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

LLM Program Optimization via Retrieval Augmented Search

Sagnik Anupam, Alexander Shypula, Osbert Bastani

Recent work has demonstrated the potential of large language models (LLMs) for program optimization, a key challenge in programming languages. We propose a blackbox adaptation method called Retrieval Augmented Search (RAS) that performs beam search over candidate optimizations; at each step, it retrieves in-context examples from a given training dataset of slow-fast program pairs to guide the LLM. Critically, we find that performing contextual retrieval based on an LLM-generated natural language description significantly outperforms retrieval based on the source code. We also propose AEGIS, a method for improving interpretability by decomposing training examples into "atomic edits” that are significantly more incremental in nature. We show that RAS performs up to 2.06\times better than prior state-of-the-art blackbox adaptation strategies on optimizing C++ programs, and that AEGIS performs up to 1.37\times better while making significantly smaller edits. We also show that using RAS improves the mean runtime percentile of Python programs by 10.27 compared to baselines.

ACL 2026

On Safety Risks in Experience-Driven Self-Evolving Agents

Weixiang Zhao, Yichen Zhang, Yingshuo Wang, Yang Deng, Yanyan Zhao, Xuda Zhi, Yongbo Huang, Hao He, Wanxiang Che, Bing Qin, Ting Liu

Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduces underexplored safety risks. In this study, we investigate how experience accumulation and utilization in self-evolving agents affect safety performance across web-based and embodied environments. Notably, experience gathered solely from benign tasks can still compromise safety in high-risk scenarios. Further analysis attributes this degradation to the execution-oriented nature of accumulated experience, which reinforces agents’ tendency to act rather than refuse. In more realistic settings where agents encounter both benign and harmful tasks, refusal-related experience mitigates safety decline but induces over-refusal, revealing a fundamental safety–utility trade-off. Overall, our findings expose inherent limitations of current self-evolving agents and call for more principled strategies to ensure safe and reliable adaptation.

ACL 2026

Beyond Single-Shot: Multi-step Tool Retrieval via Query Planning

Wei Fang, James R. Glass

LLM agents operating over massive, dynamic tool libraries rely on effective retrieval, yet standard single-shot dense retrievers struggle with complex requests. These failures primarily stem from the disconnect between abstract user goals and technical documentation, and the limited capacity of fixed-size embeddings to model combinatorial tool compositions. To address these challenges, we propose ToolQP, a lightweight framework that models retrieval as iterative query planning. Instead of single-shot matching, ToolQP decomposes instructions into sub-tasks and dynamically generates queries to interact with the retriever, effectively bridging the semantic gap by targeting the specific sub-tasks required for composition. We train ToolQP using synthetic query trajectories followed by optimization with Reinforcement Learning with Verifiable Rewards (RLVR). Experiments demonstrate that ToolQP achieves state-of-the-art performance, exhibiting superior zero-shot generalization, robustness across diverse retrievers, and significant improvements in downstream agentic execution.

ACL 2026

EntroBench: Evaluating LLM Watermarking Under Multi-Entropy Scenarios and Practical User Operations

Pengyuan Qin, Linnan Tu, Yuhan Ke, Hefei Ling

Large language models (LLMs) watermarking has been proposed as an active approach for content provenance verification, yet existing evaluations are largely confined to fixed entropy settings. In this paper, we introduce EntroBench, a benchmark for LLM watermarking that systematically covers three entropy levels and seven representative tasks. We conducted a fair evaluation of eight watermarking methods through hyper-parameter search based on an anchored dataset. We find that current approaches struggle to perform consistently across different entropy levels. Our analysis reveals a clear trade-off between watermark detectability and downstream output quality that varies across tasks and entropy conditions. Furthermore, we assess watermark robustness under realistic user interaction scenarios and show that common, non-adversarial user behaviors can substantially degrade watermark signals. These results indicate that practical usage-driven perturbations pose a significant challenge to current watermarking techniques. EntroBench provides a unified evaluation framework for studying these issues and supports the development of more adaptive and robust LLM watermarking methods. Dataset and codes are available at https://github.com/py-qin/EntroBench.

ACL 2026

Direct Token Optimization: A Self-Contained Approach to Large Language Model Unlearning

Hong kyu Lee, Ruixuan Liu, Li Xiong

Machine unlearning is an emerging technique that removes the influence of a subset of training data (forget set) from a model without full retraining, with applications including privacy protection, content moderation, and model correction. The key challenge lies in achieving strong unlearning efficacy while preserving the overall utility. Existing unlearning methods for large language models (LLMs) often rely on auxiliary models, retain datasets, or even commercial AI services. However, dependence on these external resources is often impractical and could potentially introduce additional privacy risks. In this work, we propose direct token optimization (DTO), a self-contained unlearning approach for LLMs that directly optimizes the token-level objectives to unlearn specific sequences without external resources.For each sequence to be unlearned, we identify target tokens that encode critical knowledge for unlearning and treat remaining tokens as non-target ones for maintaining the model utility. DTO maximizes an unlearning objective on target tokens and applies a utility-preservation regularizer on non-target tokens.Across multiple unlearning benchmarks, DTO improves the forget quality up to 16.8\times over the latest baselines while maintaining comparable model utility. Our code is available at github.com/Emory-AIMS/direct_token_optimization.

ACL 2026

Prior Beliefs Prejudice LLM-as-Judge: Evidence from Persuasion Evaluation

Pardis Sadat Zahraei, Xiaoning Wang, Nimet Beyza Bozdag, Gokhan Tur, Dilek Hakkani-Tur

Large Language Models (LLMs) are increasingly used as judges to evaluate text quality, moderate content, and assess arguments. We investigate whether alignment-instilled prior beliefs bias LLM judgments, using persuasion evaluation as a representative task. We find a systematic failure: models conflate their trained beliefs with rhetorical quality, rating identical claims differently based on belief alignment rather than argumentative merit. A bare assertion aligned with training receives higher scores than a well-crafted counter-argument, even when explicitly instructed to judge rhetoric alone. We introduce ConvinceQA, a dataset of 27,756 persuasive arguments with controlled stance variation across subjective, harmful, and misinformation domains, and demonstrate this prior prejudice across models. We exploit this failure through persuasion-based probing: evaluating minimal pairs that differ only in the subject token bypasses learned refusals and reveals hidden biases. Analysis identifies three failure modes, with belief-conditioned rating inflation accounting for 88% of cases. Cross-task validation on essay quality assessment and debate judging confirms this is a pervasive limitation.

ACL 2026

Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings

Aakriti Agrawal, Gouthaman KV, Rohith Aralikatti, Gauri Jagatap, Jiaxin Yuan, Sarvesh Baskar, Vijay Kamarshi, Andrea Fanelli, Furong Huang

Hallucinations in Large Vision-Language Models (LVLMs) remain a persistent challenge, often stemming from inadequate integration of visual information during multimodal reasoning. A key cause is the model’s over-reliance on textual priors and underutilization of visual cues, leading to outputs that are linguistically fluent but visually inaccurate. For example, given an image of an empty kitchen countertop, an LVLM might hallucinate a “bowl of fruit” or “cup of coffee,” relying on language associations rather than visual evidence. Most LVLMs incorporate visual features by appending them to the input stream of a pre-trained LLM and training on large-scale vision-language datasets. Our systematic analysis reveals that this strategy often leads to over-dependence on textual information due to the inherent bias of LLMs towards language-dominant representations. This imbalance skews attention towards the text over visual content, weakening the model’s ability to ground outputs in visual inputs. To address this, we propose a simple yet effective visual feature incorporation method that encourages the model to learn visually-informed textual embeddings distinct from those of the base LLM and promotes a more balanced attention distribution. Experimental results across multiple hallucination benchmarks demonstrate that our method significantly reduces hallucinations and fosters more balanced multimodal reasoning. Notably, our approach achieves substantial gains, including \textbf{+9.33}% on MMVP-MLLM, \textbf{+2.99}% on POPE-AOKVQA, up to \textbf{+3.4}% on Merlin, and \textbf{+3}% on the hard-data split of HallusionBench.

ACL 2026

DUSK: Do Not Unlearn Shared Knowledge

Wonje Jeung, Sangyeon Yoon, Hyesoo Hong, Soeun Kim, Seungju Han, Youngjae Yu, Albert No

Machine unlearning aims to remove “forget” data while preserving knowledge from the “retain” data, yet a fundamental question arises when the two share content. By definition, an unlearned model should be indistinguishable from a model retrained solely on the retain set, which implies that shared knowledge must remain while only forget-specific content is removed. To evaluate this requirement, we introduce DUSK, the first benchmark for unlearning under realistic knowledge overlap. DUSK constructs documents containing both shared and unique knowledge and defines seven metrics to test whether methods erase forget-specific expressions without discarding shared facts. Evaluating nine recent approaches, we find that although surface text is often removed, current methods struggle to distinguish shared from unique knowledge, either erasing information that should be retained or failing to fully forget target content. DUSK provides a controlled, reproducible testbed for diagnosing these failures and guiding precise unlearning algorithms.

ACL 2026

Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality

Qipeng Xie, Zi Liang, Jiafei Wu, Yufei Chen, Weizheng Wang, Wenao Ma, Zhong Ming, Haiqin Yang, Kaishun Wu

Large Language Models (LLMs) often exhibit extreme sensitivity to surface-level prompt variations, where minor lexical perturbations trigger disproportionate performance fluctuations. Moving beyond black-box optimization or coarse-grained templates, we conduct the first analysis of n-gram token-level mechanisms, leveraging a large-scale dataset of 132,000 prompt variants. Our investigation uncovers the Scaling Law of Prompt Performance Stability: higher average performance is inherently associated with lower variance and greater stability. We identify that this robustness is driven by two linguistic pillars: Domain-Specific Terminology, which anchors semantic boundaries, and Explicit Action Directives, which formalize reasoning trajectories. By narrowing the model’s interpretative space, these patterns effectively “lock” the generation process. We operationalize these findings into an automated Prompt-Refining Agent that autonomously restructures queries via domain anchoring and operational constraints. Empirical results show a 40.7% reduction in performance variance for code generation, offering a statistically grounded framework for robust prompt engineering.

ACL 2026

PO-KGQA: Preference Optimization for Low-Resource Complex Knowledge Graph Question Answering

Prerna Agarwal, Ayushman Kumar singh, Srikanta Bedathur

Existing low-resource in-context learning-based knowledge graph question answering (KGQA) methods rely heavily on large language models (LLMs) to convert the natural language question into its corresponding logical form (LF), such as SPARQL, KoPL, etc. Recently, a few alignment techniques have been introduced that enable instruction-based fine-tuning of language models. They provide explicit negative signals and comparative objectives to learn how to avoid negative signals using preference optimization methods. Exploring such fine-tuning techniques with LLMs becomes very challenging due to the high computational resource requirements associated with them. Due to this, the focus has been shifted towards Small Language Models (SLMs), which offer advantages such as ease of (i) deployment for practical applications and (ii) instruction fine-tuning for specialized tasks. Motivated by this, in this work, we propose PO-KGQA: An SLM-based preference optimization framework for the complex KGQA task in a low-resource setting. Our extensive experiments demonstrate how PO-KGQA outperforms other fine-tuning alignment techniques on complex benchmarks such as KQA Pro by approximately 9% (avg).

ACL 2026

PROPER Agents: Proactivity Driven Personalized Agents for Advancing Knowledge Gap Navigation

Kirandeep Kaur, Vinayak Gupta, Aditya Gupta, Chirag Shah

Current approaches to proactive assistance move beyond the ask-and-respond paradigm by anticipating user needs. In practice, they either burden users with clarifying questions or rely on context-based extrapolation, often leading to unnecessary or mistimed interventions. Such systems lack explicit mechanisms to model users’ knowledge gaps, resulting in incomplete or suboptimal task outcomes. To address this, we propose PROPER, a framework that explicitly models user-specific knowledge gaps in a controlled manner. Central to our approach is the notion of dimensions: structured, task-relevant factors that define the considerations required for effective task completion. Given a user query, the DGA (Dimension Generating Agent) identifies explicit dimensions (from the user’s query) and generates a set of candidate implicit dimensions capturing unarticulated aspects of the task. The RGA (Response Generating Agent) integrates both explicit and implicit dimensions selectively to produce personalized, context-aware, and proactively informative responses. We evaluate PROPER across multiple domains using a structured, gap-aware rubric that measures coverage, initiative appropriateness, and intent alignment. PROPER improves on quality scores and win rates across all domains, achieving up to 84% gains in single-turn evaluation and consistent dominance in multiturn interactions. All code for PROPER is available at: https://github.com/i-kiran/ProPer-Agent.

ACL 2026

Grounded Concreteness: Human-Like Concreteness Sensitivity in Vision–Language Models

Aryan Roy, Zekun Wang, Christopher J. MacLellan

Do vision-language models (VLMs) develop more human-like sensitivity to linguistic concreteness than text-only large language models (LLMs) when both are evaluated with text-only prompts? We study this question with a controlled comparison between matched Llama text backbones and their Llama Vision counterparts across multiple model scales, treating multimodal pretraining as an ablation on perceptual grounding rather than access to images at inference. We measure concreteness effects at three complementary levels: (i) output behavior, by relating question-level concreteness to QA accuracy; (ii) embedding geometry, by testing whether representations organize along a concreteness axis; and (iii) attention dynamics, by quantifying context reliance via attention-entropy measures. In addition, we elicit token-level concreteness ratings from models and evaluate alignment to human norm distributions, testing whether multimodal training yields more human-consistent judgments. Across benchmarks and scales, VLMs show larger gains on more concrete inputs, exhibit clearer concreteness-structured representations, produce ratings that better match human norms, and display systematically different attention patterns consistent with increased grounding.

ACL 2026

ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents

Xing Fu, Yulin Hu, Mengtong Ji, Haozhen Li, Yixin Sun, Weixiang Zhao, Yanyan Zhao, Bing Qin

Memory-augmented language agents are increasingly deployed in affective applications such as emotional support, where understanding and responding to users’ latent emotional needs is critical. However, existing research often treats memory as a tool for factual retrieval, overlooking its role in shaping users’ emotional experiences. In this work, we introduce ENPMR-Bench, a benchmark for evaluating Emotional Need-aware Proactive Memory Retrieval (ENPMR), a core capability that enables agents to infer users’ latent emotional needs and proactively retrieve appropriate memories to support empathetic interaction. Grounded in Maslow’s hierarchy of needs, ENPMR-Bench includes over 1,800 memory-augmented dialogues and defines structured mappings between emotional needs and supportive memory types. Experimental results demonstrate that current retrieval paradigms, including both embedding-based and LLM-driven approaches, exhibit substantial deficiencies, with empathy scores significantly lagging behind golden memory conditions. While chain-of-thought prompting improves the alignment between inferred emotional needs and retrieved memories to some extent, a notable performance gap remains. Together, these findings reveal critical limitations in current agents and outline directions for advancing personalized emotional support through need-sensitive memory retrieval.

ACL 2026

Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models

Zhining Liu, Tianyi Wang, Xiao Lin, Penghao Ouyang, Gaotang Li, Ze Yang, Hui Liu, Sumit Keswani, Vishwa Pardeshi, Huijun Zhao, Wei Fan, Hanghang Tong

Despite substantial efforts toward improving the moral alignment of Vision-Language Models (VLMs), it remains unclear whether their ethical judgments are stable in realistic settings. This work studies moral robustness in VLMs, defined as the ability to preserve moral judgments under textual and visual perturbations that do not alter the underlying moral context. We systematically probe VLMs with a diverse set of model-agnostic multimodal perturbations and find that their moral stances are highly fragile, frequently flipping under simple manipulations. Our analysis reveals systematic vulnerabilities across perturbation types, moral domains, and model scales, including a sycophancy trade-off where stronger instruction-following models are more susceptible to persuasion. We further show that lightweight inference-time interventions can partially restore moral stability. These results demonstrate that moral alignment alone is insufficient and that moral robustness is a necessary criterion for the responsible deployment of VLMs.

ACL 2026

The Inner Monologue of Language Models: When Reasoning Traces Reveal More Than They Hide

Pratham Singla, Shivank Garg, Ayush Singh, Ishan Garg, Ketan Suhaas Saichandran

Recent advances in post-training techniques have endowed Large Language Models (LLMs) with enhanced capabilities for tackling complex, logic-intensive tasks through the generation of supplementary planning tokens. This development raises a fundamental question – Are these models aware of what they "learn” and "think”? To address this, we define three core competencies: (1) awareness of learned latent policies, (2) generalization of these policies across domains, and (3) alignment between internal reasoning traces and final outputs. We empirically evaluate these abilities on several tasks, each designed to require learning a distinct policy. Furthermore, we contrast the profiles of models post-trained via Supervised Fine-Tuning (SFT), Direct Policy Optimization (DPO), and Group Relative Policy Optimization (GRPO). Our findings indicate that RL-trained models not only demonstrate greater awareness of their learned behaviors and stronger generalizability to novel, structurally similar tasks than SFT models but also often exhibit weak alignment between their reasoning traces and final outputs, an effect most pronounced in GRPO-trained models.

ACL 2026

CoTJudger: A Graph-Driven Framework for Automatic Evaluation of Chain-of-Thought Efficiency and Redundancy in LRMs

Siyi Li, Jiajun Shi, Shiwen Ni, Ge Zhang, Shuaimin Li, Shijian Wang, Zhoufutu Wen, Yizhi Li, Hamid Alinejad-Rokny, Jiaheng Liu, Min Yang, Wenhao Huang

Large Reasoning Models (LRMs) have demonstrated strong performance by producing extended Chain-of-Thought (CoT) traces before answering. However, this paradigm often induces over-reasoning: redundant calculations and circular self-verification that increase computational cost without improving outcomes. Existing evaluations largely emphasize final accuracy or coarse token counts, and lack automated tools to separate essential logic from structural redundancy. We introduce CoTJudger, a graph-driven framework that quantifies reasoning efficiency by converting free-form CoTs into directed dependency graphs and extracting the Shortest Effective Path (SEP) needed to reach a correct solution. This yields an interpretable efficiency signal – how much of a CoT is necessary versus structurally redundant – that is comparable across models and tasks. Evaluating 21 LRMs, CoTJudger reveals pervasive redundancy and surfaces recurring failure modes, including verification obsession and compensatory redundancy. These results provide a practical metric for disentangling reasoning ability from computational waste, enabling more targeted evaluation and diagnosis of LRM efficiency.

ACL 2026

Beyond Evidence: Belief-Chain Conditioning for Persuasive Misinformation Debunking Explanation

Yi-Li Hsu, Li-Wun Chang, Chun-Yu Hsu, Wei-Kuan Shih, Aiping Xiong, Lun-Wei Ku

As AI systems increasingly mediate everyday communication, large language models (LLMs) are expected not only to provide factually accurate responses but also to generate explanations that engage with users’ mental states. We build on the concept of cognitive chains—structured representations of Situation, Clue, Thought, Action, and Emotion inspired by Theory of Mind—to investigate whether conditioning LLM outputs on such belief chains improves explanation quality. Specifically, we evaluate explanations along six reader-perceived dimensions: overall quality, logical correctness, completeness, conciseness, empathy, and agreement. Prior work shows that LLM explanations often default to neutral or uncertain stances, while individuals holding strong false beliefs remain highly resistant to correction. To address this challenge, we instantiate cognitive chains from two perspectives: believers and non-believers of the news claims. Using GPT-4.1 as a role-player across these stances, we find that incorporating believers’ chains improves the perceived quality of explanations for audiences with misinformation-aligned beliefs. Our findings underscore the importance of modeling diverse mental states in explanation generation and provide the first systematic evidence that Theory-of-Mind–based cognitive chains enhance the persuasiveness of explanations in misinformation contexts.

ACL 2026

Choose Your Lens: Multi-Perspective Value Alignment of Chain-of-Thought Reasoning

Gejian Zhao, Hanzhou Wu, Xinpeng Zhang

Large language models (LLMs) are increasingly expected to support pluralistic alignment, representing diverse human perspectives. However, current methods often induce motivated reasoning: LLMs tend to hallucinate “convenient” facts to forcefully justify a requested stance. To address this, we propose Value-Graph-Consistent Chain-of-Thought (VGC-CoT), a neuro-symbolic framework that enables steerable pluralism without distorting objective reality. We enforce a strict distinction: facts should be shared, while value trade-offs may diverge. Our approach models reasoning as a directed traversal over a multi-perspective graph comprising a fixed factual layer and perspective-specific value layers. By projecting generated CoT paths onto this structure, we align the model with target values while constraining it to a shared factual backbone. Experiments show that our method reduces factual hallucinations by 3\times and improves cross-perspective consistency by 25% compared to standard steerable baselines, paving the way for trustworthy pluralistic AI.

ACL 2026

Vulnerability of LLMs’ Stated Belief? LLMs Belief Resistance Check Through Strategic Persuasive Conversation Interventions

Fan Huang, Haewoon Kwak, Jisun An

Large Language Models (LLMs) are increasingly employed in various question-answering tasks. However, recent studies showcase that LLMs are susceptible to persuasion and could adopt counterfactual beliefs.We present a systematic evaluation of LLM susceptibility to persuasion under the Source–Message–Channel–Receiver (SMCR) communication framework. Across six mainstream Large Language Models (LLMs) and three domains (factual knowledge, medical QA, and social bias), we analyze how different persuasive strategies influence stated belief stability over multiple interaction turns.We further examine whether verbalized confidence prompting (i.e., eliciting self-reported confidence scores) affects resistance to persuasion.Results show that the smallest model (Llama 3.2-3B) exhibits extreme compliance, with 82.5% of belief changes occurring at the first persuasive turn (average end turn of 1.1–1.4).Contrary to expectations, verbalized confidence prompting increases vulnerability by accelerating belief erosion rather than enhancing robustness. Finally, an exploratory study of adversarial fine-tuning reveals highly model-dependent effectiveness: GPT-4o-mini achieves near-complete robustness (98.6%) and Mistral 7B improves substantially (35.7% \rightarrow 79.3%), but Llama models remain highly susceptible (<14% RQ1) even when fine-tuned on their own failure cases. Together, these findings highlight substantial model-dependent limits of current robustness interventions and offer guidance for developing more trustworthy LLMs[https://github.com/muyuhuatang/llm_stated_belief].

ACL 2026

A Computational Method for Measuring Open Codes in Qualitative Analysis

John Chen, Alexandros Nikolaos Lotsos, Sihan Cheng, Lexie Zhao, Yanjia Zhang, Jessica Hullman, Bruce Sherin, Uri Wilensky, Michael Horn

Qualitative analysis is critical to understanding human datasets in many social science disciplines. A central method in this process is inductive coding, where researchers identify and interpret codes directly from the datasets themselves. Yet, this exploratory approach poses challenges for meeting methodological expectations (such as “depth” and “variation”), especially as researchers increasingly adopt Generative AI (GAI) for support. Ground-truth-based metrics are insufficient because they contradict the exploratory nature of inductive coding; cluster- or topic-level metrics fail to capture the interpretive, cross-cutting nature of qualitative codes; and manual evaluation can be labor-intensive. This paper presents a theory-informed computational method for measuring inductive coding results from humans and GAI. Our method first merges individual codebooks into an Aggregated Code Space using an LLM-enriched hierarchical clustering algorithm. It then measures each coder’s contribution against the merged result using four novel metrics: Coverage, Overlap, Novelty, and Divergence, designed to capture breadth, consensus, unique contribution, and systematic deviation without assuming ground truth. Through two experiments on a human-coded online conversation dataset, we 1) reveal the merging algorithm’s impact on metrics; 2) validate the metrics’ stability and robustness across multiple runs and different LLMs; and 3) showcase the metrics’ ability to diagnose coding issues, such as excessive or irrelevant (hallucinated) codes. We discuss how these metrics should be interpreted in combination and their current limitations. Our work provides a reliable pathway for ensuring methodological rigor in human-AI qualitative analysis.

Keep browsing

More papers from top AI conferences

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