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

E-ABSA20K: A Dataset and Propose-and-Verify for Aspect-Based Sentiment Analysis in Long E-commerce Reviews

Tong Sun, Mingyang Ma, Cheng Yu

Aspect-Based Sentiment Analysis (ABSA) is critical for extracting actionable product insights from e-commerce reviews. However, most public ABSA benchmarks are restricted to short texts and a limited range of domains, and therefore underrepresent the challenges posed by real-world reviews—where multiple aspects co-occur, colloquial and noisy expressions are common, and evidence must often be aggregated across sentences in long contexts.We introduce E-ABSA20K, a multi-domain dataset of 20K reviews from four product categories (Women’s Bags, Dresses, Cosmetics, and Furniture), annotated with review-level sentiment quads. Compared to existing benchmarks, E-ABSA20K contains substantially longer and more aspect-dense reviews, averaging 63.9 words and 6.0 quads per review. We further propose a two-stage propose-and-verify framework for review-level quadruple extraction (target, aspect, opinion, sentiment). The first stage generates high-recall candidates under strict schema constraints, while the second stage conducts explicit grounding, scope, and modality verification, followed by review-level consolidation to mitigate hallucinations and scope leakage in long reviews. Experiments across multiple Qwen3 model sizes demonstrate that our approach consistently outperforms single-stage prompting (with and without chain-of-thought) as well as competitive ABSA extraction baselines, improving quad-level micro-F1 and robustness on discourse-hard cases such as comparisons and conditionals.

ACL 2026

If Only My CGM Could Speak: A Privacy-Preserving Agent for Question Answering over Continuous Glucose Data

Yanjun Cui, Ali Emami, Temiloluwa Prioleau, Nikhil Singh

Continuous glucose monitors (CGMs) used in diabetes care collect rich personal health data that could improve day-to-day self-management. However, current patient platforms only offer static summaries which do not support inquisitive user queries. Large language models (LLMs) could enable free-form inquiries about continuous glucose data, but deploying them over sensitive health records raises privacy and accuracy concerns. In this paper, we present CGM-Agent, a privacy-preserving framework for question answering over personal glucose data. In our design, the LLM serves purely as a reasoning engine that selects analytical functions. All computation occurs locally, and personal health data never leaves the user’s device. For evaluation, we construct a benchmark of 4,180 questions combining parameterized question templates with real user queries and ground truth derived from deterministic program execution. Evaluating 6 leading LLMs, we find that top models achieve 94% value accuracy on synthetic queries and 88% on ambiguous real-world queries. Errors stem primarily from intent and temporal ambiguity rather than computational failures. Additionally, lightweight models achieve competitive performance in our agent design, suggesting opportunities for low-cost deployment. We release our code and benchmark to support future work on trustworthy health agents.

ACL 2026

Not All Modalities at Once: Dynamic Dropout and Bidirectional Fusion for Robust Multi-modal Knowledge Graph Completion

Jiashun Peng, Fu Zhang, Hongzhi Chen, Jingwei Cheng, Yingsong Ning, Xiaoke Wang

Multi-modal Knowledge Graph Completion (MKGC) aims to infer missing links in multimodal knowledge graphs by leveraging structured triples together with auxiliary modalities such as text and images. Existing MKGC methods typically train with all modalities available, implicitly assuming consistent complementarity; however, this practice often induces modality dependence and modality competition under heterogeneous noise, which can hinder robust multi-modal fusion and limit overall performance.To address these issues, we propose MDBGF, a Modality Dropout and Bidirectional Gated Fusion framework for MKGC. MDBGF introduces a dynamic, probability-based modality dropout schedule. When the dropout is activated, MDBGF drops either the textual or visual modality during training while always preserving the structural information, encouraging the model to reduce over-reliance on any single auxiliary modality and to learn complementary cues under missing-modality conditions. When the dropout is not activated (i.e., all modalities are present), we further design a bidirectional gated fusion mechanism that enables mutual modulation between textual and visual modalities, enhancing cross-modal interaction and flexible fusion. In addition, we propose an adaptive proportional hybrid negative sampling strategy to strengthen MDBGF’s discriminative ability on hard negatives. Experiments on three benchmarks show that MDBGF consistently outperforms existing baselines and achieves new state-of-the-art results. Our code is available at https://anonymous.4open.science/r/MDBGF-AHNS.

ACL 2026

Multi-Docker-Eval: A ‘Shovel of the Gold Rush’ Benchmark on Automatic Environment Building for Software Engineering

Kelin Fu, Tianyu Liu, Zeyu Shang, YINGWEI MA, Jiaheng Liu, Jian Yang, Kaigui Bian

Automated environment configuration is a critical bottleneck in scaling software engineering (SWE) automation. To provide a reliable evaluation standard for this task, we present Multi-Docker-Eval benchmark. It includes 40 real-world repositories spanning 9 programming languages and measures both success in achieving executable states and efficiency under realistic constraints. Our extensive evaluation of state-of-the-art LLMs and agent frameworks reveals key insights: (1) the overall success rate of current models is low (F2P at most 37.7%), with environment construction being the primary bottleneck; (2) model size and reasoning length are not decisive factors, and open-source models like DeepSeek-V3.1 and Kimi-K2 are competitive in both efficiency and effectiveness; (3) agent framework and programming language also have significantly influence on success rate. These findings provide actionable guidelines for building scalable, fully automated SWE pipelines.

ACL 2026

Dunhuang-Bench: How Well Do MLLMs Understand Cultural Heritage?

Junyi Yuan, Jian Zhang, Tianxiu Yu, Yanlin Zhou, Xiaobo Jin, Qiufeng Wang, Fangyu Wu

Dunhuang art, a cornerstone of global heritage, demands fine-grained visual perception anchored by specialized cultural knowledge. Given the strong performance of multimodal large language models (MLLMs) on generic multimodal benchmarks, to what extent can they understand artifacts from Dunhuang art that are grounded in cultural context? To this end, we construct Dunhuang-Bench, a large-scale benchmark comprising 486 images and 22,970 QA pairs. It incorporates diverse task formats to evaluate MLLMs’ cultural understanding: Question Answering with Text Description, Multi-turn Dialogue, and Question Answering with Choices. Guided by Panofsky’s theory of iconology, we design two tasks including visual perception and knowledge reasoning for the evaluation of content understanding. In addition, we follow the theory of formal analytic tradition to design another task of artistic appreciation in our Dunhuang-Bench. Extensive evaluations of 20 mainstream MLLMs on Dunhuang-Bench reveal a consistent performance drop from perception and appreciation to reasoning. Moreover, CoT and few-shot prompting show marginal or negative impact, highlighting the limits of prompting-based improvements. Dunhuang-Bench thus provides a challenging benchmark for advancing multimodal cultural understanding. Data and code will be publicly available.

ACL 2026

Can AI Revise Research Papers with Human Review Feedback? An Empirical Study and Benchmark

Zihan Luo, Hong Huang, Jianxun Lian, Yu Chang, Xing Xie, Hai Jin

The rise of Human-AI collaboration can effectively speed up the research process for experts and allow anyone with critical thinking skills to conduct innovative work. A key part of this collaboration is the AI’s ability to improve a paper with human feedback—updating both the text and experiments to meet high standards. To evaluate this skill, we introduce ReviseBench, an extensible benchmark built on real academic data that can be easily scaled via agent-driven automated data collection. It tests the skills of Large Language Models (LLMs) on paper interpretation, experimental implementation, and paper formulation, using authors’ camera-ready versions as natural human baselines. To facilitate a fine-grained assessment, we further propose ReviseArena, a platform supporting pair-wise comparisons between different AI-revised papers. Our initial evaluation results on ReviseBench reveal that even state-of-the-art foundation LLMs struggle significantly in this domain, achieving a win rate of less than 10% against human experts, and facing issues like incremental revision, unprofessional revision, and potential data fabrication. Our code and data are released publicly at: https://github.com/CGCL-codes/ReviseBench.

ACL 2026

Plug-and-Play Data Module for Code RL: Adaptive Ambiguity Replay

Jianqing Zhang, Wei Xia, Zhezheng Hao, Hong Wang, Hande Dong, Qiang Lin, Yang Liu, Jian Cao, Qiang Yang

Reinforcement learning (RL) is effective for improving code generation but suffers from data scarcity. While experience replay mitigates this, existing approaches rely on static, in-epoch metrics that overlook training dynamics, often introducing low-utility or outdated data. Analyzing RL dynamics via dataset cartography, we observe that “ambiguous” samples, which are vital for model generalization, rapidly migrate to “easy-to-learn” regions, diminishing their training value. To address this, we propose Adaptive Ambiguity Replay (A2R) for RL, a plug-and-play module that prioritizes cross-epoch ambiguous samples. To neutralize the noise from stale experiences, A2R incorporates an adaptive importance mechanism based on policy divergence to weigh replayed rollouts. Extensive experiments on nine LLMs (3B–14B) demonstrate that A2R outperforms state-of-the-art baselines on real-world code editing tasks across both unseen and learned domains. Our results highlight cross-epoch ambiguity as a key factor for effective replay in RL. Code: https://github.com/TsingZ0/verl-A2R

ACL 2026

GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts

Wenhao Zeng, Xuteng Zhang, Yuling Shi, Chao Hu, Yuting Chen, Beijun Shen, Xiaodong Gu

Large Reasoning Models (LRMs) achieve remarkable performance by explicitly generating multi-step chains of thought, but this capability incurs substantial inference latency and computational cost. Collaborative inference offers a promising solution by selectively allocating work between lightweight and large models, yet a fundamental challenge remains: determining when a reasoning step requires the capacity of a large model or the efficiency of a small model. Existing routing strategies either rely on local token probabilities or post-hoc verification, introducing significant inference overhead. In this work, we propose a novel perspective on step-wise collaboration: the difficulty of a reasoning step can be inferred from its very first token. Inspired by the “Aha Moment” phenomenon in LRMs, we show that the entropy of the initial token serves as a strong predictor of step difficulty. Building on this insight, we introduce GlimpRouter, a training-free step-wise collaboration framework. GlimpRouter employs a lightweight model to generate only the first token of each reasoning step and routes the step to a larger model only when the initial token entropy exceeds a threshold. Experiments on multiple benchmarks demonstrate that our approach significantly reduces inference latency while preserving accuracy. For instance, GlimpRouter attains a substantial 10.7% improvement in accuracy while reducing inference latency by 25.9% compared to a standalone large model on AIME25. These results suggest a simple yet effective mechanism for reasoning: allocating computation based on a glimpse of thought rather than full-step evaluation.

ACL 2026

Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation

Jiaang Li, Zhendong Mao, Quan Wang, Yuning Wan, Yongdong Zhang

Retrieval-Augmented Generation (RAG) enhances the factuality of Large Language Models (LLMs) by incorporating retrieved documents and/or generated context. However, LLMs often exhibit a stylistic bias when presented with mixed contexts, favoring fluent but hallucinated generated content over factually grounded yet disorganized retrieved evidence. This phenomenon reveals that the utility of retrieved information is bottlenecked by its presentation. To bridge this gap, we propose QREAM, a style-controlled rewriter that aligns retrieved documents with a question-oriented style while preserving facts, better for LLM readers to utilize. Our framework consists of two stages: (1) QREAM-ICL, which uses stylistic seeds to guide iterative rewriting exploration; and (2) QREAM-FT, a lightweight student model distilled from denoised ICL outputs. QREAM-FT employs dual-criteria rejection sampling, filtering based on answer correctness and factual consistency to ensure high-quality supervision. QREAM seamlessly integrates into existing RAG pipelines as a plug-and-play module. Experiments demonstrate that QREAM consistently enhances advanced RAG pipelines, yielding up to 8% relative improvement with negligible latency overhead, effectively balancing question relevance with factual grounding.

ACL 2026

FARSS: Fisher-Optimized Adaptive Low-Rank and Singular-Vector Selection for Knowledge-Preserving Fine-Tuning

Renxing Chen, Ziwei Xiang, Peisong Wang, Hongjian Fang, Meng Li, Fanhu Zeng, Yanan Zhu, Peipei Yang, Xu-Yao Zhang, Jian Cheng

Parameter-efficient fine-tuning (PEFT) has become a prevalent approach for adapting large language models (LLMs). However, low-rank adaptation methods face an inherent trade-off: improving target task performance can compromise pre-trained world knowledge, while aggressively constraining updates to preserve world knowledge may hinder improvements in the target task. Furthermore, most current methods fail to account for layer-wise differences in adaptation sensitivity, resulting in suboptimal preservation of world knowledge and task adaptation. To address these challenge, we propose Fisher-Optimized Adaptive Low Rank and Singular-VectorSelection (FARSS), an effective framework for knowledge-preserving fine-tuning. This framework introduces two key innovations. First, we propose a Fisher-guided adaptive rank allocation strategy, which assigns smaller ranks to shallow layers that are critical for preserving world knowledge, and larger ranks to deep layers that are essential for task adaptation. Second, we introduce a task-aware initialization method that integrates singular value information with layer-specific second-order statistics estimated from activation and gradient covariances, enabling efficient and task-sensitive low-rank updates. We evaluated several models across various tasks, and the experimental results show that our approach outperforms existing PEFT methods, including LoRA, Corda, and KaSA, achieving a balance between preserving world knowledge and enhancing target task performance. The code is available at https://github.com/chenyehuang/FARSS.

ACL 2026

Lost in Diffusion: Uncovering Hallucination Patterns and Failure Modes in Diffusion Large Language Models

Zhengnan Guo, Fei Tan

While Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive paradigm comparable to auto-regressive (AR) models, their faithfulness, specifically regarding hallucination, remains largely underexplored. To bridge this gap, we present the first controlled comparative study to evaluate hallucination patterns in dLLMs. Our results demonstrate that current dLLMs exhibit a higher propensity for hallucination than AR counterparts controlled for architecture, scale, and pre-training weights. Furthermore, an analysis of inference-time compute reveals divergent dynamics: while quasi-autoregressive generation suffers from early saturation, non-sequential decoding unlocks potential for continuous refinement. Finally, we identify distinct failure modes unique to the diffusion process, including premature termination, incomplete denoising, and context intrusion. Our findings underscore that although dLLMs have narrowed the performance gap on general tasks, their distinct hallucination mechanisms pose a critical challenge to model reliability.

ACL 2026

MEIC-DT: Memory-Efficient Incremental Clustering for Long-Text Coreference Resolution with Dual-Threshold Constraints

Kangyang Luo, Shuzheng Si, Yuzhuo Bai, Cheng Gao, Zhitong Wang, Cheng Huang, Yingli Shen, Yufeng Han, Wenhao Li, Cunliang Kong, Maosong Sun

In the era of large language models (LLMs), supervised neural methods remain the state-of-the-art (SOTA) for Coreference Resolution. Yet, their full potential is underexplored, particularly in incremental clustering, which faces the critical challenge of balancing efficiency with performance for long texts. To address the limitation, we propose MEIC-DT, a novel dual-threshold, memory-efficient incremental clustering approach based on a lightweight Transformer. MEIC-DT features a dual-threshold constraint mechanism designed to precisely control the Transformer’s input scale within a predefined memory budget. This mechanism incorporates two key components: a Statistics-Aware Eviction Strategy (SAES) and an Internal Regularization Policy (IRP). The SAES utilizes distinct statistical profiles from the training and inference phases for intelligent cache management. The IRP strategically condenses clusters by selecting the most representative mentions, thereby preserving semantic integrity. Extensive experiments on common benchmarks demonstrate that MEIC-DT achieves highly competitive coreference performance under stringent memory constraints.

ACL 2026

Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax

Zeli Su, Ziyin Zhang, Zhou Liu, Xuexian Song, Zhankai Xu, Longfei Zheng, Xiaolu Zhang, Rong Fu, Guixian Xu, Wentao Zhang

Extending large language models (LLMs) to low-resource languages often incurs an “align- ment tax”: improvements in the target lan- guage come at the cost of catastrophic forget- ting in general capabilities. We argue that this trade-off arises from the rigidity of supervised fine-tuning (SFT), which enforces token-level surface imitation on narrow and biased data distributions. To address this limitation, we propose a semantic-space alignment paradigm powered by Group Relative Policy Optimiza- tion (GRPO), where the model is optimized us- ing embedding-level semantic rewards rather than likelihood maximization. This objective encourages meaning preservation through flex- ible realizations, enabling controlled updates that reduce destructive interference with pre- trained knowledge. We evaluate our approach on Tibetan–Chinese machine translation and Ti- betan headline generation. Experiments show that our method acquires low-resource capa- bilities while markedly mitigating alignment tax, preserving general competence more effec- tively than SFT. Despite producing less rigid surface overlap, semantic RL yields higher se- mantic quality and preference in open-ended generation, and few-shot transfer results indi- cate that it learns more transferable and ro- bust representations under limited supervision. Overall, our study demonstrates that reinforce- ment learning with semantic rewards provides a safer and more reliable pathway for inclusive low-resource language expansion.

ACL 2026

Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization

Huimin Xu, Shuai Zhao, Xiaobao Wu, Anh Tuan Luu

Reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning ability of large language models. However, widely used RLVR algorithms, such as GRPO, often suffer from entropy collapse, leading to premature determinism and unstable optimization. Existing remedies, including entropy regularization and ratio-based clipping heuristics, either control entropy in a coarse-grained manner or rely on approximate on-policy training. In this paper, we revisit entropy collapse from a token-level entropy flow perspective. Our analysis reveals that entropy-decreasing tokens consistently outweigh entropy-increasing ones, resulting in a severely imbalanced entropy flow. This perspective provides a unified explanation of entropy collapse in existing RLVR algorithms and highlights the importance of balancing entropy dynamics. Motivated by this analysis, we propose On-Policy Entropy Flow Optimization (OPEFO), an adaptive entropy flow balancing mechanism that rescales entropy-increasing and entropy-decreasing updates according to their contributions to entropy change, while remaining strict on-policy. Experiments on six mathematical reasoning benchmarks demonstrate that OPEFO improves training stability and final performance. We will release the code and models upon publication.

ACL 2026

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models

Xiangxi Zheng, Linjie Li, Zhengyuan Yang, Ping Yu, Alex Jinpeng Wang, Rui Yan, Yuan Yao, Lijuan Wang

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in visual-text processing. However, existing static image-text benchmarks are insufficient for evaluating their dynamic perception and interactive reasoning abilities. We introduce Vision-centric Multiple Abilities Game Evaluation (V-MAGE), a novel game-based evaluation framework designed to systematically assess MLLMs’ visual reasoning in interactive, continuous-space environments. V-MAGE features five distinct video games comprising over 30 carefully constructed evaluation scenarios. These scenarios are set in free-form, visually complex environments that require models to interpret dynamic game states and make decisions based solely on visual input, thereby closely reflecting the conditions encountered by human players. To ensure robust and interpretable comparisons across models, V-MAGE employs a dynamic ELO-based ranking system that accounts for varying difficulty levels and task diversity. Benchmarking state-of-the-art MLLMs against human baselines reveals that while leading models approach human-level performance in simple tasks, their performance drops significantly in complex scenarios requiring advanced reasoning and task orchestration. This persistent performance gap highlights fundamental limitations in current MLLMs’ ability to perform vision-grounded, interactive frame-by-frame control in simulated continuous-time environments. Through extensive analyses, we demonstrate the utility of V-MAGE in uncovering these limitations and providing actionable insights for improving the visual and reasoning capabilities of MLLMs in dynamic, interactive settings. Code is publicly available at https://github.com/CSU-JPG/V-MAGE.

ACL 2026

When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning

Ruotao Xu, Yixin Ji, Yu Luo, Jinpeng Li, Dong Li, Peifeng Li, Juntao Li, Min Zhang

Large reasoning models (LRMs) have achieved strong performance enhancement through scaling test time computation, but due to the inherent limitations of the underlying language models, they still have shortcomings in tasks that require precise computation and extensive knowledge reserves. Tool-Integrated Reasoning (TIR) has emerged as a promising paradigm that incorporates tool call and execution within the reasoning trajectory. Although recent works have released some powerful open-source TIR models, our analysis reveals that these models still suffer from critical deficiencies. We find that when the reasoning of the model conflicts with the tool results, the model tends to believe in its own reasoning. And there are cases where the tool results are correct but are ignored by the model, resulting in incorrect answers, which we define as “Tool Ignored”. This indicates that the model does not know when to trust or ignore the tool. To overcome these limitations, We introduce Adaptive Tool Trust Calibration (ATTC), a novel framework that guides the model to adaptively choose to trust or ignore the tool results based on the confidence score of generated code blocks. The experimental results from various open-source TIR models of different sizes and across multiple datasets demonstrate that ATTC effectively reduces the “Tool Ignored” issue, resulting in a performance increase of 4.1% to 7.5%.

ACL 2026

What’s Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning

Songze Li, Xiaoke Guo, Tianqi Liu, Biao Yi, Zhaoyan Gong, Zhiqiang Liu, Huajun Chen, Wen Zhang

Existing Graphical User Interface (GUI) reasoning tasks remain challenging, particularly in UI understanding. Current methods typically rely on direct screen-based decision-making, which lacks interpretability and overlooks a comprehensive understanding of UI elements, ultimately leading to task failure. To enhance the understanding and interaction with UIs, we propose an innovative GUI reasoning paradigm called UI-in-the-Loop (UILoop). Our approach treats the GUI reasoning task as a cyclic Screen-UI elements-Action process. By enabling Multimodal Large Language Models (MLLMs) to explicitly learn the localization, semantic functions, and practical usage of key UI elements, UILoop achieves precise element discovery and performs interpretable reasoning. Furthermore, we introduce a more challenging UI Comprehension task centered on UI elements with three evaluation metrics. Correspondingly, we contribute a benchmark of 26K samples (UI Comprehension-Bench) to comprehensively evaluate existing methods’ mastery of UI elements. Extensive experiments demonstrate that UILoop achieves state-of-the-art UI understanding performance while yielding superior results in GUI reasoning tasks.

ACL 2026

GAPO: Robust Advantage Estimation for Real-World Code LLMs

Jianqing Zhang, Zhezheng Hao, Wei Xia, Hande Dong, Hong Wang, Chenxing Wei, Yuyan Zhou, Yubin Qi, Qiang Lin, Jian Cao

Reinforcement learning (RL) is widely used for post-training large language models (LLMs) in code editing, where group-relative methods, such as GRPO, are popular due to their critic-free and normalized advantage estimation. However, in real-world code-editing scenarios, reward distributions are often skewed with unpredictable noise, leading to distorted advantage computation and increased rollout outliers. To address this issue, we propose Group Adaptive Policy Optimization (GAPO), which adaptively finds an interval with the highest SNR (Signal to Noise Ratio) per prompt and uses the median of that interval as an adaptive Q to replace the group mean in advantage calculation to reduce noise further. This adaptive Q robustly handles rollout noise while remaining plug-and-play and efficient. We evaluate GAPO on nine instruction-tuned LLMs (3B–14B) using a collected large dataset of 51,844 real-world, history-aware code-editing tasks spanning 10 programming languages. GAPO yields up to 4.35 in-domain (ID) and 5.30 out-of-domain (OOD) exact-match improvements over GRPO and its variant DAPO, while achieving lower clipping ratios and higher GPU throughput. Code: https://github.com/TsingZ0/verl-GAPO

ACL 2026

Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints

Songping Peng, Zhiheng Zhang, Daojian Zeng, Lincheng Jiang, Xieping Gao

Safety alignment in Large Language Models (LLMs) remains highly fragile during fine-tuning, where even benign adaptation can degrade pre-trained refusal behaviors and enable harmful responses. Existing defenses typically constrain either weights or activations in isolation, without considering their coupled effects on safety. In this paper, we first theoretically demonstrate that constraining either weights or activations alone is insufficient for safety preservation. To robustly preserve safety alignment, we propose Coupled Weight and Activation Constraints (CWAC), a novel approach that simultaneously enforces a precomputed safety subspace on weight updates and applies targeted regularization to safety-critical features identified by sparse autoencoders. Extensive experiments across four widely used LLMs and diverse downstream tasks show that CWAC consistently achieves the lowest harmful scores with minimal impact on fine-tuning accuracy, substantially outperforming strong baselines even under high harmful data ratios.

ACL 2026

EAIR: Entity-aware Inference-Time Knowledge Routing for Multi-Hop Knowledge Editing

JunGyu Lee, Kunhui Lee, Gyun Lee, Seung-Hoon Na

Existing in-context editing (ICE) methods for multi-hop knowledge editing commonly suffer from paraphrase sensitivity, which refers to the phenomenon where these methods are not sufficiently robust to paraphrased multi-hop questions. To improve retrieval accuracy and knowledge routing to address paraphrase sensitivity, this paper proposes a novel entity-aware inference-time knowledge routing method, referred to as EAIR, which consists of four major steps: 1) Entity-referential query decomposition, which decomposes the original question into multiple entity-referential sub-question instructions; 2) Entity-aware retrieval, which leverages the previously reference-resolved topic entity in the retrieval step; 3) Evidence-conditioned contrastive decoding, which discourages the model from relying on its parametric knowledge and steers the model toward following retrieved edits; 4) Reflection-based knowledge routing, which additionally filters decoding results using refusal-style reflection to mitigate the risk introduced by contrastive decoding. Experimental results across the MQuAKE benchmark family and model scales show that EAIR achieves the highest strict case accuracy in 11 of 12 settings, substantially reducing paraphrase sensitivity.

Keep browsing

More papers from top AI conferences

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