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

SegDRE: A Salient Entity Guided Approach to Document-Level Relation Extraction

Xing Yang, Chengxiang Tan

In Document-level Relation Extraction (DocRE), relational facts are typically organized around a few salient entities. Explicitly capturing this topological structure is pivotal to addressing the two critical bottlenecks of the task: the extreme class imbalance and the complexity of multi-hop reasoning. Based on this insight, we first introduce the concept of the salient entity and propose a novel approach that decouples the extraction space into dense and sparse scenarios. Specifically, our approach restricts the search space for dense pairs to mitigate the dominance of the negative samples, and innovatively injects the rich semantic knowledge of salient entities to explicitly reconstruct the document for bridging disjoint evidence in multi-hop reasoning. Extensive experiments demonstrate that our approach yields consistent improvements over various backbone models and achieves advanced performance compared to existing enhancement methods.

ACL 2026

Rethinking Assessments of Prompt Injection Attacks

Chi Cui, Yixin Wu, Michael Backes, Yang Zhang

Prompt injection attacks are recognized as one of the primary risks faced by LLM-integrated applications in recent years. However, common evaluation frameworks remain insufficient, lacking comprehensiveness and real-world relevance. To bridge this gap, we revisit the common evaluation framework and conduct an extensive evaluation across eight different evaluation settings, including 37 real-world applications, 185 injected tasks, 21 attack instructions, and a total of 143,745 queries. The evaluation highlights several findings. For example, real-world applications are more vulnerable to prompt injection attacks compared to those used in research settings. While complex attack instructions are more sophisticated, they are less effective than simple attack instructions. We further conduct an assessment of both prompt-level and model-level defense mechanisms and highlight their limitations in real-world applications. By exploring more diverse scenarios across different dimensions, our framework provides a solid foundation for assessing vulnerabilities in LLM-integrated applications and evaluating the efficacy of defensive strategies.

ACL 2026

Position: From Noise to Signal to Selbstzweck - Reframing Human Label Variation in the Era of Post-training in NLP

Shanshan Xu, Santosh T.y.s.s, Barbara Plank

Human Label Variation (HLV) refers to legitimate disagreement in annotation that reflects the diversity of human perspectives rather than mere error. Long treated in NLP as \textit{noise} to be eliminated, HLV has only recently been reframed as a \textit{signal} for improving model robustness. With the rise of large language models (LLMs) and post-training methods such as human feedback-based alignment, the role of HLV has become increasingly consequential. Yet current preference-learning datasets routinely collapse multiple annotations into a single label, flattening diverse perspectives into artificial consensus. Preserving HLV is necessary not only for pluralistic alignment but also for sociotechnical safety evaluation, where model behavior must be assessed in relation to human interaction and societal context.This position paper argues that preserving HLV as an embodiment of human pluralism must be treated as a \textit{Selbstzweck}, an intrinsic value in itself. We analyze the limitations of existing preference datasets and propose actionable strategies for incorporating HLV into dataset construction to better preserve pluralistic human values.

ACL 2026

CMIG: Conceptual Metaphor Theory-Inspired Framework for Metaphorical Image Generation

Qingbao Huang, Cheng Yang, Jiawei Yao, Zhiyue Liu, Yi Cai, Xingmao Zhang

Metaphorical text expresses meaning through cross-domain mappings rather than literal surface content, which makes it difficult for text-to-image systems to generate semantically faithful images. We propose CMIG, a structured prompting framework inspired by Conceptual Metaphor Theory (CMT). CMIG identifies source–target mappings, filters projectable source attributes, and selects a visual realization strategy in a reproducible reasoning workflow. Experiments on DALL\cdotE 3, Imagen 2, and FLUX-1 show that CMIG consistently improves semantic alignment and yields a better overall balance of human-rated metaphor quality, visual coherence, and controllability on metaphorical prompts. To support systematic evaluation, we also construct a 3,500-instance visual metaphor benchmark.

ACL 2026

Experience-Driven Multi-Agent Optimization for Black-Box Jailbreak Attacks on Large Language Models

Zhaoyang Han, Yihe Liu, Kai Zhang, Ping Li

The rapid discovery of jailbreak prompts has revealed the alarming fragility of safety alignment in frontier large language models (LLMs). While jailbreak techniques play a critical role in red-teaming and safety evaluation, existing methods exhibit three key limitations: (i) poor transferability across model families, requiring model-specific manual tuning; (ii) heavy reliance on large-scale prompt enumeration or exhaustive search, causing prohibitive query costs and poor scalability; and (iii) high sensitivity to input preprocessing or refusal-oriented fine-tuning, leading to attack failures once the underlying model is updated. To address these, we propose Experience-driven Multi-agent Jailbreak Optimization (EMJO), which couples three collaborating agents (Attacker, Analyzer, and Judge) into a closed-loop “probe–evaluate–revise” process, together with a dynamic experience bank accumulating high-quality successful prompts and reusable strategy patterns across iterations and tasks. This design enables query-efficient and transferable jailbreak optimization under black-box access. Extensive experiments on diverse LLMs demonstrate that EMJO consistently outperforms existing black-box jailbreak baselines, achieving up to 11% absolute improvement in attack success rate while reducing the average query cost by up to 7.9\times across two benchmark datasets. These results indicate that EMJO offers an effective and scalable paradigm for systematic jailbreak discovery.

ACL 2026

AdaptiveK: Complexity-Driven Sparse Autoencoders for Interpretable Language Model Representations

Yifei Yao, Hanrong Zhang, Mengnan Du

Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable features, but existing approaches rely on fixed sparsity constraints that fail to account for input complexity. We propose AdaptiveK SAE (Adaptive Top K Sparse Autoencoders), a novel framework that dynamically adjusts sparsity levels based on the semantic complexity of each input. Leveraging linear probes, we demonstrate that context complexity is linearly encoded in LLM representations, and we use this signal to guide feature allocation during training. Experiments across ten language models demonstrate that this complexity-driven adaptation outperforms fixed-sparsity approaches on reconstruction fidelity, explained variance, cosine similarity and interpretability metrics while eliminating the burden of extensive hyperparameter tuning. Our code is available at: https://github.com/hiyukie/adaptiveK.

ACL 2026

ElasticFlow: One-Step Physics-Consistent Policy with Elastic Time Horizons for Language-Guided Manipulation

Kewei Chen, Yayu Long, Shuai Li, Mingsheng Shang

Diffusion policies have demonstrated exceptional performance in embodied AI. However, their iterative denoising process results in high latency, and existing acceleration methods often sacrifice physical consistency. To address this, we propose ElasticFlow, a distillation-free, physics-consistent one-step policy framework. We reconstruct the Mean Field Theory by directly modeling the average velocity field, enabling a direct single-step mapping from noise to action. Addressing the Temporal Heterogeneity of robotic tasks, we introduce the Elastic Time Horizons mechanism. This mechanism effectively overcomes Spectral Bias by explicitly encoding control granularity, achieving efficient alignment between semantic instructions and physical execution horizons. Experiments on benchmarks such as LIBERO, CALVIN, and RoboTwin demonstrate that ElasticFlow achieves efficient 1-NFE inference (approximately 71Hz). Furthermore, it outperforms state-of-the-art methods, including OpenVLA and \pi_0, on long-horizon tasks, highlighting its potential for efficient, robust, and semantically aligned control.

ACL 2026

BNLP: A Text Annotation Platform for Quality Control of LLM-Generated Annotations

Xinhao Zhuang, Qiongyu Tian, Yalin Chen, Tianle Xin, Yongyong Fu, Yunchao Ling, Guoqing zhang

High-quality annotated data is crucial for NLP, yet manual annotation is costly and difficult to scale in low-resource settings. Large Language Models (LLMs) have demonstrated strong zero-shot and few-shot generalization in NLP tasks, but existing annotation tools either lack LLM support or use LLMs only as one-off pre-annotation engines, without incorporating collaboration or quality control, compromising data reliability. We present BNLP, a text annotation platform that embeds LLM-assisted labeling into a quality-aware collaborative workflow. BNLP treats LLM outputs as intermediate, revisable states and integrates multi-role collaboration, iterative review cycles, and consistency analysis to enable continuous quality monitoring while preserving efficiency gains. BNLP also natively supports AI-ready formats such as Excel and JSON, ensuring seamless data flow from manual annotation to model training. Experiments show that BNLP reduces annotation time by 74.3% and improves annotation quality by 11.6% over purely manual annotation in LLM-assisted settings.

ACL 2026

Sem-DPO: Mitigating Semantic Inconsistency in Preference Optimization for Prompt Engineering

Anas Mohamed, Azal Ahmad Khan, Xinran Wang, Ahmad Faraz Khan, Shuwen Ge, Saman Bahzad Khan, Ayaan Ahmad, Ali Anwar

Generative AI can now synthesize strikingly realistic images from text, yet output quality remains highly sensitive to how prompts are phrased. Direct Preference Optimization (DPO) offers a lightweight, off-policy alternative to RL for automatic prompt engineering, but its token-level regularization leaves semantic inconsistency unchecked as prompts that win higher preference scores can still drift away from the user’s intended meaning. We introduce Sem-DPO, a variant of DPO that preserves semantic consistency yet retains its simplicity and efficiency. Sem-DPO adjusts the DPO loss using a weight based on how different the winning prompt is from the original, reducing the impact of training examples that are semantically misaligned. We provide the first analytical bound on semantic drift for preference-tuned prompt generators, showing that Sem-DPO keeps learned prompts within a provably bounded neighborhood of the original text. On three standard text-to-image prompt-optimization benchmarks and three language models, Sem-DPO achieves 8–12% higher CLIP similarity and 5–9% higher human-preference scores (HPSv2.1, PickScore) than DPO, while also outperforming state-of-the-art prompt optimization baselines as well as several DPO variants. These findings suggest that strong flat baselines augmented with semantic weighting should become the new standard for prompt-optimization studies and lay the groundwork for broader, semantics-aware preference optimization in language models.

ACL 2026

MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language Models

Boqi Chen, Xudong Liu, Jiachuan Peng, Marianne Frey-Marti, Kyle Lam, Bang Zheng, Lin Li, Jianing Qiu

Multimodal large language models (MLLMs) have shown great potential in medical applications, yet existing benchmarks inadequately capture real-world clinical complexity. We introduce MEDSYN, a multilingual, multimodal benchmark of highly complex clinical cases with up to 7 distinct visual clinical evidence (CE) types per case. Mirroring clinical workflow, we evaluate 18 MLLMs on differential diagnosis (DDx) generation and final diagnosis (FDx) selection. While frontier models often match or even outperform human experts on DDx generation, all MLLMs exhibit a much larger DDx–FDx performance gap compared to expert clinicians, indicating a failure mode in synthesis of heterogeneous CE types. Ablations attribute this failure to (i) overreliance on less discriminative textual CE (e.g., medical history) and (ii) a cross-modal CE utilization gap. We introduce Evidence Sensitivity to quantify the latter and show that a smaller gap correlates with higher diagnostic accuracy. Finally, we demonstrate how it can be used to guide interventions to improve model performance. https://github.com/jianing-lab/MEDSYN.

ACL 2026

RLShield: Dynamic Jailbreak Detection for LLMs via Reinforced Adaptive Learning

Zhao Tong, Pengfei Yang, Yimeng Gu, Haichao Shi, Qiang Liu, Xingcheng Xu, Shu Wu, Xiao-Yu Zhang

While prompt engineering enhances the capabilities of Large Language Models (LLMs), it also exposes critical safety concerns. Due to the inherent brittleness of their static safety boundaries, LLMs are vulnerable to jailbreak prompts, i.e. adversarial inputs designed to bypass safeguards and induce the generation of harmful content. Existing detection mechanisms rely on static model components or fixed decision thresholds, limiting their ability to generalize to evolving attack patterns and continual model updates. To bridge this gap, we propose RLShield, a dynamic jailbreak detection framework that employs reinforcement learning for adaptive threshold selection. RLShield incorporates three key innovations: (i) a dynamic retrieval and LLM-based rewriting module to simulate diverse adversarial contexts; (ii) a cross-layer representation analysis to pinpoint safety-critical parameters; and (iii) a Soft Actor-Critic (SAC) based agent that learns to predict optimal, sample-specific detection thresholds. Experimental results demonstrate that RLShield consistently outperforms state-of-the-art baselines in detection performance while maintaining high computational efficiency. Notably, it improves F1 by up to 7.3%, while achieving an average of 3\times gain in inference efficiency across multiple LLM backbones.

ACL 2026

Seeing Beyond Words: MatVQA for Challenging Visual-Scientific Reasoning in Materials Science

Sifan Wu, Huan Zhang, Yizhan Li, Farshid Effaty, Hongyuan Mei, Amirreza Ataei, Bang Liu

The emergence of Multimodal Large Language Models (MLLMs) that integrate vision and language modalities has unlocked new potentials for scientific reasoning, outperforming prior benchmarks in both natural language and coding domains. Current materials science evaluation datasets such as MaScQA and SciQA remain largely text-based and fail to capture the visual and research-level analytic complexity required in materials discovery and design. We introduce MatVQA, a scalable benchmark specifically designed to address this gap. Generated via an automated pipeline, MArxivAgent, from recent materials literature, MatVQA features 1672 questions across four critical structure-property-performance (SPP) reasoning tasks. Uniquely, MatVQA employs an iterative process to eliminate textual shortcuts, compelling MLLMs to perform fine-grained, low-level visual analysis of material imagery (e.g., microscopy, diffraction patterns) integrated with multi-step scientific reasoning. Benchmarking 19 open- and closed-source MLLMs on MatVQA reveals substantial gaps in current multimodal reasoning capabilities. The MatVQA benchmark is publicly available[https://huggingface.co/datasets/trqcbf/matvqa_v2] to facilitate further research on applying MLLMs to complex materials science problems.

ACL 2026

FFN Lens: How Transformers Divide Labor for Multilingual Tasks

Jiatong Li, Hailong Cao, Yang Liu

Large Language Models (LLMs) demonstrate strong performance in multilingual tasks, yet the process of constructing predictions in the target language remains under-explored. In this work, we introduce the FFN Lens, a novel interpretability method focusing on the Transformer’s core computational module, the Feed-Forward Network (FFN). By directly leveraging model parameters, the FFN Lens identifies both the critical units responsible for constructing specific information and the input features that drive them, which is essential for understanding Large Language Models. Applying FFN Lens to multilingual tasks, we demonstrate the prediction construction process and reveal the distinct division of labor across model layers. We identify a three-stage functional pipeline for constructing multilingual predictions: Latent Translation, Semantic Mapping, and Self Emphasis. We further introduce subspace analysis to validate this three-stage mechanism from a complementary perspective, and leverage these mechanistic insights to propose a training-free uncertainty estimation method.

ACL 2026

UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning

Xiaolong Wei, Zerun Zhu, Simin Niu, Xingyu Zhang, Peiying Yu, Changxuan Xiao, Yuchen Li, Jicheng Yang, Zhejun Zhao, Chong Meng, Long Xia, Daiting Shi

A fundamental challenge in creative writing lies in reconciling the inherent tension between maintaining global coherence in long-form narratives and preserving local expressiveness in short-form texts. While long-context generation necessitates explicit macroscopic planning, short-form creativity often demands spontaneous, constraint-free expression. Existing alignment paradigms, however, typically employ static reward signals and rely heavily on high-quality supervised data, which is costly and difficult to scale. To address this, we propose UniCreative, a unified reference-free reinforcement learning framework. We first introduce AC-GenRM, an adaptive constraint-aware reward model that dynamically synthesizes query-specific criteria to provide fine-grained preference judgments. Leveraging these signals, we propose ACPO, a policy optimization algorithm that aligns models with human preferences across both content quality and structural paradigms without supervised fine-tuning and ground-truth references. Empirical results demonstrate that AC-GenRM aligns closely with expert evaluations, while ACPO significantly enhances performance across diverse writing tasks. Crucially, our analysis reveals an emergent meta-cognitive ability: the model learns to autonomously differentiate between tasks requiring rigorous planning and those favoring direct generation, validating the effectiveness of our direct alignment approach.

ACL 2026

LLM Inductive Reasoning Through Multi-Agent Enhanced Monte Carlo Tree Search

Xiang Li, Yucheng Zhou, Xiangzhi Wei, Zesheng Shi, Haiyuan Wan, Gong Yifan, Fangming Liu, Jing Li

Existing methods for enhancing the inductive reasoning of large language models (LLMs) at test-time typically depend on iterative self-refinement of hypotheses, which lacks explicit optimization guidance and effective error correction. This often results in superficial rewording and the accumulation of errors. To overcome these limitations, we propose MATSIR, a plug-and-play test-time framework integrating Multi-Agent coordination with Monte Carlo Tree Search to improve Inductive Reasoning. MATSIR incorporates a dual-reward mechanism that provides explicit refinement signals, promoting logically coherent and semantically enriched hypotheses rather than mere rephrasing. Furthermore, it enables trajectory-level error correction through backtracking and pruning, allowing the system to recover from erroneous intermediate hypotheses. Experiments on five benchmarks across four LLMs show that MATSIR consistently outperforms previous best methods, yielding the highest average improvement of +4.9% on QWQ-32B and all-round improvement on Deepseek-V3. Our findings highlight that explicit guided search with built-in error correction is essential for advancing inductive reasoning in LLMs. Code is available at https://github.com/SolarWindRider/MATSIR

ACL 2026

Health-ORSC-Bench: A Benchmark for Measuring Over-Refusal and Safety Completion in Health Context

Zhihao Zhang, Liting Huang, Guanghao Wu, Preslav Nakov, Heng Ji, Usman Naseem

Safety alignment in Large Language Models is critical for healthcare; however, reliance on binary refusal boundaries often results in over-refusal of benign queries or unsafe compliance with harmful ones. While existing benchmarks measure these extremes, they fail to evaluate Safe Completion: the model’s ability to maximise helpfulness on dual-use or borderline queries by providing safe, high-level guidance without crossing into actionable harm. We introduce Health-ORSC-Bench, the first large-scale benchmark designed to systematically measure Over-Refusal and Safe Completion quality in healthcare. Comprising 31,920 benign boundary prompts across seven health categories (e.g., self-harm, medical misinformation), our framework uses an automated pipeline with human validation to test models at varying levels of intent ambiguity. We evaluate 30 state-of-the-art LLMs, including GPT-5 and Claude-4, revealing a significant tension: safety-optimised models frequently refuse up to 80% of “Hard” benign prompts, while domain-specific models often sacrifice safety for utility. Our findings demonstrate that model family and size significantly influence calibration: larger frontier models (e.g., GPT-5, Llama-4) exhibit “safety-pessimism” and higher over-refusal than smaller or MoE-based counterparts (e.g., Qwen-3-Next), highlighting that current LLMs struggle to balance refusal and compliance. Health-ORSC-Bench provides a rigorous standard for calibrating the next generation of medical AI assistants toward nuanced, safe, and helpful completions. Our code and data is available at: https://github.com/ZhihaoZhang97/Health-ORSC-Bench. Warning: Some contents may include toxic or undesired contents.

ACL 2026

Scripts Through Time: A Survey of the Evolving Role of Transliteration in NLP

Thanmay Jayakumar, Deepon Halder, Raj Dabre

Cross-lingual transfer in NLP is often hindered by the “script barrier” where differences in writing systems inhibit transfer learning between languages. Transliteration, the process of converting the script, has emerged as a powerful technique to bridge this gap by increasing lexical overlap. This paper provides a comprehensive survey of the application of transliteration in cross-lingual NLP. We present a taxonomy of key motivations to utilize transliterations in language models, and also provide an overview of different approaches of incorporating transliterations as input. We analyze the evolution and effectiveness of these methods, discussing the critical trade-offs involved, and contextualize their need in modern LLMs. The review explores various contexts how transliteration is beneficial, including handling code-mixed text, leveraging language family relatedness, and pragmatic gains in inference efficiency. Based on this analysis, we provide concrete recommendations for researchers on selecting and implementing the most appropriate transliteration strategy based on their specific language, task, and resource constraints.

ACL 2026

Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs

Kai Wang, Haoyang You, Yang Zhang, Zhongjie Wang

A core challenge for faithful LLM role-playing is sustaining consistent characterization throughout long, open-ended dialogues, as models frequently fail to recall and accurately apply their designated persona knowledge without explicit cues. To tackle this, we propose the Memory-Driven Role-Playing paradigm. Inspired by Stanislavski’s "emotional memory” acting theory, this paradigm frames persona knowledge as the LLM’s internal memory store, requiring retrieval and application based solely on dialogue context, thereby providing a rigorous test of depth and autonomous use of knowledge. Centered on this paradigm, we contribute: (1) MREval, a fine-grained evaluation framework assessing four memory-driven abilities—Anchoring, Selecting, Bounding, and Enacting; (2) MRPrompt, a prompting architecture that guides structured memory retrieval and response generation; and (3) MRBench, a bilingual (Chinese/English) benchmark for fine-grained diagnosis. The novel paradigm provides a comprehensive diagnostic for four-stage role-playing abilities across 12 LLMs. Crucially, experiments show that MRPrompt allows small models (e.g., Qwen3-8B) to match the performance of much larger closed-source LLMs (e.g., Qwen3-Max and GLM-4.7), and confirm that upstream memory gains directly enhance downstream response quality, validating the staged theoretical foundation.

ACL 2026

Verifying the Subjective: Structured Multilingual Rewards for Low-Resource Alignment

Jiu Sha, Mengxiao Zhu

Aligning LLMs in low-resource multilingual settings faces a fundamental reward bottleneck: scalar rewards lack cultural generalization, while unstructured critiques remain noisy and unverifiable. To bridge this gap, we introduce a Structured Multilingual Reward Modeling Framework that extends Reinforcement Learning with Verifiable Rewards (RLVR) to subjective and open-ended tasks. The framework unifies three core components to transform abstract quality into concrete supervision: (1) a Structured Checklist Schema decomposing evaluation into granular universal reasoning steps and task-specific criteria; (2) Structured Generative Critique Modeling, which produces rubric-aligned critiques with grounded justifications; and (3) Adaptive Multilingual Reward Optimization, integrating reasoning quality and language consistency into a verifiable objective. We integrate this framework into a bootstrapped Group Relative Policy Optimization pipeline, augmented by length-aware normalization and variance stabilization to ensure stability. Extensive experiments on a newly constructed suite covering 7 subjective task categories across 50 low-resource languages demonstrate that this checklist-driven approach yields substantial improvements in reasoning capability and response quality, particularly in settings where traditional reward models exhibit significant degradation. We publicly release our models and the corresponding evaluation benchmark to facilitate further research. Our code is available at https://github.com/Shajiu/SGCM.

ACL 2026

ReCon: Active Defense against Large Vision-Language Model Jailbreaks via Reverse Safety Concept Injection

Zheng He, Yiwei Wang, Hongxing Wang, Yujun Cai

Large Vision-Language Models (LVLMs) confront an escalating threat from sophisticated multimodal jailbreak attacks. However, existing defense strategies suffer from three critical limitations: (1) the neglect of visual threats; (2) a lack of fine-grained specificity regarding specific attack semantics; and (3) the absence of a dedicated jailbreak detection mechanism, which leads to unnecessary defensive measures against benign inputs. To address these limitations, we propose ReCon, a novel black-box defense framework. ReCon integrates a diffusion-based image purifier to neutralize visual perturbations and an autoencoder-based detector for anomaly filtration. At its core, it employs a Reverse Safety Concept Injection module that maps detected unsafe concepts to fine-grained, constructive Safe Concepts, generating targeted prompts to precisely rectify attack semantics. Extensive experiments demonstrate that ReCon significantly enhances the robustness of LVLMs against jailbreak attacks while preserving performance on benign tasks. Disclaimer: Samples in this paper may be harmful and cause discomfort.

Keep browsing

More papers from top AI conferences

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