---
title: "Findings of the Association for Computational Linguistics 2026 —"
description: "All 2,517 papers of Findings of the Association for Computational Linguistics 2026 · page 16 of 26, the most cited first; those with our…"
canonical: "https://research.elamur.ai/free/en/venues/findings/2026/papers/page/16/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/findings/2026/papers/page/16/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [Findings of the Association for…](https://md.research.elamur.ai/free/en/venues/findings/) / [2026](https://md.research.elamur.ai/free/en/venues/findings/2026/) / [papers](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/) / page 16

# Findings of the Association for Computational Linguistics 2026: all accepted papers

2,517 papers · page 16 of 26 · the most cited first · [← Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)

[← prev](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/page/15/) [1](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/) … [10](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/page/10/) … [15](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/page/15/) **16** [17](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/page/17/) … [20](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/page/20/) … [26](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/page/26/) [next →](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/page/17/)

1501. **[Localized Cultural Knowledge is Conserved and Controllable in Large Language Models ↗](https://aclanthology.org/2026.findings-acl.2141/)**Veniamin Veselovsky, Berke Argın, Benedikt Stroebl et al.
1502. **[Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models ↗](https://aclanthology.org/2026.findings-acl.502/)**Hengyuan Zhang, Zhihao Zhang, Ercong Nie et al.
1503. **[LogToP: Logic Tree-of-Program with Table Instruction-tuned LLMs for Controlled Logical Table-to-Text Generation ↗](https://aclanthology.org/2026.findings-eacl.280/)**Yupian Lin, Guangya Yu, Cheng Yuan et al.
1504. **[Logical Structure as Knowledge: Enhancing LLM Reasoning via Structured Logical Knowledge Density Estimation ↗](https://aclanthology.org/2026.findings-acl.436/)**Zhen Bi, Zhenlin Hu, Xueshu Chen et al.
1505. **[Logit Arithmetic Elicits Long Reasoning Capabilities Without Training ↗](https://aclanthology.org/2026.findings-acl.1249/)**Yunxiang Zhang, Muhammad Khalifa, Lechen Zhang et al.
1506. **[LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation ↗](https://aclanthology.org/2026.findings-acl.1655/)**Tianyu Liu, Qitan Lv, Hao Li et al.
1507. **[Logits-Based Block Pruning with Affine Transformations for Large Language Models ↗](https://aclanthology.org/2026.findings-eacl.193/)**Zekun Hu, Yichu Xu, De-Chuan Zhan
1508. **[Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLMs ↗](https://aclanthology.org/2026.findings-acl.2131/)**Israfel Salazar, Desmond Elliott, Yova Kementchedjhieva
1509. **[LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding. ↗](https://aclanthology.org/2026.findings-acl.965/)**ZhaoYang Han, Qihan Lin, Hao Liang et al.
1510. **[LongMP-Bench: A Benchmark for Multimodal Persona Understanding in Long-Term Dialogues ↗](https://aclanthology.org/2026.findings-acl.1159/)**Zhuoqun Li, Zhaopei Huang, Wenxuan Wang et al.
1511. **[Look Twice before You Leap: A Rational Framework for Localized Adversarial Text Anonymization ↗](https://aclanthology.org/2026.findings-acl.274/)**Donghang Duan, Xu Zheng, Yuefeng He et al.
1512. **[Look and Think: Efficient Multimodal Reasoning via Modality-Decoupled Compression ↗](https://aclanthology.org/2026.findings-acl.1241/)**Xidi Cai, Junhao Zheng, Jingye Li et al.
1513. **[LoopCoder: Scaling Code Intelligence via Looped Language Models ↗](https://aclanthology.org/2026.findings-acl.796/)**Jian Yang, Wei Zhang, Shuyue Guo et al.
1514. **[Losses that Cook: Topological Optimal Transport for Structured Recipe Generation ↗](https://aclanthology.org/2026.findings-acl.1318/)**Mattia Ottoborgo, Daniele Rege Cambrin, Paolo Garza
1515. **[Lost in Decomposition: Analyzing and Mitigating the Limitations of Long Context Methods via Context Dependency ↗](https://aclanthology.org/2026.findings-acl.2097/)**Jiayuan Guo, Yueyang Su, Yuyao Ge et al.
1516. **[Lost in Diffusion: Uncovering Hallucination Patterns and Failure Modes in Diffusion Large Language Models ↗](https://aclanthology.org/2026.findings-acl.882/)**Zhengnan Guo, Fei Tan
1517. **[Lost in Stories: Consistency Bugs in Long Story Generation by LLMs ↗](https://aclanthology.org/2026.findings-acl.410/)**Junjie Li, Xinrui Guo, Yuhao Wu et al.
1518. **[Lost in Translation: Do LVLM Judges Generalize Across Languages? ↗](https://aclanthology.org/2026.findings-acl.1746/)**Md Tahmid Rahman Laskar, Mohammed Saidul Islam, Mir Tafseer Nayeem et al.
1519. **[Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language Models ↗](https://aclanthology.org/2026.findings-acl.1921/)**Hyunjong Ok, Jaeho Lee
1520. **[Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward ↗](https://aclanthology.org/2026.findings-acl.1209/)**Guanhua Huang, Tingqiang Xu, Mingze Wang et al.
1521. **[Lunar-Bench: Towards Evaluating Task-Oriented Reasoning of LLMs in Lunar Exploration Scenarios ↗](https://aclanthology.org/2026.findings-acl.83/)**Xin-Yu Xiao, Ye Tian, Erwei Yin et al.
1522. **[LycheeCluster: Efficient Long-Context Inference with Structure-Aware Chunking and Hierarchical KV Indexing ↗](https://aclanthology.org/2026.findings-acl.376/)**Dongfang Li, Zixuan Liu, Gang Lin et al.
1523. **[M-TRACE: Detecting and Mitigating Time-Anchor Drift via Step-wise Conflict Checking in Temporal Reasoning ↗](https://aclanthology.org/2026.findings-acl.1204/)**Danyu Huang, Jiayuan Jiang, Yao Zhang et al.
1524. **[M3TQA: Massively Multilingual Multitask Table Question Answering ↗](https://aclanthology.org/2026.findings-acl.1134/)**Daixin Shu, Jian Yang, Zhenhe Wu et al.
1525. **[MA$^2$P: A Meta-Cognitive Autonomous Intelligent Agents Framework for Complex Persuasion ↗](https://aclanthology.org/2026.findings-acl.1550/)**Dingyi Zhang, Ziqing Zhuang, Linhai Zhang et al.
1526. **[MAC-Reasoner: A Multi-Agent Collaborative Framework for Enhancing Logical Reasoning in Large Language Models ↗](https://aclanthology.org/2026.findings-acl.233/)**Yehua Lin, Liping Zheng, Yin Chen
1527. **[MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction ↗](https://aclanthology.org/2026.findings-eacl.159/)**Wei-Chieh Huang, Cornelia Caragea
1528. **[MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning ↗](https://aclanthology.org/2026.findings-acl.340/)**JunJian Wang, Lidan Zhao, Xi Sheryl Zhang
1529. **[MAKI: Multi-layer Aligned Knowledge Injection for Structure-aware Knowledge Graph Completion with Large Language Models ↗](https://aclanthology.org/2026.findings-acl.1423/)**Zhiwen Xie, Xin Wang, Guangyou Zhou et al.
1530. **[MAPLE: A Meta-learning Framework for Cross-Prompt Essay Scoring ↗](https://aclanthology.org/2026.findings-acl.997/)**Salam Albatarni, May Bashendy, Sohaila Eltanbouly et al.
1531. **[MAPLE: Multi-Aspect Panels of LLM Evaluators for Open-Ended Questions ↗](https://aclanthology.org/2026.findings-acl.1351/)**Michinori Jinji, Kyohei Atarashi, Koh Takeuchi et al.
1532. **[MAPS: A Multilingual Benchmark for Agent Performance and Security ↗](https://aclanthology.org/2026.findings-eacl.42/)**Omer Hofman, Jonathan Brokman, Oren Rachmil et al.
1533. **[MARCH: Evaluating the Intersection of Ambiguity Interpretation and Multi-hop Inference ↗](https://aclanthology.org/2026.findings-acl.1352/)**Jeonghyun Park, Ingeol Baek, Seunghyun Yoon et al.
1534. **[MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification ↗](https://aclanthology.org/2026.findings-acl.421/)**Jingwei Song, Xinyu Wang, Hanbin Wang et al.
1535. **[MASH: Evading Black-Box AI-Generated Text Detectors via Style Humanization ↗](https://aclanthology.org/2026.findings-acl.1487/)**Yongtong Gu, Songze Li, Xia Hu
1536. **[MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation ↗](https://aclanthology.org/2026.findings-acl.480/)**Xingchen Xiao, Heyan Huang, Runheng Liu et al.
1537. **[MASS: Deep Research for Social Sciences with Memory-Augmented Social Simulation ↗](https://aclanthology.org/2026.findings-acl.988/)**Yongrui Liu, Deyi Xiong
1538. **[MAST: A Multi-View Alignment Strategy for Optimal Transport-Based Contrastive Clustering of Short Text ↗](https://aclanthology.org/2026.findings-acl.660/)**Zijian Zheng, Yonghe Lu
1539. **[MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answering ↗](https://aclanthology.org/2026.findings-acl.1672/)**Sieun Hyeon, Jusang Oh, Sunghwan Steve Cho et al.
1540. **[MATCHA: Matching Text via Contrastive Semantic Alignment ↗](https://aclanthology.org/2026.findings-acl.1055/)**Siran Li, Ece Sena Etoglu, Carsten Eickhoff et al.
1541. **[MATH-IDN: A Multilingual Mathematical Problem Solving Dataset Featuring Local Languages in Indonesia ↗](https://aclanthology.org/2026.findings-eacl.231/)**Xiao Xiao, Iftitahu Ni'mah, Yuyun Wabula et al.
1542. **[MAXS: Meta-Adaptive Exploration with LLM Agents ↗](https://aclanthology.org/2026.findings-acl.670/)**Jian Zhang, Zhiyuan Wang, Zhangqi Wang et al.
1543. **[MCGA: A Multi-task Classical Chinese Literary Genre Audio Corpus ↗](https://aclanthology.org/2026.findings-acl.1543/)**Yexing Du, Kaiyuan Liu, Bihe Zhang et al.
1544. **[MCLE-Mol: Empowering LLM with Molecular Comprehension and Low-Cost Continual Evolution for Interpretable Property Prediction ↗](https://aclanthology.org/2026.findings-acl.262/)**Zhili Pu, Lantian Zhang, Hao Duan et al.
1545. **[MDC-Bench: A Multidisciplinary Causal Benchmark Based on Causal Structures for Evaluating Large Language Models ↗](https://aclanthology.org/2026.findings-acl.1409/)**Peng Wang, Yuxiong Yan, Xiao Ding et al.
1546. **[MDocRAG-RL: Empowering Multi-Modal Document RAG via Complex Visual Reasoning with Reinforcement Learning ↗](https://aclanthology.org/2026.findings-acl.420/)**Zhongyu Wang
1547. **[MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Dialogue Evaluators ↗](https://aclanthology.org/2026.findings-eacl.109/)**John Mendonça, Alon Lavie, Isabel Trancoso
1548. **[MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language Models ↗](https://aclanthology.org/2026.findings-acl.1183/)**Boqi Chen, Xudong Liu, Jiachuan Peng et al.
1549. **[MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment ↗](https://aclanthology.org/2026.findings-eacl.340/)**Omid Ghahroodi, Arshia Hemmat, Marzia Nouri et al.
1550. **[MEIC-DT: Memory-Efficient Incremental Clustering for Long-Text Coreference Resolution with Dual-Threshold Constraints ↗](https://aclanthology.org/2026.findings-acl.881/)**Kangyang Luo, Shuzheng Si, Yuzhuo Bai et al.
1551. **[MENTOR: Efficient Autoregressive Image Generation with Balanced Multimodal Control ↗](https://aclanthology.org/2026.findings-acl.1508/)**Haozhe Zhao, Zefan Cai, Shuzheng Si et al.
1552. **[MENTOR: Mitigating Identity Drift in Dynamic Role-Playing via Dual-Chain Structured Memory ↗](https://aclanthology.org/2026.findings-acl.1046/)**Zhu Zhuoning, Xingyu Gao, Hailong Shi
1553. **[MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models ↗](https://aclanthology.org/2026.findings-acl.1382/)**Suhyun Lee, Palakorn Achananuparp, Neemesh Yadav et al.
1554. **[MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models ↗](https://aclanthology.org/2026.findings-acl.673/)**Kailin Jiang, Ning Jiang, Yuntao Du et al.
1555. **[MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining ↗](https://aclanthology.org/2026.findings-acl.676/)**Phung Gia Huy, Hai An Vu, Minh-Phuc Truong et al.
1556. **[MIThinker: A Plug-and-Play Policy-Optimized Thinker For Motivational Interviewing Counseling ↗](https://aclanthology.org/2026.findings-acl.163/)**Yizhe Yang, Palakorn Achananuparp, Heyan Huang et al.
1557. **[MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning ↗](https://aclanthology.org/2026.findings-acl.1488/)**Jiahang Lin, Kai Hu, Binghai Wang et al.
1558. **[MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language Models ↗](https://aclanthology.org/2026.findings-acl.1447/)**Jinsong Shu, Chenyang Wu, Zhongle Xie et al.
1559. **[MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting ↗](https://aclanthology.org/2026.findings-acl.467/)**Kangda Wei, Ruihong Huang
1560. **[MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models ↗](https://aclanthology.org/2026.findings-eacl.287/)**Siwei Wu, King Zhu, Yu Bai et al.
1561. **[MMTabReal: Real-World Benchmark for Multimodal Table Understanding ↗](https://aclanthology.org/2026.findings-acl.2047/)**Prasham Yatinkumar Titiya, Jainil Trivedi, Chitta Baral et al.
1562. **[MMUIE: Massive Multi-Domain Universal Information Extraction for Long Documents ↗](https://aclanthology.org/2026.findings-eacl.334/)**Shuyi Zhang, Zhenbin Chen, Shuting Li et al.
1563. **[MOSAIC: Masked Objective with Selective Adaptation for In-domain Contrastive Learning ↗](https://aclanthology.org/2026.findings-eacl.197/)**Vera Pavlova, Mohammed Makhlouf
1564. **[MPTc-Bench: Measuring Cross-market Generative Ability of Vision-Language Models via Movie Poster Transcreation ↗](https://aclanthology.org/2026.findings-acl.1889/)**Youyuan Lin, Yuan Li, Yahan Yu et al.
1565. **[MR-ALIGN: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models ↗](https://aclanthology.org/2026.findings-acl.204/)**Xinming Wang, Jian Xu, Bin Yu et al.
1566. **[MSCode: Advancing Human Motion-Language Understanding via Modality-Shared Codebook ↗](https://aclanthology.org/2026.findings-acl.1901/)**Haoyu Shi, Huaiwen Zhang
1567. **[MSIA: Adaptive Medical Multimodal Multi-turn Semantic Jailbreak ↗](https://aclanthology.org/2026.findings-acl.1096/)**Zhiheng Han, Yao Zhang, Jun Wang et al.
1568. **[MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generation ↗](https://aclanthology.org/2026.findings-acl.1203/)**Haoyuan Shi, Yunxin li, Nanhao Deng et al.
1569. **[MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation ↗](https://aclanthology.org/2026.findings-acl.1354/)**Jyotika Singh, Fang Tu, Miguel Ballesteros et al.
1570. **[MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues](https://md.research.elamur.ai/free/en/papers/pan-2026-mt-video-bench-holistic-video/)**Yaning Pan, Qianqian Xie, Guohui Zhang et al.*our summary*
1571. **[MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch ↗](https://aclanthology.org/2026.findings-acl.1236/)**Nikolay Banar, Ehsan Lotfi, Jens Van Nooten et al.
1572. **[MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues ↗](https://aclanthology.org/2026.findings-acl.96/)**Zheyuan Liu, Dongwhi Kim, Yixin Wan et al.
1573. **[MTO: A Multi-turn Conversational Text-to-OverpassQL Dataset for Enhanced OpenStreetMap Query Generation ↗](https://aclanthology.org/2026.findings-acl.36/)**Haodi Zhang, Xinrui Zhu, Mingze Kong et al.
1574. **[MTP-RL: Acceleration of Reinforcement Learning Rollouts with Policy-Aligned Multi-Token Prediction ↗](https://aclanthology.org/2026.findings-acl.1871/)**Ke Wang, Aohan Zeng, Zhengxiao Du et al.
1575. **[MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models ↗](https://aclanthology.org/2026.findings-acl.263/)**Zhang He, Wenqian Cui, Haoning Xu et al.
1576. **[MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversations ↗](https://aclanthology.org/2026.findings-acl.503/)**Sara Rosenthal, Yannis Katsis, Vraj Shah et al.
1577. **[MaRF: Leveraging Representation-Level Fusion of Formula Semantics for Mathematical Information Retrieval ↗](https://aclanthology.org/2026.findings-acl.1277/)**Suyuan Wang, Hongbo Zheng, Nickvash Kani
1578. **[Machine Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model Decisions ↗](https://aclanthology.org/2026.findings-acl.1547/)**Jiseon Kim, Jea Kwon, Luiz Felipe Vecchietti et al.
1579. **[Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation ↗](https://aclanthology.org/2026.findings-acl.1006/)**Zhiheng Li, Zongyang Ma, Yuntong Pan et al.
1580. **[Making Revisions Understandable: A Survey of Edit Intentions, Methods, and Applications ↗](https://aclanthology.org/2026.findings-acl.1747/)**Fangping Lan, Qi Zhang, Eduard Dragut
1581. **[MalURLBench: A Benchmark Evaluating Agents' Vulnerabilities When Processing Web URLs ↗](https://aclanthology.org/2026.findings-acl.716/)**Dezhang Kong, Zhuxi Wu, Shiqi Liu et al.
1582. **[ManCC: A Task-Anchored Benchmark for Manchu–Classical Chinese Cross-Lingual Modeling ↗](https://aclanthology.org/2026.findings-acl.1359/)**Meiqi Wang, Xiaoxin Sun, Dongjie Wang et al.
1583. **[Many-Shot Scaling of In-Context Learning with Self-Generated Demonstrations ↗](https://aclanthology.org/2026.findings-acl.2013/)**Zhengyao Gu, Henry Peng Zou, Yankai Chen et al.
1584. **[Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference ↗](https://aclanthology.org/2026.findings-acl.170/)**Jianuo Huang, Yaojie Zhang, Yicun Yang et al.
1585. **[MaskLoRA: Low-Rank Subspace–Induced Token Masking for Efficient and Faithful Language Models ↗](https://aclanthology.org/2026.findings-eacl.300/)**Rifat Rafiuddin
1586. **[MaskTab: Scalable Masked Tabular Pretraining with Scaling Laws and Distillation for Industrial Classification ↗](https://aclanthology.org/2026.findings-acl.2053/)**Bo Zheng, Yudong Chen, Zihua Xiong et al.
1587. **[Masked Text-to-Audio Flow-Matching and Reward Feedback Optimization ↗](https://aclanthology.org/2026.findings-acl.1891/)**Rongjie Huang, Dongchao Yang, Wenxiang Guo et al.
1588. **[Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in RAG ↗](https://aclanthology.org/2026.findings-acl.414/)**Agam Goyal, Koyel Mukherjee, Apoorv Saxena et al.
1589. **[MathMist: A Parallel Multilingual Benchmark Dataset for Mathematical Problem Solving and Reasoning ↗](https://aclanthology.org/2026.findings-eacl.131/)**Mahbub E Sobhani, Md. Faiyaz Abdullah Sayeedi, Tasnim Mohiuddin et al.
1590. **[MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning ↗](https://aclanthology.org/2026.findings-acl.118/)**Xuchen Li, Jing Chen, Xuzhao Li et al.
1591. **[Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction ↗](https://aclanthology.org/2026.findings-acl.1211/)**Shuoxin Wang, Chang Liu, Gowen Loo et al.
1592. **[MeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning ↗](https://aclanthology.org/2026.findings-acl.1386/)**Ruijun Huang, Zhiqiao Kang, Yuxuan Zhu et al.
1593. **[Measuring Large Language Models' Adversarial Behavior in Social Deduction Games ↗](https://aclanthology.org/2026.findings-acl.2043/)**Marissa Zhao Li, Esha Shivakumar, Peiran Wang et al.
1594. **[Measuring Watermarking under Jailbreaking: ASR Inflation and Goal-Compliance Mismatch ↗](https://aclanthology.org/2026.findings-acl.1797/)**Sungwoo Han, Sangjun Moon, Jingun Kwon et al.
1595. **[Measuring What Matters Beyond Text: Evaluating Multimodal Summaries by Quality, Alignment, and Diversity ↗](https://aclanthology.org/2026.findings-acl.1448/)**Abid Ali, Diego Molla, Usman Naseem
1596. **[Mechanistic Insights into Deferred Semantic Drift in LLMs ↗](https://aclanthology.org/2026.findings-acl.57/)**Jingjie Zeng, Huayang Li, Liang Yang et al.
1597. **[Mechanistic Interpretability of Large-Scale Counting in LLMs through a System-2 Strategy ↗](https://aclanthology.org/2026.findings-acl.2031/)**Hosein Hasani, Mohammadali Banayeeanzade, Ali Nafisi et al.
1598. **[Med-SRAF: A Multi-Agent Framework for Medical Reasoning via Semantic Routing and Agentic Fusion ↗](https://aclanthology.org/2026.findings-acl.1895/)**Xiao Li, Zhuo Chen, Jun Xia et al.
1599. **[MedCPI: A Construct–Personalize–Integrate Framework for KG-enhanced Clinical Prediction ↗](https://aclanthology.org/2026.findings-acl.1215/)**Hang Wang, Hang Dong, Lu Liu
1600. **[MedCoach: Enhancing Medical Reasoning in LLMs via Knowledge Graph-Augmented Chain-of-Thought Distillation ↗](https://aclanthology.org/2026.findings-acl.1683/)**Chuan Li, Ye Lyu, Chengyu Wang et al.

[← prev](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/page/15/) [1](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/) … [10](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/page/10/) … [15](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/page/15/) **16** [17](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/page/17/) … [20](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/page/20/) … [26](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/page/26/) [next →](https://md.research.elamur.ai/free/en/venues/findings/2026/papers/page/17/)

- [← back to](https://md.research.elamur.ai/free/en/venues/findings/2026/) — Findings of the Association for Computational Linguistics 2026