---
title: "ACL 2026 — all accepted papers, page 26 — the most cited first"
description: "All 2,650 papers of ACL 2026 · page 26 of 27, the most cited first; those with our summary link to it."
canonical: "https://research.elamur.ai/free/en/venues/acl/2026/papers/page/26/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/acl/2026/papers/page/26/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [ACL](https://md.research.elamur.ai/free/en/venues/acl/) / [2026](https://md.research.elamur.ai/free/en/venues/acl/2026/) / [papers](https://md.research.elamur.ai/free/en/venues/acl/2026/papers/) / page 26

# ACL 2026: all accepted papers

2,650 papers · page 26 of 27 · the most cited first · [← ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)

[← prev](https://md.research.elamur.ai/free/en/venues/acl/2026/papers/page/25/) [1](https://md.research.elamur.ai/free/en/venues/acl/2026/papers/) … [20](https://md.research.elamur.ai/free/en/venues/acl/2026/papers/page/20/) … [25](https://md.research.elamur.ai/free/en/venues/acl/2026/papers/page/25/) **26** [27](https://md.research.elamur.ai/free/en/venues/acl/2026/papers/page/27/) [next →](https://md.research.elamur.ai/free/en/venues/acl/2026/papers/page/27/)

2501. **[Union-of-Experts: Neurons in Mixture-of-Experts are Secretly Routers ↗](https://aclanthology.org/2026.acl-long.1675/)**Songhao Wu, Ang Lv, Ruobing Xie et al. · Long Papers
2502. **[Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning ↗](https://aclanthology.org/2026.acl-long.548/)**Renjie Gu, Jiazhen Du, Yihua Zhang et al. · Long Papers
2503. **[Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning ↗](https://aclanthology.org/2026.acl-long.620/)**Jiacheng Hua, Yishu Yin, Yuhang Wu et al. · Long Papers
2504. **[Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text ↗](https://aclanthology.org/2026.acl-long.452/)**Zhihao Xu, Rumei Li, Jiahuan Li et al. · Long Papers
2505. **[Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering ↗](https://aclanthology.org/2026.acl-long.1138/)**Qiming Li, Xiaocheng Feng, Yixuan Ma et al. · Long Papers
2506. **[Unlocking the Potential of Diffusion Language Models through Template Infilling ↗](https://aclanthology.org/2026.acl-long.284/)**Junhoo Lee, Seungyeon Kim, Nojun Kwak · Long Papers
2507. **[Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses ↗](https://aclanthology.org/2026.acl-long.2101/)**Sugyeong Eo, Heuiseok Lim · Long Papers
2508. **[Unveiling the Unknown: Open-Set Entity Typing via Two-Stage Generation ↗](https://aclanthology.org/2026.acl-long.947/)**Hu Chen, Binhan Yang, Wei Shen · Long Papers
2509. **[UrbanGeoEval: A City-Scale Benchmark for Evaluating Large Language Models in Geospatial Reasoning ↗](https://aclanthology.org/2026.acl-long.1867/)**Mutian Bao, Qiuyi Qi, Tian Liang et al. · Long Papers
2510. **[User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios ↗](https://aclanthology.org/2026.acl-long.1645/)**Xiaoyuan Wu, Roshni Kaushik, Wenkai Li et al. · Long Papers
2511. **[Using Perspectival Words Is Harder Than Vocabulary Words for Humans –-and Even More So for Multimodal Language Models ↗](https://aclanthology.org/2026.acl-long.84/)**Dota Tianai Dong, Yifan Luo, Po-Ya Angela Wang et al. · Long Papers
2512. **[VALU: A Benchmark for Video Anomaly Temporal Localization and Understanding at Multiple Semantic Levels ↗](https://aclanthology.org/2026.acl-long.56/)**Yixiao He, Menghao Zhang, Haifeng Sun et al. · Long Papers
2513. **[VAPO: End-to-end Slide-Enhanced Speech Recognition with Omni-modal Large Language Models ↗](https://aclanthology.org/2026.acl-long.425/)**Rui Hu, Delai Qiu, Yining Wang et al. · Long Papers
2514. **[VC-Inspector: Advancing Reference-free Evaluation of Video Captions with Factual Analysis ↗](https://aclanthology.org/2026.acl-long.1552/)**Shubhashis Roy Dipta, Tz-Ying Wu, Subarna Tripathi · Long Papers
2515. **[VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision ↗](https://aclanthology.org/2026.acl-long.1298/)**Xuan Gong, Senmiao Wang, Hanbo Huang et al. · Long Papers
2516. **[VEG: Verbal $\epsilon$-greedy for Semantic Exploration in Multi-Turn RL Agents ↗](https://aclanthology.org/2026.acl-industry.82/)**Yongchang Hao, Jie Hao, Yongsheng Mei et al. · Industry Track
2517. **[VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation ↗](https://aclanthology.org/2026.acl-long.407/)**Yixia Li, Yaqing Shi, Zhiwen Ruan et al. · Long Papers
2518. **[VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models ↗](https://aclanthology.org/2026.acl-long.712/)**Chahat Raj, Bowen Wei, Aylin Caliskan et al. · Long Papers
2519. **[VISTA: Verification In Sequential Turn-based Assessment ↗](https://aclanthology.org/2026.acl-long.1890/)**Ashley Lewis, Andrew Perrault, Eric Fosler-Lussier et al. · Long Papers
2520. **[VL-Calibration: Decoupled Confidence Calibration for Large Vision-Language Models Reasoning ↗](https://aclanthology.org/2026.acl-long.2074/)**Wenyi Xiao, Xinchi XU, Leilei Gan · Long Papers
2521. **[VLN-MME: Diagnosing MLLMs as Language-guided Visual Navigation Agents ↗](https://aclanthology.org/2026.acl-long.1300/)**Xunyi Zhao, Gengze Zhou, Qi Wu · Long Papers
2522. **[VLN-NF: Feasibility-Aware Vision-and-Language Navigation with False-Premise Instructions ↗](https://aclanthology.org/2026.acl-long.1152/)**Hung-Ting Su, Ting-Jun Wang, Jia-Fong Yeh et al. · Long Papers
2523. **[VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs ↗](https://aclanthology.org/2026.acl-long.784/)**Avinash Amballa, Yashas Malur Saidutta, Chi-Heng Lin et al. · Long Papers
2524. **[VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training ↗](https://aclanthology.org/2026.acl-long.1103/)**Dingwei Zhu, Shihan Dou, Zhiheng Xi et al. · Long Papers
2525. **[Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification ↗](https://aclanthology.org/2026.acl-long.498/)**Stefan Krsteski, Giuseppe Russo, Serina Chang et al. · Long Papers
2526. **[Validator-Guided Hard Negative Mining for Masked Language Modeling in Low-Resource Ancient Languages ↗](https://aclanthology.org/2026.acl-srw.69/)**Andrei Voinea · Student Research Workshop
2527. **[Value of Information: A Framework for Human–Agent Communication ↗](https://aclanthology.org/2026.acl-long.1987/)**Yijiang River Dong, Tiancheng Hu, Zheng Hui et al. · Long Papers
2528. **[VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization ↗](https://aclanthology.org/2026.acl-long.1454/)**Dingyu Yao, Chenxu Yang, Zhengyang Tong et al. · Long Papers
2529. **[Vector Calligrapher: Generating Scalable Vector Graphics via Structured Linguistic Supervision ↗](https://aclanthology.org/2026.acl-long.511/)**Bo Zhou, Xikang Chen, Yan Gong et al. · Long Papers
2530. **[Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning ↗](https://aclanthology.org/2026.acl-long.1712/)**Sangkwon Park, Donghun Kang, Jisoo Mok et al. · Long Papers
2531. **[Verifiable LLM-Generated Text Detection via Projected Semantic-Structural Distributions ↗](https://aclanthology.org/2026.acl-long.638/)**Ruochong Xiong, Qien Li, Wangwang Lian et al. · Long Papers
2532. **[Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing ↗](https://aclanthology.org/2026.acl-long.1440/)**Wenhao Yuan, Chenchen Lin, Jian Chen et al. · Long Papers
2533. **[VerilogLAVD: LLM-Aided Pattern Generation for Verilog CWE Detection ↗](https://aclanthology.org/2026.acl-long.1304/)**Xiang Long, Yingjie Xia, Li Kuang et al. · Long Papers
2534. **[ViLL-E: Video LLM Embeddings for Retrieval ↗](https://aclanthology.org/2026.acl-long.2003/)**Rohit Gupta, Jayakrishnan Unnikrishnan, Fan Fei et al. · Long Papers · 🏆 Outstanding Paper
2535. **[VideoCuRL: Video Curriculum Reinforcement Learning with Orthogonal Difficulty Decomposition ↗](https://aclanthology.org/2026.acl-long.953/)**Hongbo Jin, Kuanwei Lin, Wenhao Zhang et al. · Long Papers
2536. **[VideoPro: Adaptive Program Reasoning for Long Video Understanding ↗](https://aclanthology.org/2026.acl-long.341/)**Chenglin Li, Feng Han, Yikun Wang et al. · Long Papers
2537. **[VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG ↗](https://aclanthology.org/2026.acl-long.1656/)**Honghao Fu, Miao Xu, Yiwei Wang et al. · Long Papers
2538. **[VisAidMath: Benchmarking Visual-Aided Mathematical Reasoning ↗](https://aclanthology.org/2026.acl-long.1719/)**Jingkun Ma, Runzhe Zhan, Yang Li et al. · Long Papers
2539. **[VisPCO: Visual Token Pruning Configuration Optimization via Budget-Aware Pareto-Frontier Learning for Vision-Language Models ↗](https://aclanthology.org/2026.acl-long.420/)**Huawei Ji, Yuanhao Sun, Yuan Jin et al. · Long Papers
2540. **[VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval ↗](https://aclanthology.org/2026.acl-long.1192/)**Di Wu, Yixin Wan, Kai-Wei Chang · Long Papers
2541. **[VishBox v2: A Multi-Agent System for Adaptive Voice Phishing Simulation ↗](https://aclanthology.org/2026.acl-industry.145/)**Sungmi Park, Daon Choi, Yoonmo Yang et al. · Industry Track
2542. **[Vision-Language Introspection: Mitigating Overconfident Hallucinations in MLLMs via Interpretable Bi-Causal Steering ↗](https://aclanthology.org/2026.acl-long.1784/)**Shuliang Liu, Songbo Yang, Dong Fang et al. · Long Papers
2543. **[Vista-LLM: Decoupled Query-Guided Visual Token Pruning for Efficient Long-Video Large Language Models ↗](https://aclanthology.org/2026.acl-long.601/)**Zhenyu Li, Zuchao Li, Ping Wang et al. · Long Papers
2544. **[Visual Attention Reasoning via Hierarchical Search and Self-Verification ↗](https://aclanthology.org/2026.acl-long.406/)**Wei Cai, Jian Zhao, Yuchen Yuan et al. · Long Papers
2545. **[Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images ↗](https://aclanthology.org/2026.acl-long.490/)**Qishun Yang, Shu Yang, Lijie Hu et al. · Long Papers
2546. **[Visual and Memory–Augmented Soccer Commentary Generation ↗](https://aclanthology.org/2026.acl-long.485/)**Haoran Sun, Natthawut Kertkeidkachorn, Kiyoaki Shirai · Long Papers
2547. **[Visually-Guided Policy Optimization for Multimodal Reasoning ↗](https://aclanthology.org/2026.acl-long.301/)**Zengbin Wang, Feng Xiong, Liang Lin et al. · Long Papers
2548. **[Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination ↗](https://aclanthology.org/2026.acl-long.1782/)**Yangneng Chen, Junlin Li, Weijun Yao et al. · Long Papers
2549. **[Vocabulary Shapes Cross-Lingual Variation of Word-Order Learnability in Language Models ↗](https://aclanthology.org/2026.acl-long.1510/)**Jonas Mayer Martins, Jaap Jumelet, Viola Priesemann et al. · Long Papers
2550. **[VoxMind: An End-to-End Agentic Spoken Dialogue System ↗](https://aclanthology.org/2026.acl-long.459/)**Tianle Liang, Yifu Chen, Shengpeng Ji et al. · Long Papers
2551. **[WIGVO: Real-Time Bidirectional Speech Translation over Legacy PSTN Calls via Dual-Session Echo Gating ↗](https://aclanthology.org/2026.acl-demo.33/)**Hyeong-seob Kim, Sang-Woo Son, Hyun-woo Cho et al. · System Demonstrations
2552. **[WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement ↗](https://aclanthology.org/2026.acl-long.1456/)**Fangyuan Li, Pengfei Li, Shijie Wang et al. · Long Papers
2553. **[WSDPO: A Generative Word Sense Disambiguation Framework with Chain-of-Thought and Preference Optimization ↗](https://aclanthology.org/2026.acl-long.1610/)**Kunpeng Kang, Shuaimin Li, Kaiyuan Zhang et al. · Long Papers
2554. **[Wait! There's a Way Out: A Decision Mechanism for Forecasting Conversational Derailment ↗](https://aclanthology.org/2026.acl-long.1943/)**Laerdon Kim, Vivian Nguyen, Cristian Danescu-Niculescu-Mizil · Long Papers
2555. **[WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Models ↗](https://aclanthology.org/2026.acl-long.1124/)**Rui Wang, Ce Zhang, Jun-Yu Ma et al. · Long Papers
2556. **[WebClipper: Efficient Evolution of Web Agents with Graph-based Trajectory Pruning ↗](https://aclanthology.org/2026.acl-long.988/)**Junjie Wang, Zequn Xie, Dan Yang et al. · Long Papers
2557. **[WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics ↗](https://aclanthology.org/2026.acl-long.535/)**Chenxu Liu, Yingjie Fu, Wei Yang et al. · Long Papers
2558. **[WebSTAR: Scalable Data Synthesis for Computer Use Agents with Step-Level Filtering ↗](https://aclanthology.org/2026.acl-long.21/)**Yifei He, Pranit Chawla, Yaser Souri et al. · Long Papers
2559. **[WebSynthesis: World Model-Guided Monte Carlo Tree Search for Efficient WebAgent Trajectory Synthesis ↗](https://aclanthology.org/2026.acl-long.1157/)**Yifei Gao, Junhong Ye, Yifan Yang et al. · Long Papers
2560. **[WeightLoRA: Keep Only Necessary Adapters ↗](https://aclanthology.org/2026.acl-long.566/)**Andrey Veprikov, Vladimir Solodkin, Zyl Alexander et al. · Long Papers
2561. **[What About the Scene With the Hitler Reference? HAUNT: A Framework to Probe LLMs' Self-consistency in Closed Domains Via Adversarial Nudge ↗](https://aclanthology.org/2026.acl-long.2169/)**Arka Dutta, Sujan Dutta, Rijul Magu et al. · Long Papers
2562. **[What Deserves Memory: Adaptive Memory Distillation for LLM Agents ↗](https://aclanthology.org/2026.acl-long.1607/)**Wenquan Ma, Jiayan Nan, WenLong Wu · Long Papers
2563. **[What Do LLMs Learn First? Asymmetric Learning Dynamics of Input Complexity and Output Ambiguity in Preference Alignment ↗](https://aclanthology.org/2026.acl-long.789/)**Mengyang Li, Jingwen Wang, Pinlong Zhao · Long Papers
2564. **[What Do Prosody and Text Convey? Characterizing How Meaningful Information is Distributed Across Multiple Channels ↗](https://aclanthology.org/2026.acl-long.1085/)**Aditya Yadavalli, Tiago Pimentel, Tamar I Regev et al. · Long Papers
2565. **[What Does LLM Refinement Actually Improve? A Systematic Study on Document-Level Literary Translation ↗](https://aclanthology.org/2026.acl-long.268/)**Shaomu Tan, Dawei Zhu, Ke Tran et al. · Long Papers
2566. **[What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time ↗](https://aclanthology.org/2026.acl-long.1337/)**Dong Yan, Jian Liang, Yanbo Wang et al. · Long Papers
2567. **[What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations ↗](https://aclanthology.org/2026.acl-short.70/)**Yujie Luo, Zhuoyun Yu, Xuehai Wang et al. · Short Papers
2568. **[What Makes Good Instruction-Tuning Data? An In-Context Learning Perspective ↗](https://aclanthology.org/2026.acl-long.45/)**Guangzeng Han, Xiaolei Huang · Long Papers
2569. **[What Makes LLMs Effective Sequential Recommenders? A Study on Preference Intensity and Temporal Context ↗](https://aclanthology.org/2026.acl-long.656/)**Zhongyu Ouyang, Qianlong Wen, Chunhui Zhang et al. · Long Papers
2570. **[What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning ↗](https://aclanthology.org/2026.acl-long.1591/)**Yaning Jia, Chunhui Zhang, Xingjian Diao et al. · Long Papers
2571. **[What Makes an Ideal Quote? Recommending “Unexpected yet Rational” Quotations via Novelty ↗](https://aclanthology.org/2026.acl-long.362/)**Powei Chang, Jin Xiao, Guanglei Yue et al. · Long Papers
2572. **[What Moves the Pareto Frontier in Tool-Using Agents? A Compute-Aware Study of ReAct Variants ↗](https://aclanthology.org/2026.acl-srw.82/)**Rishi N. Simhadri · Student Research Workshop
2573. **[What Question Did You Answer? Refining Contact Center Evaluation Plans via Backward Questions ↗](https://aclanthology.org/2026.acl-industry.113/)**Prajwal Sood, Rushikesh Pawar, Digvijay Anil Ingle et al. · Industry Track
2574. **[What is a protest anyway? Codebook conceptualization is still a first-order concern in LLM-era classification ↗](https://aclanthology.org/2026.acl-long.92/)**Andrew Halterman, Katherine A. Keith · Long Papers
2575. **[What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews ↗](https://aclanthology.org/2026.acl-long.293/)**Fanxiao Li, Jiaying Wu, Tingchao Fu et al. · Long Papers
2576. **[When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors ↗](https://aclanthology.org/2026.acl-long.478/)**Chenghao Yang, Yuning Zhang, Zhoufutu Wen et al. · Long Papers
2577. **[When Background Matters: Breaking Medical Vision Language Models by Transferable Attack ↗](https://aclanthology.org/2026.acl-long.1768/)**Akash Ghosh, Subhadip Baidya, Sriparna Saha et al. · Long Papers
2578. **[When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure ↗](https://aclanthology.org/2026.acl-long.395/)**Boyu Xiao, Xiuqi Tian, Xuwen Song et al. · Long Papers
2579. **[When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action Models ↗](https://aclanthology.org/2026.acl-long.2066/)**Xuan Dong, Zhe Han, Tianhao Niu et al. · Long Papers
2580. **[When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval ↗](https://aclanthology.org/2026.acl-long.1455/)**Tongyao Zhu, Huang Chao Ming, Min-Yen Kan · Long Papers
2581. **[When Efficiency Becomes a Vulnerability: Computational Cost Attacks on WebAgents ↗](https://aclanthology.org/2026.acl-long.1775/)**Liang-Bo Ning, Yuchen Zhu, Heqing Huang et al. · Long Papers
2582. **[When Efficiency Meets Safety: A Benchmark Security Analysis of KV Cache Compression in Large Language Models ↗](https://aclanthology.org/2026.acl-long.1123/)**Xiaoxiao Ma, Kuofeng Gao, Zeyi Lu et al. · Long Papers
2583. **[When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation ↗](https://aclanthology.org/2026.acl-industry.60/)**Lin Sun, Wangdexian, Jingang Huang et al. · Industry Track
2584. **[When High Accuracy Hides Poor Calibration: Rethinking Confidence Evaluation in Transformer-Based Text Classification with Balanced Brier Score ↗](https://aclanthology.org/2026.acl-long.2128/)**Guilherme Fonseca, Gabriel Prenassi, Washington Cunha et al. · Long Papers
2585. **[When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning ↗](https://aclanthology.org/2026.acl-long.1080/)**Yang Xiang, Yixin Ji, Ruotao Xu et al. · Long Papers
2586. **[When KV Cache Reuse Fails in Multi-Agent Systems: Cross-Candidate Interaction is Crucial for LLM Judges ↗](https://aclanthology.org/2026.acl-long.327/)**Sichu Liang, Zhenglin Wang, Chujiajia et al. · Long Papers
2587. **[When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors ↗](https://aclanthology.org/2026.acl-long.762/)**Yuqing Yang, Qi Zhu, Zhen Han et al. · Long Papers
2588. **[When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platforms ↗](https://aclanthology.org/2026.acl-long.93/)**Chaewan Chun, Delvin Ce Zhang, Dongwon Lee · Long Papers
2589. **[When Models Hesitate: Answer Instability as a Label-Free Uncertainty Signal for LLMs ↗](https://aclanthology.org/2026.acl-srw.72/)**Jasper Meynard Arana, Kristine Ann M. Carandang, Ethan Robert Casin et al. · Student Research Workshop
2590. **[When More Words Say Less: Decoupling Length and Specificity in Image Description Evaluation ↗](https://aclanthology.org/2026.acl-short.34/)**Rhea Kapur, Robert D. Hawkins, Elisa Kreiss · Short Papers
2591. **[When Morphology Hides in Plain Sight: Breaking the Isolation in Vietnamese and Beyond ↗](https://aclanthology.org/2026.acl-long.472/)**Anh Trac Duc Dinh, Khang Hoang Nhat Vo, Tai Tien Ta et al. · Long Papers
2592. **[When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents ↗](https://aclanthology.org/2026.acl-long.1260/)**Jiahe Guo, Xiangran Guo, Yulin Hu et al. · Long Papers
2593. **[When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection ↗](https://aclanthology.org/2026.acl-long.1998/)**Lang Gao, Xuhui Li, Chenxi Wang et al. · Long Papers
2594. **[When Seeing Is not Enough: Revealing the Limits of Active Reasoning in MLLMs ↗](https://aclanthology.org/2026.acl-long.1264/)**Hongcheng Liu, Pingjie Wang, Yuhao Wang et al. · Long Papers
2595. **[When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models ↗](https://aclanthology.org/2026.acl-long.642/)**Francesco Ortu, Zhijing Jin, Diego Doimo et al. · Long Papers
2596. **[When TableQA Meets Noise: A Dual Denoising Framework for Complex Questions and Large-scale Tables ↗](https://aclanthology.org/2026.acl-long.1102/)**Shenghao Ye, Yu Guo, Dong Jin et al. · Long Papers
2597. **[When “Correct” Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents? ↗](https://aclanthology.org/2026.acl-long.707/)**Yibo Peng, James Song, Lei Li et al. · Long Papers
2598. **[When in Doubt, Consult: Expert Debate for Sexism Detection via Confidence-Based Routing ↗](https://aclanthology.org/2026.acl-long.1936/)**Anwar Alajmi, Gabriele Pergola · Long Papers
2599. **[Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models ↗](https://aclanthology.org/2026.acl-long.1933/)**Chenchen Yuan, Zheyu Zhang, Gjergji Kasneci · Long Papers
2600. **[Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation ↗](https://aclanthology.org/2026.acl-long.477/)**Dongding Lin, Jian Wang, Yongqi Li et al. · Long Papers

[← prev](https://md.research.elamur.ai/free/en/venues/acl/2026/papers/page/25/) [1](https://md.research.elamur.ai/free/en/venues/acl/2026/papers/) … [20](https://md.research.elamur.ai/free/en/venues/acl/2026/papers/page/20/) … [25](https://md.research.elamur.ai/free/en/venues/acl/2026/papers/page/25/) **26** [27](https://md.research.elamur.ai/free/en/venues/acl/2026/papers/page/27/) [next →](https://md.research.elamur.ai/free/en/venues/acl/2026/papers/page/27/)

- [← back to](https://md.research.elamur.ai/free/en/venues/acl/2026/) — ACL 2026