AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

ACL 2026

Thought-Action Graph Reasoning: Faithful and Efficient Reasoning of Large Language Models via Reusing Past Experience

Zhixiao Qi, Feng Huang, Yunqi Zhang, Shijie Zhang, Qingqing Sun, Yongfeng Huang, Minghu Jiang, Shuai Chen, Tianyi Zhang

Large language models (LLMs) often hallucinate in question answering (QA) tasks due to a lack of factual knowledge. While integrating knowledge graphs (KGs) with LLMs has alleviated this issue, existing methods suffer from poor generalization or low reasoning efficiency, and critically, they overlook the learning and reuse of reasoning paths from past experiences. To address these challenges, we introduce Thought-Action Graph (TAG), a structured repository of reasoning experiences. TAG decomposes successful LLM-KG interaction trajectories into fine-grained semantic operators, which are stored in TAG constructed by the thought layer and action layer. Building upon TAG, we propose a novel KGQA paradigm \textemdash TAG-Reasoning (TAGR). TAGR first retrieves and assembles reasoning blueprints from TAG, and then guides LLM to efficiently execute on KG according to them. Through this approach, TAGR transforms the computationally expensive online exploration process of LLMs into an offline process of TAG retrieval and assembly. Experimental results on multiple KGQA benchmarks demonstrate that TAGR significantly outperforms state-of-the-art methods across key metrics, while drastically reducing the number of LLM calls and generated tokens. This work opens new avenues for building continual learning, efficient, and faithful KGQA systems.

ACL 2026

Structured Dialogue Refinement: Building Retrieval-Augmented Question Answering on Goal-Oriented Dialogues

Bin WU, Sawan Kumar, Prasetya Ajie Utama, Mohamed Yahya

Retrieval-Augmented Generation (RAG) is widely used for question answering over well-structured document corpora. However, a large amount of real-world problem-solving knowledge is captured in goal-oriented dialogues, where common ground misalignment between users and helpers gives rise to sparse, diffuse, and dynamically refined evidence that challenges standard RAG pipelines. We propose Structured Dialogue Refinement (SDR), a unified framework that adapts dialogue corpora for RAG at both the retrieval and generation stages without altering the underlying pipeline. Specifically, SDR introduces Dual Dialogue Querying for intent-aligned retrieval via issue-centric and solution-centric pseudo-documents, and Graph-Structured Dialogues coupled with a relevance-driven subgraph selection strategy to enable effective utilization of conversational evidence. We further adopt a nugget-based evaluation setup for dialogue-grounded RAG, enabling fine-grained analysis of retrieval coverage and grounded answer generation. Experiments demonstrate that SDR substantially improves both retrieval quality and grounded QA performance under dialogue-specific structural challenges.

ACL 2026

Large Language Models Are Overconfident in Their Own Responses

Mario Sanz-Guerrero, Manuel Mager, Katharina von der Wense

Prior work has shown that instruction-tuned large language models (LLMs) are less well calibrated than their base pre-trained counterparts. However, little is known about the frequently used chat template’s effect on the calibration of conversational LLMs. In this work, we investigate the mechanisms driving this miscalibration by decoupling the effects of the post-training algorithm and the chat format. We find that, while instruction tuning fundamentally harms calibration, the chat template aggravates the issue through an “ownership bias” – models are significantly more confident in their own answers than in identical answers provided by a user. Extensive experiments across six recent open-weight LLMs, three benchmarks, and three confidence elicitation methods show that models assign up to 26% higher confidence to their own responses. Leveraging this insight, we propose a simple inference-time strategy: framing the model’s answer as user input during confidence elicitation. This approach significantly reduces overconfidence and improves calibration by up to 26% without the need for retraining, narrowing the gap between base and instruction-tuned models.

ACL 2026

A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code

Keke Lian, Wang Bin, Lei Zhang, Libo Chen, Junjie Wang, Ziming Zhao, Yujiu Yang, Miaoqian Lin, Haotong Duan, Haoran Zhao, Shuang Liao, Mingda Guo, Quan Jiazheng, Yilu Zhong, Chenhao He, Chen Zichuan, Jie Wu, Haoling Li, Zhaoxuan Li, Jiongchi Yu, Hui Li, Dong Zhang

The increasing adoption of large language models (LLMs) in software engineering necessitates rigorous security evaluation of their generated code. However, existing benchmarks often lack relevance to real-world AI-assisted programming scenarios, making them inadequate for assessing the practical security risks associated with AI-generated code in production environments. To address this gap, we introduce A.S.E (AI Code Generation Security Evaluation), a repository-level evaluation benchmark designed to closely mirror real-world AI programming tasks, offering a comprehensive and reliable framework for assessing the security of AI-generated code. Our evaluation of leading LLMs on A.S.E reveals several key findings. In particular, current LLMs still struggle with secure coding. The complexity in repository-level scenarios presents challenges for LLMs that typically perform well on snippet-level tasks. Moreover, a larger reasoning budget does not necessarily lead to better code generation. These observations offer valuable insights into the current state of AI code generation and help developers identify the most suitable models for practical tasks. They also lay the groundwork for refining LLMs to generate secure and efficient code in real-world applications.

ACL 2026

The Best of Both Worlds: Combining Parallel and Sequential Inference Scaling via Aggregation Fine-Tuning

Yafu Li, Zhilin Wang, Tingchen Fu, Ganqu Cui, Sen Yang, Yu Cheng

Scaling data and model size has been proven effective for boosting the performance of large language models. In addition to training-time scaling, recent studies have revealed that increasing test-time computational resources can further improve performance. In this work, we introduce Aggregation Fine-Tuning (AFT), a supervised fine-tuning paradigm where the model learns to synthesize multiple draft responses, referred to as proposals, into a single, refined answer, termed aggregation. At inference time, we apply a propose-and-aggregate strategy that iteratively generates and aggregates proposals, effectively scaling inference-time computation without relying on external guidance such as a reward model. Empirical results across benchmark datasets demonstrate that AFT-trained models achieve substantial gains with test-time scaling, outperforming best-of-N baselines while eliminating the need for external reward signals. Notably, an AFT model, fine-tuned from Llama3.1-8B-Base with only 64k data, achieves a 41.3% LC win rate on AlpacaEval 2, surpassing significantly larger LLMs such as Llama3.1-405B-Instruct and GPT-4. By combining sequential refinement and parallel sampling, the propose-and-aggregate framework scales inference-time computation in a flexible manner.

ACL 2026

Incomplete Prompt Jailbreaks in Large Language Models

Yeonjea Kim, Bumjin Park, Jaesik Choi

Large language models (LLMs) are increasingly released as open-weight models with safeguards against harmful requests. Nevertheless, sentence completion remains vulnerable to incomplete harmful prompts. In this work, we formalize this phenomenon as incomplete prompt jailbreaks (IPJ) and provide a systematic empirical characterization of when and how incomplete prompts elicit harmful continuations. We analyze diverse attractor types associated with incomplete sentence continuation and show that LLMs systematically delay refusal until sentence termination. We further demonstrate that training models to refuse incomplete harmful prompts via parameter tuning is insufficient, failing to generalize across both content domains and attractor types. To enable fine-grained control, we identify two functional neurons: termination and continuation neurons. By clarifying their roles in sentence completion, we highlight the potential of neuron-level interventions for more precise and robust IPJ defenses.

ACL 2026

pQuant: Towards Effective Low-Bit Language Models via Decoupled Linear Quantization-Aware Training

Wenzheng Zhang, Bingzheng Liu

Quantization-Aware Training from scratch has emerged as a promising approach for building efficient large language models (LLMs) with extremely low-bit weights (sub 2-bit), which can offer substantial advantages for edge deployment. However, existing methods still fail to achieve satisfactory accuracy and scalability. In this work, we identify a parameter democratization effect as a key bottleneck: the sensitivity of all parameters becomes homogenized, severely limiting expressivity. To address this, we propose pQuant, a method that decouples parameters by splitting linear layers into two specialized branches: a dominant 1-bit branch for efficient computation and a compact high-precision branch dedicated to preserving the most sensitive parameters. Through tailored feature scaling, we explicitly guide the model to allocate sensitive parameters to the high-precision branch. Furthermore, we extend this branch into multiple, sparsely-activated experts, enabling efficient capacity scaling. Extensive experiments indicate our pQuant achieves state-of-the-art performance in extremely low-bit quantization.

ACL 2026

Revisiting the Uniform Information Density Hypothesis in LLM Reasoning

Minju Gwak, Guijin Son, Jaehyung Kim

The Uniform Information Density (UID) hypothesis proposes that effective communication is achieved by maintaining a stable flow of information. In this work, we revisit this principle in the context of Large Language Model (LLM) reasoning, asking whether step-level uniformity reflects reasoning quality. To this end, we introduce a novel framework to quantify uniformity of information flow at both local and global levels, using an entropy-based stepwise density metric. Across experiments on seven reasoning benchmarks, we see a counter-intuitive pattern: while high-quality reasoning exhibit smooth step-by-step transitions (local uniformity) and structured, non-uniform information flow at the trajectory level (global non-uniformity). The results demonstrate that these uniformities outperform alternative internal signals as predictors of reasoning quality, and such divergence with human communication is not a model deficiency, but a byproduct of distinct objectives between human communication and LLM reasoning.

ACL 2026

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets

Yuan Xiao, Jiaming Wang, Yuchen Chen, Wei Song, Jun Sun, Shiqing Ma, Yanzhou Mu, Juan Zhai, Chunrong Fang, Jin Song Dong, Zhenyu Chen

The widespread availability of large-scale code datasets has accelerated the development of code large language models (CodeLLMs), raising concerns about unauthorized dataset usage. Dataset poisoning offers a proactive defense by reducing the utility of such unauthorized training. However, existing poisoning methods often require full-dataset poisoning and introduce transformations that break code compilability. In this paper, we introduce FunPoison, a functionality-preserving poisoning approach that injects short, compilable weak-use fragments into executed code paths. FunPoison leverages reusable statement-level templates with automatic repair and conservative safety checking to ensure side-effect freedom, while a type-aware synthesis module preserves type correctness, suppresses static-analysis warnings, and improves stealth. Extensive experiments across multiple CodeLLMs and code-generation benchmarks show that FunPoison achieves effective poisoning by contaminating only 10% of the dataset, while maintaining 100% compilability and functional correctness. FunPoison also remains robust against advanced code sanitization techniques, including detection, purification, rewriting, static-analysis, and formatting defenses.

ACL 2026

AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing

Zhenhua Xu, Dongsheng Chen, Shuo Wang, Jian Li, Chengjie Wang, Meng Han, Yabiao Wang

LLM role-playing seeks to portray arbitrary characters in interactive narratives, yet existing systems often lack immersion and adapt ability. They typically under-model dynamic environment information and assume a largely static scene/cast, offering limited support for multi-character orchestration, scene transitions, and on-the-fly character introduction. We propose an adaptive multi-agent interaction framework dubbed AdaMARP, which featuring an immersive message format that interleaves [Thought], (Action), Environment, and Speech, and an explicit Scene Manager that controls role-playing via discrete actions (init_scene, pick_speaker, switch_scene, add_role, end) with rationales. To train these abilities, we construct AdaRPSet for the Actor Model and AdaSMSet for supervising or chestration decisions, and introduce AdaptiveBench for trajectory-level evaluation. Experiments across multiple backbones and scales show consistent gains: AdaRPSet improves character consistency, environment grounding, and narrative coherence—an 8B actor outperforming several commercial LLMs, while AdaSMSet enables smoother scene transitions and more natural role introductions, surpassing Claude Sonnet 4.5 with only 14B LLMs.

ACL 2026

WoW-Bench: Evaluating Fine-Grained Acoustic Perception in Audio-Language Models via Marine Mammal Vocalizations

Jaeyeon Kim, Heeseung Yun, Tony Woo, Chao-Han Huck Yang, Gunhee Kim

Large audio-language models (LALMs) extend language understanding into the auditory domain, yet their ability to perform low-level listening, such as pitch and duration detection, remains underexplored. However, low-level listening is critical for real-world, out-of-distribution tasks where models must reason about unfamiliar sounds based on fine-grained acoustic cues. To address this gap, we introduce the World-of-Whale benchmark (WoW-Bench) to evaluate low-level auditory perception and cognition using marine mammal vocalizations. We use marine mammal vocalizations as out-of-distribution sound events to better assess models’ low-level listening and so that the models do not rely on prior knowledge of the sound events. WoW-bench is composed of a Perception benchmark for categorizing novel sounds and a Cognition benchmark, inspired by Bloom’s taxonomy, to assess the abilities to remember, understand, apply, and analyze sound events. For the Cognition benchmark, we additionally introduce distractor questions to evaluate whether models are truly solving problems through listening rather than relying on other heuristics. Experiments with state-of-the-art LALMs show performance far below human levels, indicating a need for stronger auditory grounding in LALMs.

ACL 2026

G-HiRel: Enhancing the Adaption to Knowledge Updating for Large Language Model Reasoning

Yudai Pan, Jiajie Hong, Tianzhe Zhao, Lingyun Song, Lingling Zhang, Yixin Chen, Xuequn Shang

Large language models (LLMs) have achieved good performance in multiple reasoning tasks. However, they are limited to adapt the rapid knowledge updates in the real-world scenario without retraining the entire LLM or modifying the model weights. Excluding these consuming methods, knowledge graphs (KGs) are used as external memory under knowledge updating because of their structural knowledge and efficient updating ability, which is yet limited by the gap between structural KG and LLM, and the deficient entity-independent semantics. To this end, we propose an LLM reasoning framework with hierarchical relational retrieval for large-scale knowledge updating, named G-HiRel. To integrate the structural edited KG into continuous LLMs, G-HiRel generates hierarchical instructions based on natural language questions. In order to handle the knowledge inconsistency between the KG and LLM and obtain the entity independence, G-HiRel utilizes a designed hierarchical relational retrieval for relational path candidates, which are selected by a designed semantics-based strategy. Finally, top entity-independent relational paths are instantiated and integrated into LLMs to generate the answer, in order to verify the reasoning performance under knowledge edits. Extensive experiments of G-HiRel on three benchmarks show that G-HiRel achieves superiority in terms of accuracy and interpretability. The code of G-HiRel is available at the link: https://github.com/HJJ-designed/G-HiRel.

ACL 2026

BCL: Bayesian In-Context Learning Framework for Information Extraction

Haoliang Liu, Chengkun Cai, Xu Zhao, Han Zhu, Shizhou Huang, Xinglin Zhang, Tao Chen, Jenq-Neng Hwang, Zhang Huaping, Lei Li

Existing information extraction (IE) tasks increasingly adopt in-context learning (ICL) with large language models. However, current approaches either show inconsistent performance across model scales or lack systematic optimization and generalizability. Building on this, we propose BCL-IE (Bayesian In-Context Learning Framework for Information Extraction), the first optimization framework that uses particle filtering with Bayesian updates to systematically refine label representations across IE tasks. Through four steps—initialization, observation, weight update, and resampling, BCL-IE generalizes to both sequence labeling and relation classification paradigms. Extensive experiments demonstrate substantial improvements over existing approaches (up to 30%), achieving prior performance while other methods either fail to generalize or show limited effectiveness.

ACL 2026

Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning

Zhenpeng Su, Leiyu Pan, Minxuan Lv, Tiehua Mei, Zijia Lin, Yuntao Li, Wenping Hu, Ruiming Tang, Kun Gai, Guorui Zhou

Large language model post-training relies on reinforcement learning to improve model capability and alignment quality. However, the off-policy training paradigm introduces distribution shift, which often pushes the policy beyond the trust region, leading to training instabilities manifested as fluctuations in policy entropy and unstable gradients. Although PPO-Clip mitigates this issue through importance clipping, it still overlooks the global distributional shift of actions. To address these challenges, we propose using the entropy ratio between the current and previous policies as a new global metric that effectively quantifies the relative change in policy exploration throughout updates. Building on this metric, we introduce an Entropy Ratio Clipping (ERC) mechanism that imposes bidirectional constraints on the entropy ratio. This stabilizes policy updates at the global distribution level and compensates for the inability of PPO-clip to regulate probability shifts of un-sampled actions. We integrate ERC into both DAPO and GPPO reinforcement learning algorithms. Experiments across multiple benchmarks show that ERC consistently improves performance.

ACL 2026

Cognitive Analysis Graph-Guided Multi-Turn Safety Enhancement for Large Language Models

Lanxue Zhang, Yuqiang Xie, Fang Fang, Yubing Ren, Xuebin Wang, Yanan Cao

Large Language Models exhibit advanced reasoning capabilities that enable them to address complex tasks, but these capabilities also increase the risk of generating harmful content, particularly in multi-turn dialogues. Existing inference-phase safety alignment methods face three major challenges. First, they lack the relationship consideration between question and response, making the model easy to provide harmful content toward complex scenarios. Second, they are difficult to adapt to defense instruction. Third, these methods fail to effectively leverage historical information for safe response generation. To address these challenges, we propose CogGSE, an inference-time safety alignment framework that explicitly models the cognitive process of problem solving through a structured cognitive analysis graph. We retrieve a question-specific graph to ensure the safety information is tailored to the query. To fully exploit historical information in multi-turn settings, we retrieve relevant graphs from previous turns and selectively retain safety-related nodes, which are jointly used with the current-turn graph to guide safe response generation. This design enables transparent, controllable reasoning while maintaining strong safety guarantees. Extensive experiments demonstrate the effectiveness of our approach in multiple safety scenarios.

ACL 2026

Break Through the Compression Bottleneck: From Theory to Practice

Xiusheng Huang, Lu Wang, Yequan Wang, Jun Zhao, Kang Liu

As the parameter size of language models continues to grow, effective model compression is required to reduce their computational and memory overhead. Existing compression methods suffer from bottleneck issues: when the compression ratio is increased, performance degrades significantly. Low-rank decomposition and quantization are two prominent compression methods that have been proven to significantly reduce the computational and memory requirements of Large Language Models (LLMs) while maintaining model accuracy. Evidently, combining these two methods will break through the existing compression bottleneck. However, how these two methods interact when combined remains a critical question for developers, as many assume they are orthogonal, meaning their combination would not introduce additional errors beyond those independently introduced by each method. This paper provides the first mathematical proof that low-rank decomposition and quantization are non-orthogonal. We validate these findings through a series of experiments on large language models. Our results demonstrate that these methods are non-orthogonal, and their combination leads to significant performance degradation. Importantly, we propose a novel approach Diagonal Adhesive Method (DAM), which can effectively combine the two methods and mitigate the performance loss. Our research provides deep insights into model compression and lays a solid theoretical and experimental foundation for future related studies.

ACL 2026

Read the Room, Read the Image: Understanding Indirect Speech Acts in Multimodal Visual Contexts

Jaehee Kim, Ji Hoon Chung, Seoyoon Park, Unsol Kim, Kyungwon Park, JiHak Kim, Yi-Jun Chen, Hansaem Kim

Indirect speech acts (ISAs) require pragmatic reasoning over context, as directive intent cannot be inferred from surface form alone. Prior text-based studies and existing multimodal benchmarks largely overlook this requirement, focusing instead on explicitly encoded context or perceptual recognition, and thus underexplore context-dependent pragmatic understanding—particularly in high-context languages such as Korean. We introduce READI, a multimodal benchmark for evaluating ISA understanding through integrated reasoning over visual context and dialogue. READI models graded indirectness grounded in pragmatic theory and formulates the task as vision-based pragmatic question answering (V-PQA), supporting cross-lingual evaluation in English and Korean. Experiments show that even state-of-the-art multimodal models struggle with visually grounded indirect speech acts, with performance declining as indirectness increases, underscoring the need for benchmarks that explicitly target contextual pragmatic reasoning.

ACL 2026

Analyze Like a Venture Capitalist: Information-Gain and Knowledge Enhanced Graph Reasoning for Startup Success Prediction

Haoyu Pei, Zhongyang Liu, Xiangyi Xiao, Xiaocong Du, Suting Hong, Kunpeng Zhang, Haipeng Zhang

Most venture capital (VC) investments fail, while a few deliver outsized returns. Predicting startup success requires synthesizing relational evidence across company fundamentals, investor track records, and investment networks through explicit reasoning, which traditional machine learning and graph neural networks lack. Large language models excel at reasoning, but applying them to VC prediction must address: selecting compact evidence subgraphs from large investment networks, one-sided label noise where failures may be latent successes, and grounding decisions in structured VC domain knowledge. We present MIRAGE-VC, an evidence-grounded reasoning framework with three innovations. First, an information-gain-driven retriever distills networks into compact evidence subgraphs. Second, a dual-layer knowledge base grounds reasoning in VC principles. Third, a noise-aware mechanism down-weights mislabeled negatives via improved Positive-Unlabeled (PU) estimation. MIRAGE-VC achieves +5.9% F1 and +22.1% Precision@5 over state-of-the-art baselines. Expert evaluation confirms professional-quality rationales. We further validate our approach on public data with consistent improvements. Code and reasoning results are available at: https://github.com/ZhangDataLab/MIRAGE-VC.git

ACL 2026

Reward Yourself: Efficient Self Rewards for Trustworthy Sampling

Mingjie Li, Wai Man Si, Michael Backes, Yang Zhang

As high-quality data becomes harder to obtain, reward models are increasingly important. Beyond the costly RLHF stage, they are now used at inference time to guide LLM generation and in data selection for post-training. These methods bring efficiency and performance gains, but current reward models often fail to prevent untrustworthy behaviors such as privacy leaks and stereotypes. Re-training reward models to address these issues is expensive, since it requires large-scale human preference data. We propose SelfRW, a lightweight intrinsic reward that needs no extra fine-tuning or auxiliary models. By pruning current LLMs to approximate an “trust” and an “untrust” token distribution, we compute the log-probability difference as an auxiliary reward. When integrated into reward-guided sampling, SelfRW significantly reduces untrustworthy outputs while preserving task performance. It also improves reward-guided data selection, yielding better post-trained models. Experiments with two reward models and four LLMs on privacy, bias, and stereotype benchmarks show that combining SelfRW consistently improves trustworthiness (over 10% in privacy tasks and 20% in bias tasks) with minimal impact on general utility benchmarks.

ACL 2026

SciText2Eq: Assessing LLMs for Explainable Equation Generation for Scientific Creativity

Yifan Mo, Xiao Fu, Yue Su, Qingyu Meng, Koen Hindriks, Qingzhi Liu, Jiahuan Pei

This work investigates the ability of large language models (LLMs) to generate mathematical equations from scientific texts. Prior work faces challenges in unstructured grounding, multi-equation dependency, and human-aligned evaluation. To address this, we construct a dataset of AI research papers, pairing contextual passages with ground-truth equations and variable descriptions. We develop an explainable equation generation workflow and evaluate it across diverse open- and closed-source LLMs. Our evaluation protocol combines automatic metrics, LLM-based rubrics, and human judgments to assess accuracy, explainability, and human-LLM alignment. Results show that LLMs achieve moderate performance on lexical and syntactic similarity, but struggle with semantic accuracy. LLM-based evaluations show limited alignment with human judgments, highlighting challenges in assessing equation quality. These findings provide insights for improving equation generation models and developing more reliable evaluation methods for scientific creativity. We provide code and data for reproducibility.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.