Search

Exploration is a crucial skill for self-improvement and open-ended problem-solving. However, it remains uncertain whether large language models can effectively explore the state-space. Existing evaluations predominantly focus on the trade-off between exploration and exploitation, often assessed in multi-armed bandit problems. In contrast, this work isolates exploration as the sole objective, tasking the agent with delivering information that enhances future returns. For the evaluation, we propose to decompose missing rewards into exploration and exploitation components by measuring the optimal achievable return for the states already explored. Our experiments with various LLMs reveal that most models struggle to sufficiently explore the state-space and that weak exploration is insufficient. We observe a positive correlation between model size and exploration performance, with larger models demonstrating superior capabilities. Furthermore, we show that our decomposition provides insights into differences in behaviors driven by agent instructions during prompt engineering, offering a valuable tool for refining LLM performance in exploratory tasks.

Human bilinguals often use similar brain regions to process multiple languages, depending on when they learned their second language and their proficiency. In large language models (LLMs), how are multiple languages learned and encoded? In this work, we explore the extent to which LLMs share representations of morphosyntactic concepts such as grammatical number, gender, and tense across languages. We train sparse autoencoders on Llama-3-8B and Aya-23-8B, and demonstrate that abstract grammatical concepts are often encoded in feature directions shared across many languages. We use causal interventions to verify the multilingual nature of these representations; specifically, we show that ablating only multilingual features decreases classifier performance to near-chance across languages. We then use these features to precisely modify model behavior in a machine translation task; this demonstrates both the generality and selectivity of these feature's roles in the network. Our findings suggest that even models trained predominantly on English data can develop robust, cross-lingual abstractions of morphosyntactic concepts.

The performance of neural networks increases steadily, but our understanding of their decision-making lags behind. Concept Bottleneck Models (CBMs) address this issue by incorporating human-understandable concepts into the prediction process, thereby enhancing transparency and interpretability. Since existing approaches often rely on large language models (LLMs) to infer concepts, their results may contain inaccurate or incomplete mappings, especially in complex visual domains. We introduce visually Grounded Concept Bottleneck Models (GCBM), which derive concepts on the image level using segmentation and detection foundation models. Our method generates inherently interpretable concepts, which can be grounded in the input image using attribution methods, allowing interpretations to be traced back to the image plane. We show that GCBM concepts are meaningful interpretability vehicles, which aid our understanding of model embedding spaces. GCBMs allow users to control the granularity, number, and naming of concepts, providing flexibility and are easily adaptable to new datasets without pre-training or additional data needed. Prediction accuracy is within 0.3-6% of the linear probe and GCBMs perform especially well for fine-grained classification interpretability on CUB, due to their dataset specificity. Our code is available on https://github.com/KathPra/GCBM., Comment: *Equal contribution

Graphical user interface (GUI) prototyping represents an essential activity in the development of interactive systems, which are omnipresent today. GUI prototypes facilitate elicitation of requirements and help to test, evaluate, and validate ideas with users and the development team. However, creating GUI prototypes is a time-consuming process and often requires extensive resources. While existing research for automatic GUI generation focused largely on resource-intensive training and fine-tuning of LLMs, mainly for low-fidelity GUIs, we investigate the potential and effectiveness of Zero-Shot (ZS) prompting for high-fidelity GUI generation. We propose a Retrieval-Augmented GUI Generation (RAGG) approach, integrated with an LLM-based GUI retrieval re-ranking and filtering mechanism based on a large-scale GUI repository. In addition, we adapt Prompt Decomposition (PDGG) and Self-Critique (SCGG) for GUI generation. To evaluate the effectiveness of the proposed ZS prompting approaches for GUI generation, we extensively evaluated the accuracy and subjective satisfaction of the generated GUI prototypes. Our evaluation, which encompasses over 3,000 GUI annotations from over 100 crowd-workers with UI/UX experience, shows that SCGG, in contrast to PDGG and RAGG, can lead to more effective GUI generation, and provides valuable insights into the defects that are produced by the LLMs in the generated GUI prototypes.

In this technical report, we investigate the predictive performance differences of a rule-based approach and the GNN architectures NBFNet and A*Net with respect to knowledge graph completion. For the two most common benchmarks, we find that a substantial fraction of the performance difference can be explained by one unique negative pattern on each dataset that is hidden from the rule-based approach. Our findings add a unique perspective on the performance difference of different model classes for knowledge graph completion: Models can achieve a predictive performance advantage by penalizing scores of incorrect facts opposed to providing high scores for correct facts.

Measuring the abundances of carbon- and oxygen-bearing molecules has been a primary focus in studying the atmospheres of hot Jupiters, as doing so can help constrain the carbon-to-oxygen (C/O) ratio. The C/O ratio can help reveal the evolution and formation pathways of hot Jupiters and provide a strong understanding of the atmospheric composition. In the last decade, high-resolution spectral analyses have become increasingly useful in measuring precise abundances of several carbon- and oxygen-bearing molecules. This allows for a more precise constraint of the C/O ratio. We present four transits of the hot Jupiter WASP-43b observed between 1.45 $-$ 2.45 $\mu$m with the high-resolution Immersion GRating InfraRed Spectrometer (IGRINS) on the Gemini-S telescope. We detected H$_2$O at a signal-to-noise ratio (SNR) of 3.51. We tested for the presence of CH$_4$, CO, and CO$_2$, but we did not detect these carbon-bearing species. We ran a retrieval for all four molecules and obtained a water abundance of $\log_{10}(\text{H}_2\text{O}) = -2.24^{+0.57}_{-0.48}$. We obtained an upper limit on the C/O ratio of C/O $<$ 0.95. These findings are consistent with previous observations from the Hubble Space Telescope and the James Webb Space Telescope., Comment: 11 pages, 6 figures

Requirements Elicitation (RE) is a crucial activity especially in the early stages of software development. GUI prototyping has widely been adopted as one of the most effective RE techniques for user-facing software systems. However, GUI prototyping requires (i) the availability of experienced requirements analysts, (ii) typically necessitates conducting multiple joint sessions with customers and (iii) creates considerable manual effort. In this work, we propose SERGUI, a novel approach enabling the Self-Elicitation of Requirements (SER) based on an automated GUI prototyping assistant. SERGUI exploits the vast prototyping knowledge embodied in a large-scale GUI repository through Natural Language Requirements (NLR) based GUI retrieval and facilitates fast feedback through GUI prototypes. The GUI retrieval approach is closely integrated with a Large Language Model (LLM) driving the prompting-based recommendation of GUI features for the current GUI prototyping context and thus stimulating the elicitation of additional requirements. We envision SERGUI to be employed in the initial RE phase, creating an initial GUI prototype specification to be used by the analyst as a means for communicating the requirements. To measure the effectiveness of our approach, we conducted a preliminary evaluation. Video presentation of SERGUI at: https://youtu.be/pzAAB9Uht80

Outlier detection is a crucial analytical tool in various fields. In critical systems like manufacturing, malfunctioning outlier detection can be costly and safety-critical. Therefore, there is a significant need for explainable artificial intelligence (XAI) when deploying opaque models in such environments. This study focuses on manufacturing time series data from a German automotive supply industry. We utilize autoencoders to compress the entire time series and then apply anomaly detection techniques to its latent features. For outlier interpretation, we (i) adopt widely used XAI techniques to the autoencoder's encoder. Additionally, (ii) we propose AEE, Aggregated Explanatory Ensemble, a novel approach that fuses explanations of multiple XAI techniques into a single, more expressive interpretation. For evaluation of explanations, (iii) we propose a technique to measure the quality of encoder explanations quantitatively. Furthermore, we qualitatively assess the effectiveness of outlier explanations with domain expertise., Comment: 14 pages, 8 figures, accepted at TempXAI @ ECML-PKDD

We present a new approach to goal recognition that involves comparing observed facts with their expected probabilities. These probabilities depend on a specified goal g and initial state s0. Our method maps these probabilities and observed facts into a real vector space to compute heuristic values for potential goals. These values estimate the likelihood of a given goal being the true objective of the observed agent. As obtaining exact expected probabilities for observed facts in an observation sequence is often practically infeasible, we propose and empirically validate a method for approximating these probabilities. Our empirical results show that the proposed approach offers improved goal recognition precision compared to state-of-the-art techniques while reducing computational complexity., Comment: Will be presented at ECAI 2024

Reinforcement learning (RL) has seen significant success across various domains, but its adoption is often limited by the black-box nature of neural network policies, making them difficult to interpret. In contrast, symbolic policies allow representing decision-making strategies in a compact and interpretable way. However, learning symbolic policies directly within on-policy methods remains challenging. In this paper, we introduce SYMPOL, a novel method for SYMbolic tree-based on-POLicy RL. SYMPOL employs a tree-based model integrated with a policy gradient method, enabling the agent to learn and adapt its actions while maintaining a high level of interpretability. We evaluate SYMPOL on a set of benchmark RL tasks, demonstrating its superiority over alternative tree-based RL approaches in terms of performance and interpretability. To the best of our knowledge, this is the first method, that allows a gradient-based end-to-end learning of interpretable, axis-aligned decision trees within existing on-policy RL algorithms. Therefore, SYMPOL can become the foundation for a new class of interpretable RL based on decision trees. Our implementation is available under: https://github.com/s-marton/SYMPOL

Tabular data is prevalent in real-world machine learning applications, and new models for supervised learning of tabular data are frequently proposed. Comparative studies assessing the performance of models typically consist of model-centric evaluation setups with overly standardized data preprocessing. This paper demonstrates that such model-centric evaluations are biased, as real-world modeling pipelines often require dataset-specific preprocessing and feature engineering. Therefore, we propose a data-centric evaluation framework. We select 10 relevant datasets from Kaggle competitions and implement expert-level preprocessing pipelines for each dataset. We conduct experiments with different preprocessing pipelines and hyperparameter optimization (HPO) regimes to quantify the impact of model selection, HPO, feature engineering, and test-time adaptation. Our main findings are: 1. After dataset-specific feature engineering, model rankings change considerably, performance differences decrease, and the importance of model selection reduces. 2. Recent models, despite their measurable progress, still significantly benefit from manual feature engineering. This holds true for both tree-based models and neural networks. 3. While tabular data is typically considered static, samples are often collected over time, and adapting to distribution shifts can be important even in supposedly static data. These insights suggest that research efforts should be directed toward a data-centric perspective, acknowledging that tabular data requires feature engineering and often exhibits temporal characteristics. Our framework is available under: https://github.com/atschalz/dc_tabeval.

Neural networks often assume independence among input data samples, disregarding correlations arising from inherent clustering patterns in real-world datasets (e.g., due to different sites or repeated measurements). Recently, mixed effects neural networks (MENNs) which separate cluster-specific 'random effects' from cluster-invariant 'fixed effects' have been proposed to improve generalization and interpretability for clustered data. However, existing methods only allow for approximate quantification of cluster effects and are limited to regression and binary targets with only one clustering feature. We present MC-GMENN, a novel approach employing Monte Carlo methods to train Generalized Mixed Effects Neural Networks. We empirically demonstrate that MC-GMENN outperforms existing mixed effects deep learning models in terms of generalization performance, time complexity, and quantification of inter-cluster variance. Additionally, MC-GMENN is applicable to a wide range of datasets, including multi-class classification tasks with multiple high-cardinality categorical features. For these datasets, we show that MC-GMENN outperforms conventional encoding and embedding methods, simultaneously offering a principled methodology for interpreting the effects of clustering patterns.

Interactive systems are omnipresent today and the need to create graphical user interfaces (GUIs) is just as ubiquitous. For the elicitation and validation of requirements, GUI prototyping is a well-known and effective technique, typically employed after gathering initial user requirements represented in natural language (NL) (e.g., in the form of user stories). Unfortunately, GUI prototyping often requires extensive resources, resulting in a costly and time-consuming process. Despite various easy-to-use prototyping tools in practice, there is often a lack of adequate resources for developing GUI prototypes based on given user requirements. In this work, we present a novel Large Language Model (LLM)-based approach providing assistance for validating the implementation of functional NL-based requirements in a GUI prototype embedded in a prototyping tool. In particular, our approach aims to detect functional user stories that are not implemented in a GUI prototype and provides recommendations for suitable GUI components directly implementing the requirements. We collected requirements for existing GUIs in the form of user stories and evaluated our proposed validation and recommendation approach with this dataset. The obtained results are promising for user story validation and we demonstrate feasibility for the GUI component recommendations.

LambdaBeam is a state-of-the-art, execution-guided algorithm for program synthesis that utilizes higher-order functions, lambda functions, and iterative loops within a Domain-Specific Language (DSL). LambdaBeam generates each program from scratch but does not take advantage of the frequent recurrence of program blocks or subprograms commonly found in specific domains, such as loops for list traversal. To address this limitation, we introduce AbstractBeam: a novel program synthesis framework designed to enhance LambdaBeam by leveraging Library Learning. AbstractBeam identifies and integrates recurring program structures into the DSL, optimizing the synthesis process. Our experimental evaluations demonstrate that AbstractBeam statistically significantly (p < 0.05) outperforms LambdaBeam in the integer list manipulation domain. Beyond solving more tasks, AbstractBeam's program synthesis is also more efficient, requiring less time and fewer candidate programs to generate a solution. Furthermore, our findings indicate that Library Learning effectively enhances program synthesis in domains that are not explicitly designed to showcase its advantages, thereby highlighting the broader applicability of Library Learning.

Explainable Artificial Intelligence is critical in unraveling decision-making processes in complex machine learning models. LIME (Local Interpretable Model-agnostic Explanations) is a well-known XAI framework for image analysis. It utilizes image segmentation to create features to identify relevant areas for classification. Consequently, poor segmentation can compromise the consistency of the explanation and undermine the importance of the segments, affecting the overall interpretability. Addressing these challenges, we introduce DSEG-LIME (Data-Driven Segmentation LIME), featuring: i) a data-driven segmentation for human-recognized feature generation, and ii) a hierarchical segmentation procedure through composition. We benchmark DSEG-LIME on pre-trained models with images from the ImageNet dataset - scenarios without domain-specific knowledge. The analysis includes a quantitative evaluation using established XAI metrics, complemented by a qualitative assessment through a user study. Our findings demonstrate that DSEG outperforms in most of the XAI metrics and enhances the alignment of explanations with human-recognized concepts, significantly improving interpretability. The code is available under: https://github. com/patrick-knab/DSEG-LIME. The code is available under: https://github. com/patrick-knab/DSEG-LIME

Transformers demonstrate impressive performance on a range of reasoning benchmarks. To evaluate the degree to which these abilities are a result of actual reasoning, existing work has focused on developing sophisticated benchmarks for behavioral studies. However, these studies do not provide insights into the internal mechanisms driving the observed capabilities. To improve our understanding of the internal mechanisms of transformers, we present a comprehensive mechanistic analysis of a transformer trained on a synthetic reasoning task. We identify a set of interpretable mechanisms the model uses to solve the task, and validate our findings using correlational and causal evidence. Our results suggest that it implements a depth-bounded recurrent mechanisms that operates in parallel and stores intermediate results in selected token positions. We anticipate that the motifs we identified in our synthetic setting can provide valuable insights into the broader operating principles of transformers and thus provide a basis for understanding more complex models.

Despite the success of deep learning for text and image data, tree-based ensemble models are still state-of-the-art for machine learning with heterogeneous tabular data. However, there is a significant need for tabular-specific gradient-based methods due to their high flexibility. In this paper, we propose $\text{GRANDE}$, $\text{GRA}$die$\text{N}$t-Based $\text{D}$ecision Tree $\text{E}$nsembles, a novel approach for learning hard, axis-aligned decision tree ensembles using end-to-end gradient descent. GRANDE is based on a dense representation of tree ensembles, which affords to use backpropagation with a straight-through operator to jointly optimize all model parameters. Our method combines axis-aligned splits, which is a useful inductive bias for tabular data, with the flexibility of gradient-based optimization. Furthermore, we introduce an advanced instance-wise weighting that facilitates learning representations for both, simple and complex relations, within a single model. We conducted an extensive evaluation on a predefined benchmark with 19 classification datasets and demonstrate that our method outperforms existing gradient-boosting and deep learning frameworks on most datasets. The method is available under: https://github.com/s-marton/GRANDE

The development dynamics of digital innovations for industry, business, and society are producing complex system conglomerates that can no longer be designed centrally and hierarchically in classic development processes. Instead, systems are evolving in DevOps processes in which heterogeneous actors act together on an open platform. Influencing and controlling such dynamically and autonomously changing system landscapes is currently a major challenge and a fundamental interest of service users and providers, as well as operators of the platform infrastructures. In this paper, we propose an architecture for such an emergent software service platform. A software platform that implements this architecture with the underlying engineering methodology is demonstrated by a smart parking lot scenario., Comment: This paper was presented on The Fifteenth International Conference on Adaptive and Self-Adaptive Systems and Applications (ADAPTIVE 2023)

The embedding spaces of image models have been shown to encode a range of social biases such as racism and sexism. Here, we investigate specific factors that contribute to the emergence of these biases in Vision Transformers (ViT). Therefore, we measure the impact of training data, model architecture, and training objectives on social biases in the learned representations of ViTs. Our findings indicate that counterfactual augmentation training using diffusion-based image editing can mitigate biases, but does not eliminate them. Moreover, we find that larger models are less biased than smaller models, and that models trained using discriminative objectives are less biased than those trained using generative objectives. In addition, we observe inconsistencies in the learned social biases. To our surprise, ViTs can exhibit opposite biases when trained on the same data set using different self-supervised objectives. Our findings give insights into the factors that contribute to the emergence of social biases and suggests that we could achieve substantial fairness improvements based on model design choices.

Goal recognition is an important problem in many application domains (e.g., pervasive computing, intrusion detection, computer games, etc.). In many application scenarios, it is important that goal recognition algorithms can recognize goals of an observed agent as fast as possible. However, many early approaches in the area of Plan Recognition As Planning, require quite large amounts of computation time to calculate a solution. Mainly to address this issue, recently, Pereira et al. developed an approach that is based on planning landmarks and is much more computationally efficient than previous approaches. However, the approach, as proposed by Pereira et al., also uses trivial landmarks (i.e., facts that are part of the initial state and goal description are landmarks by definition). In this paper, we show that it does not provide any benefit to use landmarks that are part of the initial state in a planning landmark based goal recognition approach. The empirical results show that omitting initial state landmarks for goal recognition improves goal recognition performance., Comment: Full publication: Wilken, N., Cohausz, L., Bartelt, C., Stuckenschmidt, H. (2023). Planning Landmark Based Goal Recognition Revisited: Does Using Initial State Landmarks Make Sense?. In: Seipel, D., Steen, A. (eds) KI 2023: Advances in Artificial Intelligence. KI 2023. Lecture Notes in Computer Science(), vol 14236. Springer, Cham. arXiv admin note: text overlap with arXiv:2301.10571

Decision Trees (DTs) are commonly used for many machine learning tasks due to their high degree of interpretability. However, learning a DT from data is a difficult optimization problem, as it is non-convex and non-differentiable. Therefore, common approaches learn DTs using a greedy growth algorithm that minimizes the impurity locally at each internal node. Unfortunately, this greedy procedure can lead to inaccurate trees. In this paper, we present a novel approach for learning hard, axis-aligned DTs with gradient descent. The proposed method uses backpropagation with a straight-through operator on a dense DT representation, to jointly optimize all tree parameters. Our approach outperforms existing methods on binary classification benchmarks and achieves competitive results for multi-class tasks. The method is available under: https://github.com/s-marton/GradTree

Goal recognition is an important problem in many application domains (e.g., pervasive computing, intrusion detection, computer games, etc.). In many application scenarios it is important that goal recognition algorithms can recognize goals of an observed agent as fast as possible and with minimal domain knowledge. Hence, in this paper, we propose a hybrid method for online goal recognition that combines a symbolic planning landmark based approach and a data-driven goal recognition approach and evaluate it in a real-world cooking scenario. The empirical results show that the proposed method is not only significantly more efficient in terms of computation time than the state-of-the-art but also improves goal recognition performance. Furthermore, we show that the utilized planning landmark based approach, which was so far only evaluated on artificial benchmark domains, achieves also good recognition performance when applied to a real-world cooking scenario., Comment: 9 pages. Presented at SPARK 2022 (https://icaps22.icaps-conference.org/workshops/SPARK/)

Outlier explanation is the task of identifying a set of features that distinguish a sample from normal data, which is important for downstream (human) decision-making. Existing methods are based on beam search in the space of feature subsets. They quickly becomes computationally expensive, as they require to run an outlier detection algorithm from scratch for each feature subset. To alleviate this problem, we propose a novel outlier explanation algorithm based on Sum-Product Networks (SPNs), a class of probabilistic circuits. Our approach leverages the tractability of marginal inference in SPNs to compute outlier scores in feature subsets. By using SPNs, it becomes feasible to perform backwards elimination instead of the usual forward beam search, which is less susceptible to missing relevant features in an explanation, especially when the number of features is large. We empirically show that our approach achieves state-of-the-art results for outlier explanation, outperforming recent search-based as well as deep learning-based explanation methods

Sum-Product Networks (SPNs) are expressive probabilistic models that provide exact, tractable inference. They achieve this efficiency by making use of local independence. On the other hand, mixtures of exchangeable variable models (MEVMs) are a class of tractable probabilistic models that make use of exchangeability of discrete random variables to render inference tractable. Exchangeability, which arises naturally in relational domains, has not been considered for efficient representation and inference in SPNs yet. The contribution of this paper is a novel probabilistic model which we call Exchangeability-Aware Sum-Product Networks (XSPNs). It contains both SPNs and MEVMs as special cases, and combines the ability of SPNs to efficiently learn deep probabilistic models with the ability of MEVMs to efficiently handle exchangeable random variables. We introduce a structure learning algorithm for XSPNs and empirically show that they can be more accurate than conventional SPNs when the data contains repeated, interchangeable parts., Comment: accepted at IJCAI 2022