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

JX4MEI: Multimodal Semantically-Enhanced LLM for Joint Multimodal Emotion-Intent Explanation and Classification

Yijie Huang, Xiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang, Ning Yuan, Zhuoyue Jia, Wen Zhang

Existing multimodal emotion and intent recognition tasks predominantly focus on classification, overlooking the underlying rationale and intrinsic connections between these states. Bridging this gap, we propose Joint Multimodal Emotion-Intent Explanation and Classification, JX4MEI, a novel task requiring the model to jointly predict emotion and intent, while generating natural language explanations for why they co-occur. To support this, we present XMEI-dataset, a large-scale benchmark of 15,461 multimodal samples spanning 7 emotion and 9 intent categories across text, audio, and visual modalities. Unlike prior works, our dataset provides fine-grained rationales for emotion, intent, and their causal interplay, curated via a rigorous pipeline involving Chain-of-Thought generation and strict human refinement to eliminate model artifacts. Furthermore, we propose XMEI-Qwen, a model equipped with a novel Language-Query Former (LQ-Former). By leveraging modality-specific captions as semantic queries, LQ-Former injects explicit semantic guidance into feature alignment, significantly enhancing reasoning capabilities. Empirical experiments demonstrate that XMEI-Qwen sets a new state-of-the-art on the JX4MEI task, outperforming competitive baselines in both prediction and explanation generation. Code: https://github.com/OrangeYeah1027/JX4MEI.

ACL 2026

ReMedi: Reasoner for Medical Clinical Prediction

Yushi Cao, Yiming Chen, Hongchao Jiang, Hung-yi Lee, Robby T. Tan

Predicting future clinical outcomes from electronic health records (EHR) remains challenging due to the complexity and heterogeneity of patient data. LLMs have shown strong potential for such predictive tasks, yet existing approaches mainly focus on enhancing medical knowledge through distillation or RAG while relying on the model’s internal ability to interpret contextual information. In this work, we present ReMedi (Reasoner for Medical Clinical Prediction), a framework for improving clinical outcome prediction from EHR. ReMedi generates rationale–answer pairs using a challenging sample regeneration mechanism for complex clinical questions, which leverages ground-truth answers as hints to enhance reasoning for further fine-tuning and preference tuning. ReMedi integrates ground-truth outcome guidance into the preference data construction loop, regenerating rationale-answer variants. By tuning on these rationale-answer pairs, the model improves its predictive performance. Experiments on multiple EHR prediction tasks demonstrate substantial gains of up to 19.9% over state-of-the-art baselines in terms of F1 score, underscoring ReMedi’s effectiveness in real-world clinical prediction.

ACL 2026

Graph-GRPO: Stabilizing Multi-Agent Topology Learning via Group Relative Policy Optimization

Yueyang Cang, Xiaoteng Zhang, Erlu Zhao, Zehua Ji, Yuhang Liu, Yuchen He, Zhiyuan Ning, Chen Yijun, Wenge Que, Li Shi

Optimizing communication topology is fundamental to the efficiency and effectiveness of Large Language Model (LLM)-based Multi-Agent Systems (MAS). While recent approaches utilize reinforcement learning to dynamically construct task-specific graphs, they typically rely on single-sample policy gradients with absolute rewards (e.g., binary correctness). This paradigm suffers from severe gradient variance and the credit assignment problem: simple queries yield non-informative positive rewards for suboptimal structures, while difficult queries often result in failures that provide no learning signal. To address these challenges, we propose Graph-GRPO, a novel topology optimization framework that integrates Group Relative Policy Optimization. Instead of evaluating a single topology in isolation, Graph-GRPO samples a group of diverse communication graphs for each query and computes the advantage of specific edges based on their relative performance within the group. By normalizing rewards across the sampled group, our method effectively mitigates the noise derived from task difficulty variance and enables fine-grained credit assignment. Extensive experiments on reasoning and code generation benchmarks demonstrate that Graph-GRPO significantly outperforms state-of-the-art baselines, achieving superior training stability and identifying critical communication pathways previously obscured by reward noise.

ACL 2026

DynamicFocalPO: Adaptive Focusing Strategy for Preference Optimization

Shu Zhou, Junan Chen, Rui ling, Xin Wang, Tao Fan, Hao Wang

Recent preference optimization algorithms such as Direct Preference Optimization (DPO) have become prevalent for aligning large language models (LLMs) with human preferences. FocalPO improves upon DPO by introducing a modulating factor that down-weighs misranked preference pairs. However, using a fixed modulating factor throughout training is suboptimal, as the model’s learning capacity evolves during training. We introduce DynamicFocalPO, which employs a dynamic focusing strategy that adapts over the course of training. Inspired by curriculum learning, our method initially focuses on correctly ranked samples to establish a solid foundation, then gradually incorporates harder samples as training progresses. Experiments demonstrate that DynamicFocalPO surpasses both DPO and FocalPO on benchmarks including Alpaca Eval 2.0 and Arena-Hard using Mistral-Base-7B and Llama-3-Instruct-8B. We further provide theoretical analysis showing that the dynamic schedule enables adaptive entropy regularization and selective gradient suppression.

ACL 2026

Where meaning lives: Layer-wise accessibility of psycholinguistic features in encoder and decoder language models

Taisiia Tikhomirova, Dirk U. Wulff

Understanding where transformer language models encode psychologically meaningful aspects of meaning is essential for both theory and practice. We conduct a systematic layer-wise probing study of 58 psycholinguistic features across 10 transformer models, spanning encoder-only and decoder-only architectures, and compare three embedding extraction methods. We find that apparent localization of meaning is strongly method-dependent: contextualized embeddings yield higher feature-specific selectivity and different layer-wise profiles than isolated embeddings. Across models and methods, final-layer representations are rarely optimal for recovering psycholinguistic information with linear probes. Despite these differences, models exhibit a shared depth ordering of meaning dimensions, with lexical properties peaking earlier and experiential and affective dimensions peaking later. Together, these results show that where meaning “lives” in transformer models reflects an interaction between methodological choices and architectural constraints.

ACL 2026

LatentRefusal: Latent-Signal Refusal for Unanswerable Text-to-SQL Queries

Xuancheng Ren, Shijing Hu, Zhihui Lu, Jiangqi Huang, Qiang Duan

In LLM-based Text-to-SQL systems, unanswerable and underspecified user queries may generate not only incorrect text but also executable programs that yield misleading results or violate safety constraints, thus posing a major barrier to safe deployment. Existing refusal strategies for such queries either rely on output-level instruction following, which is brittle due to model hallucinations, or on estimating output uncertainty, which adds complexity and overhead. To address this challenge, we first formalize safe refusal in Text-to-SQL systems as an answerability-gating problem, and then propose LatentRefusal, a latent-signal refusal mechanism that predicts query answerability from intermediate hidden activations of an LLM. We introduce the Tri-Residual Gated Encoder (TRGE), a lightweight probing architecture, to suppress schema noise and amplify sparse, localized question–schema mismatch cues that indicate unanswerability. Extensive empirical evaluations across diverse ambiguous and unanswerable settings, together with ablations and interpretability analyses, demonstrate the effectiveness of the proposed scheme and show that LatentRefusal provides an attachable, efficient safety layer for Text-to-SQL systems. Across four benchmarks, LatentRefusal achieves an average F1 of 88.5% and 88.8% on Llama-3.1-8B and Qwen-3-8B respectively, while adding ~2ms probe overhead.

ACL 2026

Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation

Zhiheng Li, Zongyang Ma, Yuntong Pan, Ziqi Zhang, Xiaolei Lv, Bo Li, Jun Gao, Jianing Zhang, Chunfeng Yuan, Bing Li, Weiming Hu

Multimodal Large Language Models (MLLMs) are increasingly being deployed as automated content moderators. Within this landscape, we uncover a critical threat: Adversarial Smuggling Attacks. Unlike adversarial perturbations (for misclassification) and adversarial jailbreaks (for harmful output generation), adversarial smuggling exploits the Human-AI capability gap. It encodes harmful content into human-readable visual formats that remain AI-unreadable, thereby evading automated detection and enabling the dissemination of harmful content. We classify smuggling attacks into two pathways: (1) Perceptual Blindness, disrupting text recognition; and (2) Reasoning Blockade, inhibiting semantic understanding despite successful text recognition. To evaluate this threat, we constructed SmuggleBench, the first comprehensive benchmark comprising 1,700 adversarial smuggling attack instances. Evaluations on SmuggleBench reveal that both proprietary (e.g., GPT-5) and open-source (e.g., Qwen3-VL) SOTA models are vulnerable to this threat, producing Attack Success Rates (ASR) exceeding 90%. By analyzing the vulnerability through the lenses of perception and reasoning, we identify three root causes: the limited capabilities of vision encoders, the robustness gap in OCR, and the scarcity of domain-specific adversarial examples. We conduct a preliminary exploration of mitigation strategies, investigating the potential of test-time scaling (via CoT) and adversarial training (via SFT) to mitigate this threat.

ACL 2026

G-LoRA: Global-Local Decoupled Low-Rank Adaptation

Jiahao Xiong, Yihong Huang, Yihe Liu, Xianming Hu, Hongbo Zhao, Kai Zhang

Low-Rank Adaptation (LoRA) has achieved remarkable progress in improving the fine-tuning efficiency and downstream performance of large language models (LLMs). Although prior work has recognized that different weight update matrices \Delta \mathbf{W} exhibit varying importance and therefore should be allocated different ranks, parameters within the same update matrix are still typically constrained to a uniform rank configuration, neglecting fine-grained parameter-level heterogeneity. To address this limitation, we propose G-LoRA (Global-Local Decoupled LoRA), which decomposes each update matrix into global and local adapters. The key idea is to reorganize the rows and columns of the update matrix using a first-order Taylor approximation of parameter importance, such that highly influential parameters are clustered into a local sub-block of \Delta \mathbf{W}. During training, the local adapter then focuses on this high-importance sub-region and is allocated a higher rank, whereas the global adapter captures the residual updates for the entire update matrix with relatively lower rank. By allocating higher representational capacity to more critical parameters, G-LoRA enables more efficient utilization of model resources. Extensive evaluations on benchmarks spanning commonsense reasoning, mathematical reasoning, and code generation demonstrate that G-LoRA achieves up to 2.7% absolute accuracy improvement over LoRA and its variants, validating its effectiveness for LLM fine-tuning.

ACL 2026

S2ST-Omni: Hierarchical Language-Aware SpeechLLM Adaptation for Multilingual Speech-to-Speech Translation

Yu Pan, Xiongfei Wu, Yang Yuguang, Jixun Yao, Maxime Cordy, Lei Ma, Jianjun Zhao

Despite recent advances in speech-to-speech translation (S2ST), it remains difficult to achieve both high translation accuracy and practical flexibility. In this paper, we present S2ST-Omni, a compositional S2ST framework that integrates a high-accuracy speech-to-text translation (S2TT) frontend with a modular, plug-and-play text-to-speech (TTS) backend, enabling independent optimization of translation and synthesis. On the S2TT side, we introduce a hybrid adapter that follows a “local-then-global” strategy to bridge the pretrained Whisper encoder and Qwen3 LLM, yielding a hierarchical acoustic-to-semantic abstraction. Building on this bridge, we further propose a hierarchical language-aware architecture that injects source-language information at two complementary levels. At the acoustic level, Language-Aware Dual-CTC operates on intermediate adapter features and employs FiLM-style feature modulation with a learnable gate, encouraging the model to learn language-specific but content-faithful acoustic representations. At the linguistic level, Language-Aware Prompting dynamically constructs source-language-conditioned prompts that activate language-specific translation knowledge in the LLM. To enable efficient optimization, we design a task-specific progressive fine-tuning strategy that first stabilizes speech-text alignment and then improves translation via LoRA on top of this converged foundation. The TTS backend remains fully modular and can be instantiated with any state-of-the-art synthesizer without retraining the S2TT frontend. Experiments on CVSS-C show that S2ST-Omni consistently achieves the best BLEU and ASR-BLEU across French, German, and Spanish to English directions, outperforming strong recent S2ST baselines.

ACL 2026

Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design

Xu Guo, Qiming Ge, Jian Tong, Kedi Chen, Jin Zhang, Xiaogui Yang, Xuan Gao, Haijun Lv, Zhihui Lu, Yicheng Zou, Qipeng Guo

Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capabilities of Large Language Models. When applied to RLVR, Multiple-Choice Questions (MCQs) offer a scalable source of verifiable data but risk inducing reward hacking, where models shortcut reasoning via random guessing or simple elimination. Current approaches often mitigate this by converting MCQs to open-ended formats, thereby discarding the contrastive signal provided by expert-designed distractors. In this work, we systematically investigate the impact of option design on RLVR. Our analysis highlights two primary insights: (1) Mismatches in option counts between training and testing degrade performance. (2) Strong distractors effectively mitigate random guessing, enabling effective RLVR training even with 2-way questions. Motivated by these findings, we propose Iterative Distractor Curation (IDC), a framework that actively constructs high-quality distractors to block elimination shortcuts and promote deep reasoning. Experiments on various benchmarks demonstrate that our method effectively enhances distractor quality and yields significant gains in RLVR training compared to the original data.

ACL 2026

HAUNTATTACK: When Attack Follows Reasoning as a Shadow

Jingyuan Ma, Rui Li, Zheng Li, Junfeng Liu, Heming Xia, Lei Sha, Zhifang Sui

Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities. However, the enhancement of reasoning abilities and the exposure of internal reasoning processes introduce new safety vulnerabilities. A critical question arises: when reasoning becomes intertwined with harmfulness, will LRMs become more vulnerable to jailbreaks in reasoning mode? To investigate this, we introduce HauntAttack, a novel and general-purpose black-box adversarial attack framework that systematically embeds harmful instructions into reasoning questions. Specifically, we modify key reasoning conditions in existing questions with harmful instructions, thereby constructing a reasoning pathway that guides the model step by step toward unsafe outputs. We evaluate HauntAttack on 11 LRMs and observe an average attack success rate of over 70%, achieving up to 13 percentage points of absolute improvement over the strongest prior baseline. Our further analysis reveals that even advanced safety-aligned models remain highly susceptible to reasoning-based attacks, offering insights into the urgent challenge of balancing reasoning capability and safety in future model development.

ACL 2026

EchoMLLM: Incentivizing Echocardiographic Video Understanding with Keyframe Grounding and Report Generation

Heyu Huang, Wanran Sun, Chi Chen, Bo Chen, Zonghao Guo, Yuhua Li, Ruixuan Li, Kunlun He, Maosong Sun

Echocardiography analysis demands a dual capability: rigorous quantitative keyframe localization for evidence verification and comprehensive qualitative synthesis for diagnostic reporting. However, current Multi-Modal Large Language Models (MLLMs) struggle to meet these clinical requirements due to a misalignment with diagnostic workflows, a scarcity of video instruction data, and the critical challenge of cyclic temporal ambiguity—where the repetitive nature of cardiac cycles renders standard single-frame supervision ill-posed. To bridge this gap, we introduce EchoMLLM, a unified framework designed for real-world echocardiography video understanding. First, we align model capabilities with clinical needs by defining two fine-grained tasks: cycle- and pathology-conditioned keyframe grounding and video report generation. To facilitate this, we curate EchoMM-120k, a large-scale instruction dataset specifically constructed to support temporal localization and professional reporting. Furthermore, to resolve the cyclic ambiguity, we propose a multi-stage training paradigm incorporating a novel cycle-aware Reinforcement Learning (RL) strategy. By prioritizing logical consistency over rigid index matching, our approach moves beyond rote memorization to elicit invariant reasoning. Extensive experiments demonstrate that EchoMLLM reduces temporal grounding errors by up to 76% and improves report generation quality by 65% over its backbone, achieving state-of-the-art performance against both generalist and medical baselines.

ACL 2026

Towards IP Intelligence: Benchmarking Large Language Models on Intellectual Property Knowledge and Practice

Qiyao Wang, Guhong Chen, Hongbo Wang, Huaren Liu, Minghui Zhu, Zhifei Qin, Li Linwei, Yilin Yue, Shiqiang Wang, Jiayan Li, Wu Yihang, Ziqiang Liu, Longze Chen, Run Luo, Liyang Fan, Jiaming Li, Lei Zhang, Kan Xu, Hamid Alinejad-Rokny, Chengming Li, Shiwen Ni, Yuan Lin, Min Yang

Intellectual Property (IP) is a highly specialized domain that integrates technical and legal knowledge, making it inherently complex and knowledge-intensive. Recent advancements in LLMs have demonstrated their potential to handle IP tasks, enabling more efficient analysis, understanding, and generation of IP-related content. However, existing datasets and benchmarks focus narrowly on patents or cover limited aspects of the IP field, lacking alignment with real-world scenarios. To bridge this gap, we introduce IPBench, the first comprehensive IP task taxonomy and a large-scale bilingual benchmark encompassing 8 IP mechanisms and 20 distinct tasks, designed to evaluate LLMs in real-world IP practice. We benchmark 19 main LLMs, ranging from general purpose to domain-specific, including chat-oriented and reasoning-focused models, under zero-shot, few-shot, and chain-of-thought settings. Our results show that even the top-performing model, DeepSeek-V3, achieves only 75.8% accuracy, indicating significant room for improvement. Notably, open-source IP and law-oriented models lag behind closed-source general-purpose models. To foster future research, we publicly release IPBench, and will expand it with additional tasks to better reflect real-world complexities and support model advancements in the IP domain. We provide the data, code in the supplementary materials.

ACL 2026

PEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes

Yingyu Shan, Zeming Liu, Silin Li, Boao Qian, Jiashu Yao, Yuhang Guo, Haifeng Wang

Recent advancements in Large Language Models (LLMs) have empowered home assistants with natural language interaction capabilities. However, current assistants overlook the progressive omission that occurs in human dialogue as shared context accumulates, leading to more elliptical expressions for efficient communication. Thus, current assistants still struggle to interpret such elliptical expressions accurately, which limits their effectiveness in real-world applications. In practical smart home scenarios, assistants face two major challenges caused by elliptical commands: (1) referential ambiguity caused by different environmental expectations among multiple users; and (2) intention ambiguity resulting from user preferences that evolve over time or change with the environment. To address these challenges, we introduce PEC-Home, the first simulated home dataset specifically designed for interpreting progressively elliptical commands in smart homes. Extensive experiments on various LLMs, including GPT-4o, show that existing home assistants struggle to execute user-intended operations based solely on elliptical commands. Even when equipped with tools for storing and retrieving user dialogue history, execution accuracy remains below that achieved with complete commands. Our code and dataset will be publicly available.

ACL 2026

RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding

Zihong Zhang, Zuchao Li, Lefei Zhang, Ping Wang, Hai Zhao

Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigates this through a guess-and-verify strategy, but existing training-free variants face trade-offs: retrieval-based drafts break when no exact match exists, while logits-based drafts lack structural guidance. We propose \textbf{RACER} (\textbf{R}etrieval-\textbf{A}ugmented \textbf{C}ont\textbf{e}xtual \textbf{R}apid Speculative Decoding), a lightweight and training-free method that integrates retrieved exact patterns with logit-driven future cues. This unification supplies both reliable anchors and flexible extrapolation, yielding richer speculative drafts. Experiments on Spec-Bench, HumanEval, and MGSM-ZH demonstrate that RACER consistently accelerates inference, achieving more than 2\times speedup over autoregressive decoding, and outperforms prior training-free methods, offering a scalable, plug-and-play solution for efficient LLM decoding. Our source code is available at https://github.com/hkr04/RACER.

ACL 2026

MAPLE: A Meta-learning Framework for Cross-Prompt Essay Scoring

Salam Albatarni, May Bashendy, Sohaila Eltanbouly, Tamer Elsayed

Automated Essay Scoring (AES) faces significant challenges in cross-prompt settings, where models must generalize to unseen writing prompts. To address this limitation, we propose MAPLE, a meta-learning framework that leverages prototypical networks to learn transferable representations across different writing prompts. Across three diverse datasets (ELLIPSE and ASAP (English), and LAILA (Arabic)), MAPLE achieves state-of-the-art performance on ELLIPSE and LAILA, outperforming strong baselines by 8.5 and 3 points in QWK, respectively. On ASAP, where prompts exhibit heterogeneous score ranges, MAPLE yields improvements on several traits, highlighting the strengths of our approach in unified scoring settings. Overall, our results demonstrate the potential of meta-learning for building robust cross-prompt AES systems.

ACL 2026

HIPO: A Hierarchical Prompt Optimization Framework with Task Awareness and Fine-Grained Debugging

Lu Qi, Lei Chai, Hongrui Yu, Binhang Qi, Hailong Sun

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks. However, their performance often hinges on carefully designed prompts, whose creation requires substantial human effort. While numerous automatic prompt optimization techniques have been proposed, existing methods typically apply the same prompt across all samples within a dataset, ignoring variation in sample difficulty. To address these limitations, we propose HIPO, a HIerarchical Prompt Optimization framework that shifts the paradigm from dataset-level to sample-level optimization. Our framework first employs a lightweight router model, trained offline, to predict the difficulty of each sample at test time. Based on this prediction, HIPO dynamically selects a prompt from a five-tiered hierarchy, tailoring complexity to sample difficulty. Furthermore, two refinement stages—Task Description Prompt Refine and Attribution-Based Prompt Refine—enhance generalizability and fine-grained optimization. Extensive experiments on 27 tasks demonstrate that HIPO outperforms all baselines, achieving state-of-the-art performance on 25% more tasks than the strongest baseline. Cost analysis further demonstrates substantial efficiency gains, reducing API calls, token consumption, and overall cost by 1.2× to 80×. Our implementation is publicly available at https://github.com/LuQiCode/HIPO.

ACL 2026

SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models

Weijiang Lv, Yaoxuan Feng, Xiaobo Xia, Jiayu Wang, Yan Jing, Wenchao Chen, Bo Chen

Chain-of-Thought reasoning is widely used to improve the interpretability of multimodal large language models (MLLMs), yet the faithfulness of the generated reasoning traces remains unclear. Prior work has mainly focused on perceptual hallucinations, leaving reasoning level unfaithfulness underexplored. To isolate faithfulness from linguistic priors, we introduce SPD-Faith Bench, a diagnostic benchmark based on fine-grained image difference reasoning that enforces explicit visual comparison. Evaluations on state-of-the-art MLLMs reveal two systematic failure modes, perceptual blindness and perception-reasoning dissociation. We trace these failures to decaying visual attention and representation shifts in the residual stream. Guided by this analysis, we propose SAGE, a train-free visual evidence-calibrated framework that improves visual routing and aligns reasoning with perception. Our results highlight the importance of explicitly evaluating faithfulness beyond response correctness. Our benchmark and codes are available at https://anonymous.4open.science/r/SPD-Faith/.

ACL 2026

X-Router: Decoupling Knowledge and Reasoning for Cost-Effective LLM Inference

Zixuan Wang, Yinze Ding, Zihan Wang, Jinyu Guo, Zhenhong Zhou, Junhao Dong, Chaomeng Chen

Large Language Models (LLMs) are often augmented with Retrieval-Augmented Generation (RAG) and Chain-of-Thought (CoT) prompting, yet static “always-on” use is computationally wasteful. Existing adaptive methods typically optimize a single axis, overlooking that evidence need and reasoning depth are only partially correlated. We present , a dual-axis routing framework that separates retrieval necessity from reasoning necessity under a user-defined cost–quality trade-off. Offline, profiles four pipelines (Direct, RAG, CoT, RAG+CoT) and derives supervision by selecting the utility-maximizing strategy that trades answer quality against token usage and latency. Online, a compact dual-head router, conditioned on cost weights, uses lightweight probes—retrieval-score dispersion (NQC) and single-pass draft negative log-likelihood (NLL)—to decide whether to invoke RAG and/or CoT without sampling or model internals. Across six QA benchmarks, reduces token usage by up to 86% and latency by up to 84% while improving answer quality over strong baselines.

ACL 2026

Preserving Fairness and Safety in Quantized LLMs Through Critical Weight Protection

Muhammad Alif Al Hakim, Alfan Farizki Wicaksono, Fajri Koto

Quantization is widely adopted to reduce the computational cost of large language models (LLMs); however, its implications for fairness and safety, particularly in dynamic quantization and multilingual contexts, remain underexplored. In this work, we conduct a systematic study of how static and dynamic quantization methods impact fairness and safety across benchmarks measuring intrinsic and extrinsic bias and safety alignment. For fairness, we evaluate English, French, Dutch, Spanish, and Turkish; for safety, we focus on English, Korean, and Arabic. Our findings reveal that quantization consistently degrades fairness and safety, with dynamic methods demonstrating greater stability than static ones. Moreover, fairness degradation varies across languages, while safety deterioration is especially pronounced in non-English settings. To address these risks, we introduce Critical Weight Protection, a novel technique that identifies and preserves fairness- and safety-critical weights during quantization. This approach mitigates bias and safety deterioration without costly retraining or alignment, maintaining trustworthiness while retaining efficiency.

Keep browsing

More papers from top AI conferences

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