGs were considered to deliver a more critical approach to argument interpretation, especially with unfamiliar topics. Based on the 25 participants conducted in this study, it appears that AG has demonstrated an overall positive effect on the argument interpretation process., Comment: 35 pages

In this work, we examined Business Process (BP) production as a signal; this novel approach explores a BP workflow as a linear time-invariant (LTI) system. We analysed BP productivity in the frequency domain; this standpoint examines how labour and capital act as BP input signals and how their fundamental frequencies affect BP production. Our research also proposes a simulation framework of a BP in the frequency domain for estimating productivity gains due to the introduction of automation steps. Our ultimate goal was to supply evidence to address Solow's Paradox., Comment: 16 pages, 24 figures

Formal/symbolic semantics can provide canonical, rigid controllability and interpretability to sentence representations due to their \textit{localisation} or \textit{composition} property. How can we deliver such property to the current distributional sentence representations to control and interpret the generation of language models (LMs)? In this work, we theoretically frame the sentence semantics as the composition of \textit{semantic role - word content} features and propose the formal semantic geometry. To inject such geometry into Transformer-based LMs (i.e. GPT2), we deploy Transformer-based Variational AutoEncoder with a supervision approach, where the sentence generation can be manipulated and explained over low-dimensional latent Gaussian space. In addition, we propose a new probing algorithm to guide the movement of sentence vectors over such geometry. Experimental results reveal that the formal semantic geometry can potentially deliver better control and interpretation to sentence generation.

In recent years, distributional language representation models have demonstrated great practical success. At the same time, the need for interpretability has elicited questions on their intrinsic properties and capabilities. Crucially, distributional models are often inconsistent when dealing with compositional phenomena in natural language, which has significant implications for their safety and fairness. Despite this, most current research on compositionality is directed towards improving their performance on similarity tasks only. This work takes a different approach, and proposes a methodology for measuring compositional behavior in contemporary language models. Specifically, we focus on adjectival modifier phenomena in adjective-noun phrases. We introduce three novel tests of compositional behavior inspired by Montague semantics. Our experimental results indicate that current neural language models behave according to the expected linguistic theories to a limited extent only. This raises the question of whether these language models are not able to capture the semantic properties we evaluated, or whether linguistic theories from Montagovian tradition would not match the expected capabilities of distributional models.

This paper proposes a novel productivity estimation model to evaluate the effects of adopting Artificial Intelligence (AI) components in a production chain. Our model provides evidence to address the "AI's" Solow's Paradox. We provide (i) theoretical and empirical evidence to explain Solow's dichotomy; (ii) a data-driven model to estimate and asses productivity variations; (iii) a methodology underpinned on process mining datasets to determine the business process, BP, and productivity; (iv) a set of computer simulation parameters; (v) and empirical analysis on labour-distribution. These provide data on why we consider AI Solow's paradox a consequence of metric mismeasurement., Comment: 11 pages and 9 figures

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised or rely on synthetic datasets with known generative factors. We argue that recurrent syntactic and semantic regularities in textual data can be used to provide the models with both structural biases and generative factors. We leverage the semantic structures present in a representative and semantically dense category of sentence types, definitional sentences, for training a Variational Autoencoder to learn disentangled representations. Our experimental results show that the proposed model outperforms unsupervised baselines on several qualitative and quantitative benchmarks for disentanglement, and it also improves the results in the downstream task of definition modeling., Comment: Findings of EACL 2023

Integer Linear Programming (ILP) provides a viable mechanism to encode explicit and controllable assumptions about explainable multi-hop inference with natural language. However, an ILP formulation is non-differentiable and cannot be integrated into broader deep learning architectures. Recently, Thayaparan et al. (2021a) proposed a novel methodology to integrate ILP with Transformers to achieve end-to-end differentiability for complex multi-hop inference. While this hybrid framework has been demonstrated to deliver better answer and explanation selection than transformer-based and existing ILP solvers, the neuro-symbolic integration still relies on a convex relaxation of the ILP formulation, which can produce sub-optimal solutions. To improve these limitations, we propose Diff-Comb Explainer, a novel neuro-symbolic architecture based on Differentiable BlackBox Combinatorial solvers (DBCS) (Pogan\v{c}i\'c et al., 2019). Unlike existing differentiable solvers, the presented model does not require the transformation and relaxation of the explicit semantic constraints, allowing for direct and more efficient integration of ILP formulations. Diff-Comb Explainer demonstrates improved accuracy and explainability over non-differentiable solvers, Transformers and existing differentiable constraint-based multi-hop inference frameworks.

Entailment trees have been proposed to simulate the human reasoning process of explanation generation in the context of open--domain textual question answering. However, in practice, manually constructing these explanation trees proves a laborious process that requires active human involvement. Given the complexity of capturing the line of reasoning from question to the answer or from claim to premises, the issue arises of how to assist the user in efficiently constructing multi--level entailment trees given a large set of available facts. In this paper, we frame the construction of entailment trees as a sequence of active premise selection steps, i.e., for each intermediate node in an explanation tree, the expert needs to annotate positive and negative examples of premise facts from a large candidate list. We then iteratively fine--tune pre--trained Transformer models with the resulting positive and tightly controlled negative samples and aim to balance the encoding of semantic relationships and explanatory entailment relationships. Experimental evaluation confirms the measurable efficiency gains of the proposed active fine--tuning method in facilitating entailment trees construction: up to 20\% improvement in explanatory premise selection when compared against several alternatives.

There is an increasing interest in the use of Deep Learning (DL) based methods as a supporting analytical framework in oncology. However, most direct applications of DL will deliver models with limited transparency and explainability, which constrain their deployment in biomedical settings. This systematic review discusses DL models used to support inference in cancer biology with a particular emphasis on multi-omics analysis. It focuses on how existing models address the need for better dialogue with prior knowledge, biological plausibility and interpretability, fundamental properties in the biomedical domain. For this, we retrieved and analyzed 42 studies focusing on emerging architectural and methodological advances, the encoding of biological domain knowledge and the integration of explainability methods. We discuss the recent evolutionary arch of DL models in the direction of integrating prior biological relational and network knowledge to support better generalisation (e.g. pathways or Protein-Protein-Interaction networks) and interpretability. This represents a fundamental functional shift towards models which can integrate mechanistic and statistical inference aspects. We introduce a concept of bio-centric interpretability and according to its taxonomy, we discuss representational methodologies for the integration of domain prior knowledge in such models. The paper provides a critical outlook into contemporary methods for explainability and interpretabiltiy used in DL for cancer. The analysis points in the direction of a convergence between encoding prior knowledge and improved interpretability. We introduce bio-centric interpretability which is an important step towards formalisation of biological interpretability of DL models and developing methods that are less problem- or application-specific., Comment: 25 pages, 5 figures