ACL 2025 论文列表

Large language models (LLMs) have demonstrated impressive generative capabilities, yet their inner mechanisms remain largely opaque. In this work, we introduce a novel approach to interpret LLMs generation process through the lens of an explicit Bayesian framework by inferring latent topic variables via variational inference. Specifically, we leverage a variational autoencoder-based neural topic model to dynamically approximate the posterior distribution over the high-level latent topic variables at each generation step. By reconstructing the LLM’s next-token predictions through these latent topics and maintaining a regularized latent space, our method yields interpretable and diverse topic representations but also has the ability to effectively captures semantic shifts throughout the text. We validate our approach on multiple datasets, showing that our latent topics outperform state-of-the-art topic models on intrinsic measures of coherence and diversity. Furthermore, we demonstrate the utility of our approach in downstream applications by using the inferred topic distributions to retrieve relevant demonstration examples for in-context learning, resulting in significant gains on classification and summarization tasks.

Large Language Models (LLMs) are increasingly used in tasks requiring interpretive and inferential accuracy. In this paper, we introduce ExpliCa, a new dataset for evaluating LLMs in explicit causal reasoning. ExpliCa uniquely integrates both causal and temporal relations presented in different linguistic orders and explicitly expressed by linguistic connectives. The dataset is enriched with crowdsourced human acceptability ratings. We tested LLMs on ExpliCa through prompting and perplexity-based metrics. We assessed seven commercial and open-source LLMs, revealing that even top models struggle to reach 0.80 accuracy. Interestingly, models tend to confound temporal relations with causal ones, and their performance is also strongly influenced by the linguistic order of the events. Finally, perplexity-based scores and prompting performance are differently affected by model size.

The success of Large Language Models (LLMs) in human-AI collaborative decision-making hinges on their ability to provide trustworthy, gradual, and tailored explanations. Solving complex puzzles, such as Sudoku, offers a canonical example of this collaboration, where clear and customized explanations often hold greater importance than the final solution. In this study, we evaluate the performance of five LLMs in solving and explaining 6x6 Sudoku puzzles. While one LLM demonstrates limited success in solving puzzles, none can explain the solution process in a manner that reflects strategic reasoning or intuitive problem-solving. These findings underscore significant challenges that must be addressed before LLMs can become effective partners in human-AI collaborative decision-making.

The detection of sexism in online content remains an open problem, as harmful language disproportionately affects women and marginalized groups. While automated systems for sexism detection have been developed, they still face two key challenges: data sparsity and the nuanced nature of sexist language. Even in large, well-curated datasets like the Explainable Detection of Online Sexism (EDOS), severe class imbalance hinders model generalization. Additionally, the overlapping and ambiguous boundaries of fine-grained categories introduce substantial annotator disagreement, reflecting the difficulty of interpreting nuanced expressions of sexism. To address these challenges, we propose two prompt-based data augmentation techniques: Definition-based Data Augmentation (DDA), which leverages category-specific definitions to generate semantically-aligned synthetic examples, and Contextual Semantic Expansion (CSE), which targets systematic model errors by enriching examples with task-specific semantic features. To further improve reliability in fine-grained classification, we introduce an ensemble strategy that resolves prediction ties by aggregating complementary perspectives from multiple language models. Our experimental evaluation on the EDOS dataset demonstrates state-of-the-art performance across all tasks, with notable improvements of macro F1 by 1.5 points for binary classification (Task A) and 4.1 points for fine-grained classification (Task C).

Large language models (LLMs) often generate hallucinated content, making it crucial to identify and quantify inconsistencies in their outputs. We introduce HaluMap, a post-hoc framework that detects hallucinations by mapping entailment and contradiction relations between source inputs and generated outputs using a natural language inference (NLI) model. To improve reliability, we propose a calibration step leveraging intra-text relations to refine predictions. HaluMap outperforms state-of-the-art NLI-based methods by five percentage points compared to other training-free approaches, while providing clear, interpretable explanations. As a training-free and model-agnostic approach, HaluMap offers a practical solution for verifying LLM outputs across diverse NLP tasks. The resources of this paper are available at https://github.com/caisa-lab/acl25-halumap.

Depression is a widespread mental health disorder, and clinical interviews are the gold standard for assessment. However, their reliance on scarce professionals highlights the need for automated detection. Current systems mainly employ black-box neural networks, which lack interpretability, which is crucial in mental health contexts. Some attempts to improve interpretability use post-hoc LLM generation but suffer from hallucination. To address these limitations, we propose RED, a Retrieval-augmented generation framework for Explainable depression Detection. RED retrieves evidence from clinical interview transcripts, providing explanations for predictions. Traditional query-based retrieval systems use a one-size-fits-all approach, which may not be optimal for depression detection, as user backgrounds and situations vary. We introduce a personalized query generation module that combines standard queries with user-specific background inferred by LLMs, tailoring retrieval to individual contexts. Additionally, to enhance LLM performance in social intelligence, we augment LLMs by retrieving relevant knowledge from a social intelligence datastore using an event-centric retriever. Experimental results on the real-world benchmark demonstrate RED’s effectiveness compared to neural networks and LLM-based baselines.

Large language models (LLMs) can explain grammatical rules, yet they often fail to apply those rules when judging sentence acceptability. We present grammar prompting, an explain-then-process paradigm: a large LLM first produces a concise explanation of the relevant syntactic phenomenon, then that explanation is fed back as additional context to the target model – either an LLM or a smaller language model (SLM) – before deciding which sentence of a minimal pair is grammatical. On the English BLiMP, Chinese SLING, and Russian RuBLiMP benchmarks, this simple prompt design yields substantial improvements over strong baselines across a wide range of syntactic phenomena. Feeding an LLM’s metalinguistic explanation back to the target model bridges the gap between knowing a rule and using it. On SLMs, grammar prompting alone trims the average LLM-SLM accuracy gap by 20%, and when paired with chain-of-thought, by 56% (13.0 pp → 5.8 pp), all at negligible cost. The lightweight, language-agnostic cue lets low-cost SLMs approach frontier-LLM performance in multilingual settings.

In search settings, calibrating the scores during the ranking process to quantities such as click-through rates or relevance levels enhances a system’s usefulness and trustworthiness for downstream users. While previous research has improved this notion of calibration for low complexity learning-to-rank models, the larger data demands and parameter count specific to modern neural text rankers produce unique obstacles that hamper the efficacy of methods intended for the learning-to-rank setting.This paper proposes exploiting large language models (LLMs) to provide relevance and uncertainty signals for these neural text rankers to produce scale-calibrated scores through Monte Carlo sampling of natural language explanations (NLEs). Our approach transforms the neural ranking task from ranking textual query-document pairs to ranking corresponding synthesized NLEs. Comprehensive experiments on two popular document ranking datasets show that the NLE-based calibration approach consistently outperforms past calibration methods and LLM-based methods for ranking, calibration, and query performance prediction tasks.

Recent advancements in Large Language Models (LLMs) have significantly propelled the development of Conversational Recommendation Agents (CRAs). However, these agents often generate short-sighted responses that fail to sustain user guidance and meet expectations. Although preference optimization has proven effective in aligning LLMs with user expectations, it remains costly and performs poorly in multi-turn dialogue. To address this challenge, we introduce a novel multi-turn preference optimization (MTPO) paradigm **ECPO**, which leverages Expectation Confirmation Theory to explicitly model the evolution of user satisfaction throughout multi-turn dialogues, uncovering the underlying causes of dissatisfaction. These causes can be utilized to support targeted optimization of unsatisfactory responses, thereby achieving turn-level preference optimization. ECPO eliminates the significant sampling overhead of existing MTPO methods while ensuring the optimization process drives meaningful improvements. To support ECPO, we also introduce an LLM-based user simulator, **AILO**, to simulate user feedback and expectation confirmation during conversational recommendations. Experimental results show that ECPO significantly enhances CRA’s interaction capabilities, offering notable improvements in both efficiency and effectiveness over existing MTPO methods.

Recent studies provide large language models (LLMs) with textual task-solving experiences via prompts to improve their performance.However, previous methods rely on substantial human labor or time to gather such experiences for each task, which is impractical given the growing variety of task types in user queries to LLMs.To address this issue, we design an autonomous experience transfer framework to explore whether LLMs can mimic human cognitive intelligence to autonomously transfer experience from existing source tasks to newly encountered target tasks. This not only allows the acquisition of experience without extensive costs of previous methods, but also offers a novel path for the generalization of LLMs.Experimental results on 13 datasets demonstrate that our framework effectively improves the performance of LLMs. Furthermore, we provide a detailed analysis of each module in the framework.

Large Language Models (LLMs) have shown potential in generating hypothetical documents for query expansion, thereby enhancing information retrieval performance. However, the efficacy of this method is highly dependent on the quality of the generated documents, which often requires complex prompt strategies and the integration of advanced dense retrieval techniques. This can be both costly and computationally intensive. To mitigate these limitations, we explore the use of zero-shot LLM-based query expansion to improve sparse retrieval, particularly for learned sparse retrievers. We introduce a novel fusion ranking framework, Exp4Fuse, which enhances the performance of sparse retrievers through an indirect application of zero-shot LLM-based query expansion. Exp4Fuse operates by simultaneously considering two retrieval routes—one based on the original query and the other on the LLM-augmented query. It then generates two ranked lists using a sparse retriever and fuses them using a modified reciprocal rank fusion method. We conduct extensive evaluations of Exp4Fuse against leading LLM-based query expansion methods and advanced retrieval techniques on three MS MARCO-related datasets and seven low-resource datasets. Experimental results reveal that Exp4Fuse not only surpasses existing LLM-based query expansion methods in enhancing sparse retrievers but also, when combined with advanced sparse retrievers, achieves SOTA results on several benchmarks. This highlights the superior performance and effectiveness of Exp4Fuse in improving query expansion for sparse retrieval.

Multiple-choice questions (MCQs) are a widely used and vital assessment format for evaluating large language models (LLMs). This study reveals that LLMs are susceptible to “cognitive load” caused by distractor options in MCQs, leading to excessive attention to distractors and consequent vacillation between correct and incorrect options. To mitigate this cognitive burden, we introduce a novel reasoning prompt strategy, called EoT, which effectively reduces cognitive load by steering the model’s attention away from erroneous options. This enables the model to focus more effectively on reasonable answers. Additionally, by documenting the elimination process, EoT enhances the transparency and interpretability of the model’s reasoning. Experimental results demonstrate that EoT, as a plug-and-play approach, significantly reduces cognitive load and improves performance, showcasing its potential to enhance both the accuracy and interpretability of LLMs.

Evaluating personalized text generated by large language models (LLMs) is challenging, as only the LLM user, i.e. prompt author, can reliably assess the output, but re-engaging the same individuals across studies is infeasible. This paper addresses the challenge of evaluating personalized text generation by introducing ExPerT, an explainable reference-based evaluation framework. ExPerT leverages an LLM to extract atomic aspects and their evidences from the generated and reference texts, match the aspects, and evaluate their alignment based on content and writing style—two key attributes in personalized text generation. Additionally, ExPerT generates detailed, fine-grained explanations for every step of the evaluation process, enhancing transparency and interpretability. Our experiments demonstrate that ExPerT achieves a 7.2% relative improvement in alignment with human judgments compared to the state-of-the-art text generation evaluation methods. Furthermore, human evaluators rated the usability of ExPerT’s explanations at 4.7 out of 5, highlighting its effectiveness in making evaluation decisions more interpretable.

Large language models (LLMs) are trained on extensive historical corpora, but their ability to understand time and maintain temporal awareness of time-evolving factual knowledge remains limited. Previous studies often neglect the critical aspect of utilizing knowledge from various sources. To address this gap, we introduce EvolveBench, a comprehensive benchmark that evaluates temporal competence along five key dimensions: Cognition, which examines the ability to recall and contextualize historical facts. Awareness, which tests LLMs’ awareness of temporal misalignment between external inputs and the temporal context of a query. Trustworthiness, which assesses whether models can identify and appropriately refuse queries based on invalid timestamps. Understanding, which focuses on interpreting both explicit dates and implicit historical markers. Finally, reasoning evaluates the capacity to analyze temporal relationships and draw accurate inferences. Evaluating 15 widely used LLMs on EvolveBench shows that GPT-4o achieves the highest average EM score of 79.36, while the open-source Llama3.1-70B demonstrates notable strength in handling temporally misaligned contexts with an average score of 72.47. Despite these advances, all models still struggle with handling temporal misaligned context. Our code and dataset are available at https://github.com/zzysjtuiwct/EvolveBench.

Knowledge utilization is a critical aspect of LLMs, and understanding how they adapt to evolving knowledge is essential for their effective deployment. However, existing benchmarks are predominantly static, failing to capture the evolving nature of LLMs and knowledge, leading to inaccuracies and vulnerabilities such as contamination. In this paper, we introduce EvoWiki, an evolving dataset designed to reflect knowledge evolution by categorizing information into stable, evolved, and uncharted states. EvoWiki is fully auto-updatable, enabling precise evaluation of continuously changing knowledge and newly released LLMs. Through experiments with Retrieval-Augmented Generation (RAG) and Continual Learning (CL), we evaluate how effectively LLMs adapt to evolving knowledge. Our results indicate that current models often struggle with evolved knowledge, frequently providing outdated or incorrect responses. Moreover, the dataset highlights a synergistic effect between RAG and CL, demonstrating their potential to better adapt to evolving knowledge. EvoWiki provides a robust benchmark for advancing future research on the knowledge evolution capabilities of large language models.

With the widespread of Large Language Models (LLMs), there has been an increasing need to detect LLM-generated texts, prompting extensive research in this area. However, existing detection methods mainly evaluate on static benchmarks, which neglect the evolving nature of LLMs. Relying on existing static benchmarks could create a misleading sense of security, overestimating the real-world effectiveness of detection methods.To bridge this gap, we introduce EvoBench, a dynamic benchmark considering a new dimension of generalization across continuously evolving LLMs.EvoBench categorizes the evolving LLMs into (1) updates over time and (2) developments like finetuning and pruning, covering 7 LLM families and their 29 evolving versions. To measure the generalization across evolving LLMs, we introduce a new EMG (Evolving Model Generalization) metric. Our evaluation of 14 detection methods on EvoBench reveals that they all struggle to maintain generalization when confronted with evolving LLMs. To mitigate the generalization problems, we further propose improvement strategies. For zero-shot detectors, we propose pruning the scoring model to extract shared features. For supervised detectors, we also propose a practical training strategy.Our research sheds light on critical challenges in real-world LLM-generated text detection and represents a significant step toward practical applications.

Retrieval-augmented generation (RAG) systems often struggle with narrative-rich documents and event-centric reasoning, particularly when synthesizing information across multiple sources. We present EventRAG, a novel framework that enhances text generation through structured event representations. We first construct an Event Knowledge Graph by extracting events and merging semantically equivalent nodes across documents, while expanding under-connected relationships. We then employ an iterative retrieval and inference strategy that explicitly captures temporal dependencies and logical relationships across events. Experiments on UltraDomain and MultiHopRAG benchmarks show EventRAG’s superiority over baseline RAG systems, with substantial gains in generation effectiveness, logical consistency, and multi-hop reasoning accuracy. Our work advances RAG systems by integrating structured event semantics with iterative inference, particularly benefiting scenarios requiring temporal and logical reasoning across documents.

For document-level event argument extraction, existing role-based span selection strategies suffer from several limitations: (1) ignoring interrelations among arguments within an event instance; (2) relying on pre-trained language models to capture role semantics at either the event pattern or document, without leveraging pattern-instance associations. To address these limitations, this paper proposes a multi-round role representation learning strategy. First, we construct an event pattern-instance graph (EPIG) to comprehensively capture the role semantics embedded in various direct and indirect associations, including those among roles within event patterns, arguments within event instances, and the alignments between patterns and instances. Second, to enhance the learning of role node representation in the graph, we optimize the update mechanisms for both node and edge representations in the EPIG graph. By leveraging the graph attention network, we iteratively update the representations of role nodes and role edges. The role representations learned from the EPIG are then integrated into the original role representations, further enriching their semantic information. Finally, a role representation memory module and a multi-round learning strategy is proposed to retain and refine role representations learned from previously analyzed documents. This memory mechanism enhances the prediction performance in subsequent rounds of span selection. Extensive experiments on three datasets verify the effectiveness of the model.

Large Language Models (LLMs) recently achieved great success in medical text summarization by simply using in-context learning. However, these recent efforts do not perform fine-grained evaluations under difficult settings where LLMs might fail. They typically report performance scores over the entire dataset. Through our benchmarking study, we show that LLMs show a significant performance drop for data points with high concentration of out-of-vocabulary (OOV) words or with high novelty. Vocabulary adaptation is an intuitive solution to this vocabulary mismatch issue where the LLM vocabulary gets updated with certain expert domain (here, medical) words or subwords. An interesting finding from our study is that Llama-3.1, even with a vocabulary size of around 128K tokens, still faces _over-fragmentation_ issue with medical words. To that end, we show vocabulary adaptation helps improve the LLM summarization performance even in difficult settings. Through extensive experimentation of multiple vocabulary adaptation strategies, two continual pretraining strategies, and three benchmark medical summarization datasets, we gain valuable insights into the role of vocabulary adaptation strategies for customizing LLMs to the medical domain. We also performed a human evaluation study with medical experts where they found that vocabulary adaptation results in more relevant and faithful summaries. Our codebase is made publicly available at https://github.com/gb-kgp/LLM-MedicalSummarization-Benchmark.