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

Thinking Twice Makes Large Language Models Safer and More Helpful

Yutao Mou, Yuxiao Luo, Shikun Zhang, Wei Ye

Current safety alignment techniques for large language models (LLMs) struggle to balance harmlessness and helpfulness: improving safety often comes at the cost of degraded utility. Our preliminary study shows that guiding unaligned base models with safety-aware reasoning that includes explicit self-reflection can effectively defend jailbreak attacks while preserving response quality. This observation motivates internalizing and strengthening self-reflective reasoning capabilities within LLMs to achieve a better safety–utility trade-off. We propose Safety-aware Reflective Reasoning Optimization (SaRO), a two-stage framework: (1) Reasoning-style Warmup (RW) to internalize self-reflective reasoning, and (2) Self-reflective Reasoning Process Optimization (SRPO) to encourage reflection and correction. Experiments show that SaRO outperforms existing reasoning-based alignment methods, achieving a better balance of safety and helpfulness.

ACL 2026

LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey

Henry Peng Zou, Wei-Chieh Huang, Yaozu Wu, Jizhou Guo, Yankai Chen, Chunyu Miao, Hoang H. Nguyen, Yue Zhou, Weizhi Zhang, Liancheng Fang, Hanrong Zhang, Fangxin Wang, Pengfei ZHANG, Langzhou He, Yangning Li, Dongyuan Li, Renhe Jiang, Philip S. Yu

Recent advances in large language models (LLMs) have sparked growing interest in building fully autonomous agents. However, fully autonomous LLM-based agents still face significant challenges, including limited reliability due to hallucinations, difficulty in handling complex tasks, and substantial safety and ethical risks, all of which limit their feasibility and trustworthiness in real-world applications. To overcome these limitations, LLM-based human-agent systems (LLM-HAS) incorporate human-provided information, feedback, or control into the agent system to enhance system performance, reliability, and safety. These human-agent collaboration systems enable humans and LLM-based agents to collaborate effectively by leveraging their complementary strengths.This paper provides the first comprehensive and structured survey of LLM-HAS. It clarifies fundamental concepts, systematically presents core components shaping these systems, including environment and profiling, human feedback, interaction types, orchestration, and communication, explores emerging applications, and discusses unique challenges and opportunities arising from human-AI collaboration. By consolidating current knowledge and offering a structured overview, we aim to foster further research and innovation in this rapidly evolving interdisciplinary field. Paper lists and resources are available at https://github.com/HenryPengZou/Awesome-Human-Agent-Collaboration-Interaction-Systems.

ACL 2026

EngiBench: A Benchmark for Evaluating Large Language Models on Engineering Problem Solving

Xiyuan Zhou, Xinlei Wang, Yirui He, Ruixi Zou, Yang Wu, Yuheng Cheng, Yulu Xie, Wenxuan Liu, Huan Zhao, Yan Xu, Jinjin Gu, Junhua Zhao

Large language models (LLMs) have shown strong performance on mathematical reasoning under well-defined conditions. However, real-world engineering problems involve uncertainty, context, and open-ended settings that extend beyond symbolic computation. Existing benchmarks largely focus on well-defined or abstract reasoning and therefore fail to capture these complexities. We introduce EngiBench, a hierarchical benchmark designed to evaluate LLMs on solving engineering problems. It spans three levels of increasing difficulty (foundational knowledge retrieval, contextual reasoning, and open-ended modeling) and covers diverse engineering subfields. To facilitate a deeper understanding of model performance, we systematically rewrite each problem into three controlled variants (perturbed, knowledge-enhanced, and math abstraction), enabling us to separately evaluate the model’s robustness, domain-specific knowledge, and mathematical reasoning abilities. Experimental results show clear performance stratification across difficulty levels: model accuracy declines with task complexity, degrades under minor perturbations, and remains substantially below human performance on high-level engineering tasks. These findings reveal that current LLMs still lack the high-level reasoning needed for real-world engineering, highlighting the need for future models with deeper and more reliable problem-solving capabilities. Our source code and data are available at https://github.com/AI4Engi/EngiBench.

ACL 2026

Speculative Verification: Exploiting Information Gain for Speculative Decoding

Sungkyun Kim, Jaemin Kim, Dogyeong Yun, Jiho Shin, Junyeol Lee, Jiwon Seo

Speculative decoding (SD) improves LLM inference latency by speculatively generating multiple tokens with a small draft model and verifying them with a larger target model. However, when speculation accuracy is low, the overhead from rejected tokens can negate its benefits, especially at large batch sizes.We propose Speculative Verification (SV), an efficient augmentation to SD that predicts speculation accuracy and dynamically adapts the verification length to maximize throughput. SV introduces a small companion model, similar in size to draft model, to reduce uncertainty in speculation accuracy. By exploiting the information gain from observing the companion distribution, SV reduces wasted verification on rejected tokens and improves decoding efficiency.We evaluate SV across publicly available LLMs on seven NLP tasks using over a hundred combinations of draft, companion, and target models, including 13B–72B target models spanning base, instruction-tuned, and task-specific fine-tuned variants. Compared to target-only decoding, standard SD, and state-of-the-art SD variants, SV consistently delivers higher throughput across batch sizes. SV improves SD performance by up to 1.9\times, with an average 1.4\times speedup at large batch sizes, showing robust and scalable gains for practical LLM inference.

ACL 2026

SAFER: Advancing Safety Alignment via Efficient Ex-Ante Reasoning

Kehua Feng, Keyan Ding, Yuhao Wang, Menghan Li, Fanjunduo Wei, Xinda Wang, Huajun Chen

Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often struggle to cover diverse safety scenarios and remain vulnerable to adversarial attacks. In this work, we propose SAFER, a framework for Safety Alignment via eFficient Ex-Ante Reasoning. Our approach instantiates structured Ex-Ante reasoning through initial assessment, rule verification, and path calibration, and embeds predefined safety rules to provide transparent and verifiable safety judgments. Specifically, our approach consists of two training stages: (1) supervised fine-tuning with synthetic traces to teach the multi-stage Ex-Ante reasoning, and (2) step-level reasoning preference optimization to jointly enhance safety, utility, and efficiency. Experiments on multiple open-source LLMs demonstrate that SAFER significantly enhances safety performance while maintaining helpfulness and response efficiency.

ACL 2026

Take Out Your Calculators: Estimating the Real Difficulty of Question Items with LLM Student Simulations

Christabel Acquaye, Yi-Ting Huang, Marine Carpuat, Rachel Rudinger

Standardized math assessments require expensive human pilot studies to establish the difficulty of test items. We investigate the predictive value of open-source large language models (LLMs) for evaluating the difficulty of multiple-choice math questions for real-world students. We show that, while LLMs are poor direct judges of problem difficulty, simulation-based approaches with LLMs yield promising results under the right conditions. Under the proposed approach, we simulate a “classroom” of 4th, 8th, or 12th grade students by prompting the LLM to role-play students of varying proficiency levels. We use the outcomes of these simulations to fit Item Response Theory (IRT) models, comparing learned difficulty parameters for items to their real-world difficulties, as determined by item-level statistics furnished by the National Assessment of Educational Progress (NAEP). We observe correlations as high as 0.75, 0.76, and 0.82 for grades 4, 8, and 12, respectively. In our simulations, we experiment with different “classroom sizes,” showing tradeoffs between computation size and accuracy. We find that role-plays with named students improves predictions (compared to student ids), and stratifying names across gender and race further improves predictions. Our results show that LLMs with relatively weaker mathematical abilities (Gemma) actually yield better real-world difficulty predictions than mathematically stronger models (Llama and Qwen), further underscoring the suitability of open-source models for the task.

ACL 2026

PrinciplismQA: A Philosophy-Grounded Approach to Assessing LLM-Human Clinical Medical Ethics Alignment

Chang Hong, Minghao Wu, Qingying Xiao, Yuchi Wang, Xiang Wan, Guangjun Yu, Benyou Wang, Yan Hu

As medical LLMs transition to clinical deployment, assessing their ethical reasoning capability becomes critical. While achieving high accuracy on knowledge benchmarks, LLMs lack validated assessment for navigating ethical trade-offs in clinical decision-making where multiple valid solutions exist. Existing benchmarks lack systematic approaches to incorporate recognized philosophical frameworks and expert validation for ethical reasoning assessment. We introduce PrinciplismQA, a philosophy-grounded approach to assessing LLM clinical medical ethics alignment. Grounded in Principlism, our approach provides a systematic methodology for incorporating clinical ethics philosophy into LLM assessment design. PrinciplismQA comprises 3,648 expert-validated questions spanning knowledge assessment and clinical reasoning. Our expert-calibrated pipeline enables reproducible evaluation and models ethical biases. Evaluating recent models reveals significant ethical reasoning gaps despite high knowledge accuracy, demonstrating that knowledge-oriented training does not ensure clinical ethical alignment. PrinciplismQA provides a validated tool for assessing clinical AI deployment readiness.

ACL 2026

A2O: LLM-based Agentic Learning of Action-to-Object Features for Video Action Recognition

Taiki Sekii, Fumiaki Sato

Recent action recognition based on vision–language pretraining and self-supervised video foundation models tends to induce spurious correlations and shortcut learning by relying on action-irrelevant cues, such as backgrounds and object co-occurrences. By contrast, object-detection-based approaches can suppress spurious correlations; however, the loss of input information can limit accuracy. To mitigate this trade-off, we combine these two approaches to learn complementary features that compensate for each other’s shortcomings. Specifically, we leverage the commonsense knowledge of large language models (LLMs) regarding human actions and realize a framework in which an LLM agent integrates the two approaches within an agentic learning paradigm to design motion features tailored to the target actions. The LLM agent uses an open vocabulary object detector to instruct the video foundation model with the target and nontarget objects in the video to make the model attend to objects in a video required for recognizing the target actions. The composition of the detected objects is optimized for the target actions through in-context reinforcement learning (ICRL) using the commonsense knowledge of the LLM. Experiments on multiple public action recognition datasets and an ablation study confirm the robustness of features learned using the proposed method and the effectiveness of ICRL.

ACL 2026

AI Agents for the Science of Science: A Survey of Tasks, Architectures, Evaluations, and Challenges

Yixuan Liu, Yicheng Zhang

The Science of Science (SciSci) examines how scientific knowledge is generated, evaluated, and transformed by utilizing large-scale scholarly and bibliometric data. As these data grow in scale and complexity, analysis has increasingly relied on statistical, network-based, machine learning methods, and is now seeing growing involvement of AI agents. This emerging class of such agents, ranging from multi-agent simulations of scientific behavior to tool-augmented systems for empirical analysis, is beginning to reshape how SciSci research is conducted. In this survey, we propose a task-centered taxonomy, distinguishing agents as simulations, which model citation, collaboration, and community dynamics, from agents as tools, which assist empirical analysis and scientific workflows. We review agent architectures, learning mechanisms, evaluation, and SciSci benchmarks, and examine open challenges related to reliability, data quality, and bias. Our survey aims to clarify the landscape of AI agents in SciSci and to support the development of reliable and scientifically useful AI systems for studying science and scientific communities.

ACL 2026

Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation

Abhishek Purushothama, Emma Thronson, Alexia Guo, Amir Zeldes

This paper proposes a novel in-context learning approach to support low resource machine translation for the Coptic language, using prompts based on Universal Dependencies parses of input sentences. Building on existing work using bilingual dictionaries to support inference for vocabulary items, we add several representations of syntactic analyses to our inputs, specifically exploring the inclusion of raw parser outputs, verbalizations of parses in plain English, and explanations of specific difficult constructions identified in input subgraphs and how they can be translated. Our results show that while syntactic information alone is not as useful as dictionary-based glosses, combining retrieved dictionary items with syntactic information achieves significant gains across model sizes, achieving new state-of-the-art results for the language.

ACL 2026

From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision–Language Models

Qidong Wang, Junjie Hu, Ming Jiang

Recent work has increasingly explored neuron-level interpretation in vision-language models (VLMs) to identify neurons critical to final predictions. However, existing neuron analyses generally focus on single tasks, limiting the comparability of neuron importance across tasks. Moreover, ranking strategies tend to score neurons in isolation, overlooking how task-dependent information pathways shape the write-in effects of feed-forward network (FFN) neurons. This oversight can exacerbate neuron polysemanticity in multi-task settings, introducing noise into the identification and intervention of task-critical neurons. In this study, we propose HONES (Head-Oriented Neuron Explanation Steering), a gradient-free framework for task-aware neuron attribution and steering in multi-task VLMs. HONES ranks FFN neurons by their causal write-in contributions conditioned on task-relevant attention heads, and further modulates salient neurons via lightweight scaling. Experiments on four diverse multimodal tasks and two popular VLMs show that HONES outperforms existing methods in identifying task-critical neurons and improves model performance after steering. Our source code is released at: https://github.com/petergit1/HONES.

ACL 2026

ViLegalLM: Language Models for Vietnamese Legal Text

Truong-Phuc Nguyen, Quy-Nhan Nguyen, Minh-Tien Nguyen

We present ViLegalLM, comprising ViLegalBERT and ViLegalQwen, the first suite of Vietnamese pretrained language models for legal text understanding and generation. It includes one encoder-only model (ViLegalBERT, 135M parameters) and two decoder-only models (ViLegalQwen2.5-1.5B-Base and ViLegalQwen3-1.7B-Base), all continually pretrained on a newly curated 16GB Vietnamese legal corpus, significantly larger than previous work. To mitigate data scarcity, we construct three synthetic datasets using LLM-based generation and hard negative mining for True/False QA, Multiple Choice QA, and Natural Language Inference. We establish state-of-the-art results among open-source models on four main Vietnamese legal downstream tasks spanning ten benchmarks, demonstrating that continual pretraining from base models consistently outperforms instruction-tuned adaptation. Source codes, corpus, datasets, and model checkpoints are publicly available at https://github.com/ntphuc149/ViLegalLM.

ACL 2026

Explanation Quality Assessment as Ranking with Listwise Rewards

Thomas Bailleux, Tanmoy Mukherjee, Emmanuel Lonca, Pierre Marquis, Zied Bouraoui

We reformulate explanation quality assessment as a ranking problem rather than a generation problem. Instead of optimizing models to produce a single “best” explanation token-by-token, we train reward models to discriminate among multiple candidate explanations and learn their relative quality. Concretely, we construct per-instance candidate sets with graded quality levels and train listwise and pairwise ranking models (ListNet, LambdaRank, RankNet) to preserve ordinal structure and avoid score compression typical of pointwise regression or binary preference objectives. We observe three findings: First, ranking losses consistently outperform regression on score separation across all domains tested. Second, the optimal ranking loss depends on data characteristics: listwise objectives excel with well-separated quality tiers, while pairwise methods are more robust to noisy natural annotations. Third, when trained on carefully curated and well-structured data, small encoder models can match models that are orders of magnitude larger, suggesting that data quality matters more than model scale. Finally, when used as rewards in policy optimization, ranking-based scores enable stable convergence in settings where regression-based rewards fail entirely. Code and data are available at: https://github.com/Tankiit/PPO_Learning_to_rank

ACL 2026

Do LLM Agents Really Mimic Humans? Diagnosing and Aligning Microeconomic Behaviors in Macro-ABMs

Guangya Liu, Cheng Wang, Jiangtong Li, Huafei Wu, changjun jiang

Large Language Models (LLMs) are increasingly adopted in macroeconomic agent-based modeling(ABM). However, existing research focuses on replicating macro-level stylized facts while often neglecting verification of micro-level decision-making. We investigate this gap by comparing LLM agents to human responses from the Survey of Consumer Expectations (SCE) dataset. Our empirical analysis identifies specific limitations: weak trend responsiveness, mode collapse, and a potential data leakage. We propose the Heterogeneous Shock-Response Causal Transmission Framework to tackle these issues. To ensure theoretical consistency, we use LLMs to build a literature-verified causal graph in which macroeconomic shocks influence decisions via generated mediator nodes, while agent profiles serve as edge moderators. Building on this, during inference, we perform a path search to retrieve relevant causal chains and inject them as an explicit Chain-of-Thought(CoT), prioritizing mechanistic logic over statistical pattern matching. To evaluate the effectiveness of our inference approach, we validate it via a two-stage process that combines micro-level dataset testing and macro-level simulation in the EconAgent system. Results from these experiments indicate that our framework improves alignment with human trends and effectively captures behavioral heterogeneity. Overall, this work contributes to the development of reliable and grounded economic simulations.

ACL 2026

Inventive Problem Solving with LLMs: A Benchmark for TRIZ Reasoning

Zhu Wang, Brian Uzzi

Large language models are increasingly used in inventive problem-solving, but effective support requires more than open-ended idea generation. Inventive problem-solving requires improving one aspect of a technical system without unintentionally worsening another. TRIZ (Theory of Inventive Problem Solving) provides a unique and structured framework for this setting by representing engineering trade-offs as contradictions and linking them to standardized inventive principles. However, prior TRIZ–LLM evaluations are typically small-scale, case studies in focused areas of technology, and rarely grounded in patent text, which makes it difficult to assess structured reasoning at scale. We introduce TRIZBench, a dataset and benchmark for TRIZ reasoning grounded in open technical sources and U.S. patents. TRIZBench evaluates the core TRIZ workflow through three tasks: contradiction prediction, inventive principle prediction, and grounded TRIZ reasoning. Experiments with multiple LLM baselines show that detecting contradictions is easier than recovering correct trade-off pairs, while principle prediction benefits from explicitly exploiting TRIZ structure. Our findings further underscore the importance of grounding. We show that semantic retrieval enables evidence-based justifications and helps explain why LLMs fail. Dataset and code are available at https://github.com/ellenzhuwang/trizbench.

ACL 2026

Measuring Watermarking under Jailbreaking: ASR Inflation and Goal-Compliance Mismatch

Sungwoo Han, Sangjun Moon, Jingun Kwon, Hidetaka Kamigaito, Manabu Okumura

Recently, watermarking has attracted growing attention as a practical technique for source attribution of machine-generated text. However, most prior work studies watermarking under benign prompts, while its behavior under jailbreaking prompts remains underexplored. This gap matters because jailbreaking can bypass safety policies and shift the generation regime, raising concerns that watermarking may interact with model alignment under attack. To address this gap, we evaluate six watermarking methods on four LLMs across two jailbreak benchmarks and three settings: Static, AutoDAN, and DSN. We find that watermarking can inflate judge-based attack success rate, denoted ASR, under jailbreaking, with the largest effects appearing in biased schemes that perturb logits. At the same time, these ASR increases often do not reflect higher harmful-goal compliance when measured by StrongREJECT or by human judgments. This suggests that ASR-only evaluations can be brittle to decoding perturbations and may overestimate harmful-goal compliance, motivating complementary goal-compliance metrics (e.g., StrongREJECT) and human evaluations.

ACL 2026

Beyond Static Synthetic Noise: Assessing the Robustness of Large Language Models to Natural Context Variation in the Real World

Yulong Wu, Viktor Schlegel, Riza Batista-Navarro

Robustness evaluation in Question Answering (QA) has predominantly relied on synthetic perturbations that poorly capture natural text evolution in real-world settings, a limitation that becomes more pronounced with the widespread deployment of Large Language Models (LLMs) in dynamic, user-facing environments. In this work, we address this gap by proposing a framework for automatically evaluating QA models under naturally occurring textual perturbations, replacing context passages with revised counterparts from Wikipedia edit histories. Through extensive evaluation on SQUAD across diverse encoder architectures, we construct two challenging sets where human performance remains stable, yet state-of-the-art LLMs exhibit significant degradation, with performance drops of up to 28.28%. These robustness gaps further generalize to more complex QA scenarios, such as DROP and HOTPOTQA. To mitigate these errors, we show that robustness to natural perturbations can be improved via adversarial training for encoder-only models and in-context demonstrations of perturbed instances for LLMs, though a more generalizable and effective defense strategy remains an open challenge.

ACL 2026

Evaluating Perspectival Biases in Cross-Modal Retrieval

Teerapol Saengsukhiran, Peerawat Chomphooyod, Narabodee Rodjananant, Chompakorn Chaksangchaichot, Patawee Prakrankamanant, Witthawin Sripheanpol, Pak Lovichit, Sarana Nutanong, Ekapol Chuangsuwanich

Multimodal retrieval systems are expected to operate in a semantic space, agnostic to the language or cultural origin of the query. In practice, however, retrieval outcomes systematically reflect perspectival biases: deviations shaped by linguistic prevalence and cultural associations. We introduce the Cross-Cultural, Cross-Modal, Cross-lingual Multimodal (3XCM) benchmark to isolate these effects. Results from our studies indicate that, for image-to-text retrieval, models tend to favor entries from prevalent languages over those that are semantically faithful. For text-to-image retrieval, we observe a consistent "tugging effect” in the joint embedding space between semantic alignment and language-conditioned cultural association. When semantic representations are insufficiently resolved, particularly in low-resource languages, similarity is increasingly governed by culturally familiar visual patterns, leading to systematic association bias in retrieval. Our findings suggest that achieving equitable multimodal retrieval necessitates targeted strategies that explicitly decouple language from culture, rather than relying solely on broader data exposure. This work highlights the need to treat linguistic and cultural biases as distinct, measurable challenges in multimodal representation learning.

ACL 2026

PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption

Xue Tan, Yi Zheng, Chang Huo, Yunruo Zhang, Yu Liu, Hao Luan, Zhuyang Yu, Jun Dai, Xiaoyan Sun, Ping Chen

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge, effectively mitigating their inherent knowledge limitations. However, RAG remains vulnerable to poisoning attacks that manipulate retrieved texts to mislead model outputs. Existing defense mechanisms often lack theoretical robustness guarantees and perform unreliably when the LLM has limited knowledge of the retrieved content. In this work, we propose PRA-RAG, a provably robust retrieval aggregation algorithm designed to defend against poisoning attacks on retrieved texts. PRA-RAG samples multiple combinations of retrieved texts and utilizes geometric structures in the embedding space to identify a robust subset, from which a stable aggregated representation is derived. We provide theoretical bounds on the maximum impact of poisoned retrieved content and establish a quantitative measure of RAG’s robustness. Experiments across multiple benchmarks and RAG architectures demonstrate that PRA-RAG reduces the attack success rate to as low as 1% while maintaining an accuracy of 71%, significantly outperforming representative state-of-the-art (SOTA) methods.

ACL 2026

RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine

Jiatan Huang, Mingchen Li, Zonghai Yao, Dawei Li, Yuxin Zhang, Zhichao Yang, Yongkang Xiao, Feiyun Ouyang, Xiaohan Li, Shuo Han, Hong Yu

Answering complex real-world questions in the medical domain often requires accurate retrieval from medical Textual Knowledge Graphs (medical TKGs), as the relational path information from TKGs could enhance the inference ability of Large Language Models (LLMs). However, the main bottlenecks lie in the scarcity of existing medical TKGs, the limited expressiveness of their topological structures, and the lack of comprehensive evaluations of current retrievers for medical TKGs. To address these challenges, we first develop a dataset for LLMs Complex Reasoning over medical Textual Knowledge Graphs (RiTeK), covering a broad range of topological structures. Specifically, we synthesize realistic user queries integrating diverse topological structures, relational information, and complex textual descriptions. We conduct a rigorous medical expert evaluation process to assess and validate the quality of our synthesized queries. RiTeK also serves as a comprehensive benchmark dataset for evaluating the capabilities of retrieval systems built upon LLMs. By assessing 11 representative retrievers on this benchmark, we observe that existing methods struggle to perform well, revealing notable limitations in current LLM-driven retrieval approaches. These findings highlight the pressing need for more effective retrieval systems tailored for semi-structured data in the medical domain.

Keep browsing

More papers from top AI conferences

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