Search

In-context learning (ICL) has proven to be a significant capability with the advancement of Large Language models (LLMs). By instructing LLMs using few-shot demonstrative examples, ICL enables them to perform a wide range of tasks without needing to update millions of parameters. This paper presents a unified framework for LLMs that allows them to self-select influential in-context examples to compose their contexts; self-rank candidates with different demonstration compositions; self-optimize the demonstration selection and ordering through reinforcement learning. Specifically, our method designs a parameter-efficient retrieval head that generates the optimized demonstration after training with rewards from LLM's own preference. Experimental results validate the proposed method's effectiveness in enhancing ICL performance. Additionally, our approach effectively identifies and selects the most representative examples for the current task, and includes more diversity in retrieval., Comment: 12 pages, 3 figures

Large Language Models (LLMs) have demonstrated impressive in-context learning (ICL) capabilities from few-shot demonstration exemplars. While recent learning-based demonstration selection methods have proven beneficial to ICL by choosing more useful exemplars, their underlying mechanisms are opaque, hindering efforts to address limitations such as high training costs and poor generalization across tasks. These methods generally assume the selection process captures similarities between the exemplar and the target instance, however, it remains unknown what kinds of similarities are captured and vital to performing ICL. To dive into this question, we analyze the working mechanisms of the learning-based demonstration selection methods and empirically identify two important factors related to similarity measurement: 1) The ability to integrate different levels of task-agnostic text similarities between the input of exemplars and test cases enhances generalization power across different tasks. 2) Incorporating task-specific labels when measuring the similarities significantly improves the performance on each specific task. We validate these two findings through extensive quantitative and qualitative analyses across ten datasets and various LLMs. Based on our findings, we introduce two effective yet simplified exemplar selection methods catering to task-agnostic and task-specific demands, eliminating the costly LLM inference overhead.

Emergence, broadly conceptualized as the ``intelligent'' behaviors of LLMs, has recently been studied and proved challenging to quantify due to the lack of a measurable definition. Most commonly, it has been estimated statistically through model performances across extensive datasets and tasks, which consumes significant resources. In addition, such estimation is difficult to interpret and may not accurately reflect the models' intrinsic emergence. In this work, we propose a quantifiable solution for estimating emergence. Inspired by emergentism in dynamics, we quantify the strength of emergence by comparing the entropy reduction of the macroscopic (semantic) level with that of the microscopic (token) level, both of which are derived from the representations within the transformer block. Using a low-cost estimator, our quantification method demonstrates consistent behaviors across a suite of LMs (GPT-2, GEMMA, etc.) under both in-context learning (ICL) and natural sentences. Empirical results show that (1) our method gives consistent measurements which align with existing observations based on performance metrics, validating the effectiveness of our emergence quantification; (2) our proposed metric uncovers novel emergence patterns such as the correlations between the variance of our metric and the number of ``shots'' in ICL, which further suggests a new way of interpreting hallucinations in LLMs; (3) we offer a potential solution towards estimating the emergence of larger and closed-resource LMs via smaller LMs like GPT-2. Our codes are available at: https://github.com/Zodiark-ch/Emergence-of-LLMs/.

In-context Learning (ICL) has emerged as a powerful capability alongside the development of scaled-up large language models (LLMs). By instructing LLMs using few-shot demonstrative examples, ICL enables them to perform a wide range of tasks without updating millions of parameters. However, the precise contributions of demonstrations towards improving end-task performance have not been thoroughly investigated in recent analytical studies. In this paper, we empirically decompose the overall performance of ICL into three dimensions, label space, format, and discrimination, and we evaluate four general-purpose LLMs across a diverse range of tasks. Counter-intuitively, we find that the demonstrations have a marginal impact on provoking discriminative knowledge of language models. However, ICL exhibits significant efficacy in regulating the label space and format, which helps LLMs respond to desired label words. We then demonstrate that this ability functions similar to detailed instructions for LLMs to follow. We additionally provide an in-depth analysis of the mechanism of retrieval helping with ICL. Our findings demonstrate that retrieving the semantically similar examples notably boosts the model's discriminative capability. However, we also observe a trade-off in selecting good in-context examples regarding label diversity., Comment: 39 pages, 8 figures. Accepted by Conference On Language Modeling (COLM) 2024

Large Language Models (LLMs) are emerging as promising approaches to enhance session-based recommendation (SBR), where both prompt-based and fine-tuning-based methods have been widely investigated to align LLMs with SBR. However, the former methods struggle with optimal prompts to elicit the correct reasoning of LLMs due to the lack of task-specific feedback, leading to unsatisfactory recommendations. Although the latter methods attempt to fine-tune LLMs with domain-specific knowledge, they face limitations such as high computational costs and reliance on open-source backbones. To address such issues, we propose a Reflective Reinforcement Large Language Model (Re2LLM) for SBR, guiding LLMs to focus on specialized knowledge essential for more accurate recommendations effectively and efficiently. In particular, we first design the Reflective Exploration Module to effectively extract knowledge that is readily understandable and digestible by LLMs. To be specific, we direct LLMs to examine recommendation errors through self-reflection and construct a knowledge base (KB) comprising hints capable of rectifying these errors. To efficiently elicit the correct reasoning of LLMs, we further devise the Reinforcement Utilization Module to train a lightweight retrieval agent. It learns to select hints from the constructed KB based on the task-specific feedback, where the hints can serve as guidance to help correct LLMs reasoning for better recommendations. Extensive experiments on multiple real-world datasets demonstrate that our method consistently outperforms state-of-the-art methods., Comment: 11 pages, 4 figures

Dense retrievers and retrieval-augmented language models have been widely used in various NLP applications. Despite being designed to deliver reliable and secure outcomes, the vulnerability of retrievers to potential attacks remains unclear, raising concerns about their security. In this paper, we introduce a novel scenario where the attackers aim to covertly disseminate targeted misinformation, such as hate speech or advertisement, through a retrieval system. To achieve this, we propose a perilous backdoor attack triggered by grammar errors in dense passage retrieval. Our approach ensures that attacked models can function normally for standard queries but are manipulated to return passages specified by the attacker when users unintentionally make grammatical mistakes in their queries. Extensive experiments demonstrate the effectiveness and stealthiness of our proposed attack method. When a user query is error-free, our model consistently retrieves accurate information while effectively filtering out misinformation from the top-k results. However, when a query contains grammar errors, our system shows a significantly higher success rate in fetching the targeted content.

Large language models (LLMs) have demonstrated remarkable proficiency in understanding and generating responses to complex queries through large-scale pre-training. However, the efficacy of these models in memorizing and reasoning among large-scale structured knowledge, especially world knowledge that explicitly covers abundant factual information remains questionable. Addressing this gap, our research investigates whether LLMs can effectively store, recall, and reason with knowledge on a large scale comparable to latest knowledge bases (KBs) such as Wikidata. Specifically, we focus on three crucial aspects to study the viability: (1) the efficiency of LLMs with different sizes in memorizing the exact knowledge in the large-scale KB; (2) the flexibility of recalling the memorized knowledge in response to natural language queries; (3) the capability to infer new knowledge through reasoning. Our findings indicate that while LLMs hold promise as large-scale KBs capable of retrieving and responding with flexibility, enhancements in their reasoning capabilities are necessary to fully realize their potential.

The proliferation of fake news has emerged as a severe societal problem, raising significant interest from industry and academia. While existing deep-learning based methods have made progress in detecting fake news accurately, their reliability may be compromised caused by the non-transparent reasoning processes, poor generalization abilities and inherent risks of integration with large language models (LLMs). To address this challenge, we propose {\methodname}, a novel framework for trustworthy fake news detection that prioritizes explainability, generalizability and controllability of models. This is achieved via a dual-system framework that integrates cognition and decision systems, adhering to the principles above. The cognition system harnesses human expertise to generate logical predicates, which guide LLMs in generating human-readable logic atoms. Meanwhile, the decision system deduces generalizable logic rules to aggregate these atoms, enabling the identification of the truthfulness of the input news across diverse domains and enhancing transparency in the decision-making process. Finally, we present comprehensive evaluation results on four datasets, demonstrating the feasibility and trustworthiness of our proposed framework. Our implementation is available at \url{https://github.com/less-and-less-bugs/Trust_TELLER}., Comment: Accepted by Findings of ACL 2024. 28 pages, 2 figures, 16 tables

While recent Large Language Models (LLMs) have proven useful in answering user queries, they are prone to hallucination, and their responses often lack credibility due to missing references to reliable sources. An intuitive solution to these issues would be to include in-text citations referring to external documents as evidence. While previous works have directly prompted LLMs to generate in-text citations, their performances are far from satisfactory, especially when it comes to smaller LLMs. In this work, we propose an effective training framework using fine-grained rewards to teach LLMs to generate highly supportive and relevant citations, while ensuring the correctness of their responses. We also conduct a systematic analysis of applying these fine-grained rewards to common LLM training strategies, demonstrating its advantage over conventional practices. We conduct extensive experiments on Question Answering (QA) datasets taken from the ALCE benchmark and validate the model's generalizability using EXPERTQA. On LLaMA-2-7B, the incorporation of fine-grained rewards achieves the best performance among the baselines, even surpassing that of GPT-3.5-turbo., Comment: Accepted by ACL 2024

Making inferences in text comprehension to understand the meaning is essential in language processing. This work studies the entailment verification (EV) problem of multi-sentence premises that requires a system to make multiple inferences implicitly. Studying EV for such complex premises is important because modern NLP problems, such as detecting inconsistent model-generated rationales, require complex multi-hop reasoning. However, current textual inference datasets mostly contain short premises that only partially focus on these challenges. To address this, we compile an EV benchmark that includes datasets from three NLP domains (NLI, contextual QA, and rationales) containing multi-sentence premises. On benchmarking humans and LLMs, we find that LLMs are better than humans in multi-hop reasoning across extended contexts, while humans perform better in simple deductive reasoning tasks. We also finetune a Flan-T5 model for EV using two training objectives to obtain a strong open-source model that outperforms GPT-3.5 and rivals GPT-4. Finally, we use this model to filter out inconsistent model-generated rationales in self-consistency decoding, resulting in a 6% accuracy improvement on average across three MCQ datasets.

Social media misinformation harms individuals and societies and is potentialized by fast-growing multi-modal content (i.e., texts and images), which accounts for higher "credibility" than text-only news pieces. Although existing supervised misinformation detection methods have obtained acceptable performances in key setups, they may require large amounts of labeled data from various events, which can be time-consuming and tedious. In turn, directly training a model by leveraging a publicly available dataset may fail to generalize due to domain shifts between the training data (a.k.a. source domains) and the data from target domains. Most prior work on domain shift focuses on a single modality (e.g., text modality) and ignores the scenario where sufficient unlabeled target domain data may not be readily available in an early stage. The lack of data often happens due to the dynamic propagation trend (i.e., the number of posts related to fake news increases slowly before catching the public attention). We propose a novel robust domain and cross-modal approach (\textbf{RDCM}) for multi-modal misinformation detection. It reduces the domain shift by aligning the joint distribution of textual and visual modalities through an inter-domain alignment module and bridges the semantic gap between both modalities through a cross-modality alignment module. We also propose a framework that simultaneously considers application scenarios of domain generalization (in which the target domain data is unavailable) and domain adaptation (in which unlabeled target domain data is available). Evaluation results on two public multi-modal misinformation detection datasets (Pheme and Twitter Datasets) evince the superiority of the proposed model. The formal implementation of this paper can be found in this link: https://github.com/less-and-less-bugs/RDCM, Comment: Accepted by TIFS 2023

Large language models (LLMs) have showcased their capability with few-shot inference known as in-context learning. However, in-domain demonstrations are not always readily available in real scenarios, leading to cross-domain in-context learning. Besides, LLMs are still facing challenges in long-tail knowledge in unseen and unfamiliar domains. The above limitations demonstrate the necessity of Unsupervised Domain Adaptation (UDA). In this paper, we study the UDA problem under an in-context learning setting to adapt language models from the source domain to the target domain without any target labels. The core idea is to retrieve a subset of cross-domain elements that are the most similar to the query, and elicit language model to adapt in an in-context manner by learning both target domain distribution and the discriminative task signal simultaneously with the augmented cross-domain in-context examples. We devise different prompting and training strategies, accounting for different LM architectures to learn the target distribution via language modeling. With extensive experiments on Sentiment Analysis (SA) and Named Entity Recognition (NER) tasks, we thoroughly study the effectiveness of ICL for domain transfer and demonstrate significant improvements over baseline models., Comment: EMNLP 2023

Node.js provides Node.js applications with system interaction capabilities using system calls. However, such convenience comes with a price, i.e., the attack surface of JavaScript arbitrary code execution (ACE) vulnerabilities is expanded to the system call level. There lies a noticeable gap between existing protection techniques in the JavaScript code level (either by code debloating or read-write-execute permission restriction) and a targeted defense for emerging critical system call level exploitation. To fill the gap, we design and implement HODOR, a lightweight runtime protection system based on enforcing precise system call restrictions when running a Node.js application. HODOR achieved this by addressing several nontrivialial technical challenges. First, HODOR requires to construct high-quality call graphs for both the Node.js application (in JavaScript) and its underlying Node.js framework (in JavaScript and C/C++). Specifically, HODOR incorporates several important optimizations in both the JavaScript and C/C++ level to improve the state-of-the-art tools for building more precise call graphs. Then, HODOR creates the main-thread whitelist and the thread-pool whitelist respectively containing the identified necessary system calls based on the call graphs mappings. Finally, with the whitelists, HODOR implements lightweight system call restriction using the Linux kernel feature Secure Computing Mode (seccomp) to shrink the attack surface. We utilize HODOR to protect 83 real-world Node.js applications compromised by arbitrary code/command execution attacks. HODOR could reduce the attack surface to 16.75% on average with negligible runtime overhead (i.e., <3%).

Multimodal misinformation on online social platforms is becoming a critical concern due to increasing credibility and easier dissemination brought by multimedia content, compared to traditional text-only information. While existing multimodal detection approaches have achieved high performance, the lack of interpretability hinders these systems' reliability and practical deployment. Inspired by NeuralSymbolic AI which combines the learning ability of neural networks with the explainability of symbolic learning, we propose a novel logic-based neural model for multimodal misinformation detection which integrates interpretable logic clauses to express the reasoning process of the target task. To make learning effective, we parameterize symbolic logical elements using neural representations, which facilitate the automatic generation and evaluation of meaningful logic clauses. Additionally, to make our framework generalizable across diverse misinformation sources, we introduce five meta-predicates that can be instantiated with different correlations. Results on three public datasets (Twitter, Weibo, and Sarcasm) demonstrate the feasibility and versatility of our model., Comment: Accepted by Findings of ACL 23. 9 pages, 6 figures

Despite the much discussed capabilities of today's language models, they are still prone to silly and unexpected commonsense failures. We consider a retrospective verification approach that reflects on the correctness of LM outputs, and introduce Vera, a general-purpose model that estimates the plausibility of declarative statements based on commonsense knowledge. Trained on ~7M commonsense statements created from 19 QA datasets and two large-scale knowledge bases, and with a combination of three training objectives, Vera is a versatile model that effectively separates correct from incorrect statements across diverse commonsense domains. When applied to solving commonsense problems in the verification format, Vera substantially outperforms existing models that can be repurposed for commonsense verification, and it further exhibits generalization capabilities to unseen tasks and provides well-calibrated outputs. We find that Vera excels at filtering LM-generated commonsense knowledge and is useful in detecting erroneous commonsense statements generated by models like ChatGPT in real-world settings., Comment: EMNLP 2023 main conference

Sarcasm is a linguistic phenomenon indicating a discrepancy between literal meanings and implied intentions. Due to its sophisticated nature, it is usually challenging to be detected from the text itself. As a result, multi-modal sarcasm detection has received more attention in both academia and industries. However, most existing techniques only modeled the atomic-level inconsistencies between the text input and its accompanying image, ignoring more complex compositions for both modalities. Moreover, they neglected the rich information contained in external knowledge, e.g., image captions. In this paper, we propose a novel hierarchical framework for sarcasm detection by exploring both the atomic-level congruity based on multi-head cross attention mechanism and the composition-level congruity based on graph neural networks, where a post with low congruity can be identified as sarcasm. In addition, we exploit the effect of various knowledge resources for sarcasm detection. Evaluation results on a public multi-modal sarcasm detection dataset based on Twitter demonstrate the superiority of our proposed model., Comment: Accepted by EMNLP2022

In question answering requiring common sense, language models (e.g., GPT-3) have been used to generate text expressing background knowledge that helps improve performance. Yet the cost of working with such models is very high; in this work, we finetune smaller language models to generate useful intermediate context, referred to here as elaborations. Our framework alternates between updating two language models -- an elaboration generator and an answer predictor -- allowing each to influence the other. Using less than 0.5% of the parameters of GPT-3, our model outperforms alternatives with similar sizes and closes the gap on GPT-3 on four commonsense question answering benchmarks. Human evaluations show that the quality of the generated elaborations is high.

In this work, we study Unsupervised Domain Adaptation (UDA) in a challenging self-supervised approach. One of the difficulties is how to learn task discrimination in the absence of target labels. Unlike previous literature which directly aligns cross-domain distributions or leverages reverse gradient, we propose Domain Confused Contrastive Learning (DCCL) to bridge the source and the target domains via domain puzzles, and retain discriminative representations after adaptation. Technically, DCCL searches for a most domain-challenging direction and exquisitely crafts domain confused augmentations as positive pairs, then it contrastively encourages the model to pull representations towards the other domain, thus learning more stable and effective domain invariances. We also investigate whether contrastive learning necessarily helps with UDA when performing other data augmentations. Extensive experiments demonstrate that DCCL significantly outperforms baselines., Comment: 14 pages, 7 figures, NAACL 2022

Fine-grained aspect extraction is an essential sub-task in aspect based opinion analysis. It aims to identify the aspect terms (a.k.a. opinion targets) of a product or service in each sentence. However, expensive annotation process is usually involved to acquire sufficient token-level labels for each domain. To address this limitation, some previous works propose domain adaptation strategies to transfer knowledge from a sufficiently labeled source domain to unlabeled target domains. But due to both the difficulty of fine-grained prediction problems and the large domain gap between domains, the performance remains unsatisfactory. This work conducts a pioneer study on leveraging sentence-level aspect category labels that can be usually available in commercial services like review sites to promote token-level transfer for the extraction purpose. Specifically, the aspect category information is used to construct pivot knowledge for transfer with assumption that the interactions between sentence-level aspect category and token-level aspect terms are invariant across domains. To this end, we propose a novel multi-level reconstruction mechanism that aligns both the fine-grained and coarse-grained information in multiple levels of abstractions. Comprehensive experiments demonstrate that our approach can fully utilize sentence-level aspect category labels to improve cross-domain aspect extraction with a large performance gain., Comment: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

Information extraction (IE) aims to produce structured information from an input text, e.g., Named Entity Recognition and Relation Extraction. Various attempts have been proposed for IE via feature engineering or deep learning. However, most of them fail to associate the complex relationships inherent in the task itself, which has proven to be especially crucial. For example, the relation between 2 entities is highly dependent on their entity types. These dependencies can be regarded as complex constraints that can be efficiently expressed as logical rules. To combine such logic reasoning capabilities with learning capabilities of deep neural networks, we propose to integrate logical knowledge in the form of first-order logic into a deep learning system, which can be trained jointly in an end-to-end manner. The integrated framework is able to enhance neural outputs with knowledge regularization via logic rules, and at the same time update the weights of logic rules to comply with the characteristics of the training data. We demonstrate the effectiveness and generalization of the proposed model on multiple IE tasks., Comment: Accepted in AAAI 2020

In aspect-based sentiment analysis, most existing methods either focus on aspect/opinion terms extraction or aspect terms categorization. However, each task by itself only provides partial information to end users. To generate more detailed and structured opinion analysis, we propose a finer-grained problem, which we call category-specific aspect and opinion terms extraction. This problem involves the identification of aspect and opinion terms within each sentence, as well as the categorization of the identified terms. To this end, we propose an end-to-end multi-task attention model, where each task corresponds to aspect/opinion terms extraction for a specific category. Our model benefits from exploring the commonalities and relationships among different tasks to address the data sparsity issue. We demonstrate its state-of-the-art performance on three benchmark datasets.