📅 Papers of 2025 — page 61,725 papers · papers of all years← prev 1 … 5 6 7 … 10 … 18 next →RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code GenerationConference on Empirical Methods in Natural Language Processing (EMNLP)Qingyao Li, Wei Xia, Xinyi Dai, et al.2025 · 16 citationsSimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative RefinementConference on Empirical Methods in Natural Language Processing (EMNLP)Chelsi Jain, Yiran Wu, Yifan Zeng, et al.2025 · 16 citationsSoft Prompting for Unlearning in Large Language ModelsConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Karuna Bhaila, Minh-Hao Van, Xintao Wu2025 · 16 citationsSparks of Science: Hypothesis Generation Using Structured Paper DataarXiv:2504.12976Charles O'Neill, Tirthankar Ghosal, Roberta R\uaileanu, et al.2025 · 16 citationsSweetieChat: A Strategy-Enhanced Role-playing Framework for Diverse Scenarios Handling Emotional Support AgentInternational Conference on Computational Linguistics (COLING)Jing Ye, Lu Xiang, Yaping Zhang, et al.2025 · 16 citationsTheory of Mind in Large Language Models: Assessment and EnhancementAnnual Meeting of the Association for Computational Linguistics (ACL)Ruirui Chen, Weifeng Jiang, Chengwei Qin, et al.2025 · 16 citationsTowards Data Contamination Detection for Modern Large Language Models: Limitations, Inconsistencies, and Oracle ChallengesInternational Conference on Computational Linguistics (COLING)Vinay Samuel, Yue Zhou, Henry Peng Zou2025 · 16 citationsTowards Reasoning Ability of Small Language ModelsarXiv:2502.11569Gaurav Srivastava, Shuxiang Cao, Xuan Wang2025 · 16 citationsTranslation in the Hands of Many: Centering Lay Users in Machine Translation InteractionsConference on Empirical Methods in Natural Language Processing (EMNLP)Beatrice Savoldi, Alan Ramponi, Matteo Negri, et al.2025 · 16 citationsTreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer ReviewConference on Empirical Methods in Natural Language Processing (EMNLP)Yuan Chang, Ziyue Li, Hengyuan Zhang, et al.2025 · 16 citationsVideo Compression Commander: Plug-and-Play Inference Acceleration for Video Large Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Xuyang Liu, Yiyu Wang, Junpeng Ma, et al.2025 · 16 citationsA Survey on Latent ReasoningarXiv:2507.06203Rui-Jie Zhu, Tianhao Peng, Tianhao Cheng, et al.2025 · 15 citationsAHaSIS: Shared Task on Sentiment Analysis for Arabic DialectsRecent Advances in Natural Language Processing (RANLP)Maram I. Alharbi, Salmane Chafik, Saad Ezzini, et al.2025 · 15 citationsAnalyzing and Adapting Large Language Models for Few-Shot Multilingual NLU: Are We There Yet?Transactions of the Association for Computational Linguistics (TACL)Evgeniia Razumovskaia, Ivan Vulić, Anna Korhonen2025 · 15 citationsArtificial Intelligence Bias on English Language Learners in Automatic ScoringLecture notes in computer scienceShuchen Guo, Yun Wang, Jichao Yu, et al.2025 · 15 citationsBasqBBQ: A QA Benchmark for Assessing Social Biases in LLMs for Basque, a Low-Resource LanguageInternational Conference on Computational Linguistics (COLING)Muitze Zulaika, Xabier Saralegi2025 · 15 citationsCalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-JudgesAnnual Meeting of the Association for Computational Linguistics (ACL)Haitao Li, Junjie Chen, Qingyao Ai, et al.2025 · 15 citationsChemAgent: Self-updating Library in Large Language Models Improves Chemical ReasoningarXiv:2501.06590Xiangru Tang, Tianyu Hu, Muyang Ye, et al.2025 · 15 citationsCURIE: Evaluating LLMs On Multitask Scientific Long Context Understanding and ReasoningarXiv:2503.13517Hao Cui, Zahra Shamsi, Gowoon Cheon, et al.2025 · 15 citationsDebate-to-Write: A Persona-Driven Multi-Agent Framework for Diverse Argument GenerationInternational Conference on Computational Linguistics (COLING)Zhe Hu, Hou Pong Chan, Jing Li, et al.2025 · 15 citationsFACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Hongzhan Lin, Yang Deng, Yuxuan Gu, et al.2025 · 15 citationsFalcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and PerformancearXiv:2507.22448Jingwei Zuo, Maksim Velikanov, Ilyas Chahed, et al.2025 · 15 citationsFR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative SamplingAnnual Meeting of the Association for Computational Linguistics (ACL)Weilin Zhao, Tengyu Pan, Xu Han, et al.2025 · 15 citationsHiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden StatesAnnual Meeting of the Association for Computational Linguistics (ACL)Yilei Jiang, Xinyan Gao, Tianshuo Peng, et al.2025 · 15 citationsImprove LLM-as-a-Judge Ability as a General AbilityConference on Empirical Methods in Natural Language Processing (EMNLP)Jiachen Yu, Shaoning Sun, Xiaohui Hu, et al.2025 · 15 citationsInteractive Evolution: A Neural-Symbolic Self-Training Framework For Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Fangzhi Xu, Qiushi Sun, Kanzhi Cheng, et al.2025 · 15 citationsJuStRank: Benchmarking LLM Judges for System RankingAnnual Meeting of the Association for Computational Linguistics (ACL)Ariel Gera, Odellia Boni, Yotam Perlitz, et al.2025 · 15 citationsL4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Hyesung Jeon, Yulhwa Kim, Jae-Joon Kim2025 · 15 citationsLanguage Models Encode the Value of Numbers LinearlyInternational Conference on Computational Linguistics (COLING)Fangwei Zhu, Damai Dai, Zhifang Sui2025 · 15 citationsLLäMmlein: Transparent, Compact and Competitive German-Only Language Models from ScratchAnnual Meeting of the Association for Computational Linguistics (ACL)Jan Pfister, Julia Wunderle, Andreas Hotho2025 · 15 citationsMAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement LearningAnnual Meeting of the Association for Computational Linguistics (ACL)Chanwoo Park, Seungju Han, Xingzhi Guo, et al.2025 · 15 citationsMeasuring Chain of Thought Faithfulness by Unlearning Reasoning StepsConference on Empirical Methods in Natural Language Processing (EMNLP)Martin Tutek, Fateme Hashemi Chaleshtori, Ana Marasovic, et al.2025 · 15 citationsMETAL: A Multi-Agent Framework for Chart Generation with Test-Time ScalingAnnual Meeting of the Association for Computational Linguistics (ACL)Bingxuan Li, Yiwei Wang, Jiuxiang Gu, et al.2025 · 15 citationsMIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation SystemsConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Nandan Thakur, Suleman Kazi, Ge Luo, et al.2025 · 15 citationsNADI 2025: The First Multidialectal Arabic Speech Processing Shared TaskArabic Natural Language Processing Conference (ArabicNLP)Bashar Talafha, Hawau Olamide Toyin, Peter Sullivan, et al.2025 · 15 citationsNeuron-Level Sequential Editing for Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Houcheng Jiang, Junfeng Fang, Tianyu Zhang, et al.2025 · 15 citationsOn The Origin of Cultural Biases in Language Models: From Pre-training Data to Linguistic PhenomenaConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Tarek Naous, Wei Xu2025 · 15 citationsOntology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question AnsweringAnnual Meeting of the Association for Computational Linguistics (ACL)Runxuan Liu, Bei Luo, Jiaqi Li, et al.2025 · 15 citationsPRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable QueriesConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Mingwen Dong, Nischal Ashok Kumar, Yiqun Hu, et al.2025 · 15 citationsRethinking Reflection in Pre-TrainingarXiv:2504.04022Essential AI: Darsh J Shah, Peter Rushton, Somanshu Singla, et al.2025 · 15 citationsRewarding the Unlikely: Lifting GRPO Beyond Distribution SharpeningConference on Empirical Methods in Natural Language Processing (EMNLP)Andre Wang He, Daniel Fried, Sean Welleck2025 · 15 citationsScaling Low-Resource MT via Synthetic Data Generation with LLMsConference on Empirical Methods in Natural Language Processing (EMNLP)Ona de Gibert, Joseph Attieh, Teemu Vahtola, et al.2025 · 15 citationsToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool UseAnnual Meeting of the Association for Computational Linguistics (ACL)Junjie Ye, Zhengyin Du, Xuesong Yao, et al.2025 · 15 citationsUnderstanding Figurative Meaning through Explainable Visual EntailmentConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Arkadiy Saakyan, Shreyas Kulkarni, Tuhin Chakrabarty, et al.2025 · 15 citationsUnderstanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent SystemsConference on Empirical Methods in Natural Language Processing (EMNLP)Xu Shen, Yixin Liu, Yiwei Dai, et al.2025 · 15 citationsURIEL+: Enhancing Linguistic Inclusion and Usability in a Typological and Multilingual Knowledge BaseInternational Conference on Computational Linguistics (COLING)Aditya Khan, Mason Shipton, David Anugraha, et al.2025 · 15 citationsValue Profiles for Encoding Human VariationConference on Empirical Methods in Natural Language Processing (EMNLP)Taylor Sorensen, Pushkar Mishra, Roma Patel, et al.2025 · 15 citationsWhat are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best PracticesAnnual Meeting of the Association for Computational Linguistics (ACL)Zhi Chen, Qiguang Chen, Libo Qin, et al.2025 · 15 citationsWhat Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient PerspectiveAnnual Meeting of the Association for Computational Linguistics (ACL)Ming Li, Yanhong Li, Tianyi Zhou2025 · 15 citationsA Survey on Efficient Large Language Model Training: From Data-centric PerspectivesAnnual Meeting of the Association for Computational Linguistics (ACL)Junyu Luo, Bohan Wu, Xiao Luo, et al.2025 · 14 citationsAL-QASIDA: Analyzing LLM Quality and Accuracy Systematically in Dialectal ArabicFindings of the Association for Computational LinguisticsNathaniel Romney Robinson, Shahd Abdelmoneim, Kelly Marchisio, et al.2025 · 14 citationsAttention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Zhisong Zhang, Yan Wang, Xinting Huang, et al.2025 · 14 citationsBALSAM: A Platform for Benchmarking Arabic Large Language ModelsArabic Natural Language Processing Conference (ArabicNLP)Rawan Al-Matham, Kareem Darwish, Raghad Al-Rasheed, et al.2025 · 14 citationsBeyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target AtomsAnnual Meeting of the Association for Computational Linguistics (ACL)Mengru Wang, Ziwen Xu, Shengyu Mao, et al.2025 · 14 citationsCoMAT: Chain of Mathematically Annotated Thought Improves Mathematical ReasoningConference on Empirical Methods in Natural Language Processing (EMNLP)Joshua Ong Jun Leang, Aryo Pradipta Gema, Shay B. Cohen2025 · 14 citationsComparative Study of Multilingual Idioms and Similes in Large Language ModelsInternational Conference on Computational Linguistics (COLING)Paria Khoshtab, Danial Namazifard, Mostafa Masoudi, et al.2025 · 14 citationsDoes Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual SettingsAnnual Meeting of the Association for Computational Linguistics (ACL)Austin Xu, Srijan Bansal, Yifei Ming, et al.2025 · 14 citationsEducationQ: Evaluating LLMs' Teaching Capabilities Through Multi-Agent Dialogue FrameworkAnnual Meeting of the Association for Computational Linguistics (ACL)Yao Shi, Rongkeng Liang, Yong Xu2025 · 14 citationsEmoHopeSpeech: An Annotated Dataset of Emotions and Hope Speech in English and ArabicarXiv:2505.11959Wajdi Zaghouani, Md. Rafiul Biswas2025 · 14 citationsEnhancing Mathematical Reasoning in LLMs by Stepwise CorrectionAnnual Meeting of the Association for Computational Linguistics (ACL)Zhenyu Wu, Qingkai Zeng, Zhihan Zhang, et al.2025 · 14 citationsICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Zhenliang Zhang, Xinyu Hu, Huixuan Zhang, et al.2025 · 14 citationsIOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference OptimizationAnnual Meeting of the Association for Computational Linguistics (ACL)Xinghua Zhang, Haiyang Yu, Cheng Fu, et al.2025 · 14 citationsLarge Language Models for Automated Literature Review: An Evaluation of Reference Generation, Abstract Writing, and Review CompositionConference on Empirical Methods in Natural Language Processing (EMNLP)Xuemei Tang, Xufeng Duan, Zhenguang Cai2025 · 14 citationsLLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMsConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Do Xuan Long, Hai Nguyen Ngoc, Tiviatis Sim, et al.2025 · 14 citationsLLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented GenerationInternational Conference on Computational Linguistics (COLING)Keheng Wang, Feiyu Duan, Peiguang Li, et al.2025 · 14 citationsMA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought ReasoningarXiv:2505.20096Thang Nguyen, Peter Chin, Yu-Wing Tai2025 · 14 citationsMind the Blind Spots: A Focus-Level Evaluation Framework for LLM ReviewsConference on Empirical Methods in Natural Language Processing (EMNLP)Hyungyu Shin, Jingyu Tang, Yoonjoo Lee, et al.2025 · 14 citationsMTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teamingAnnual Meeting of the Association for Computational Linguistics (ACL)Weiyang Guo, Jing Li, Wenya Wang, et al.2025 · 14 citationsOmniThink: Expanding Knowledge Boundaries in Machine Writing through ThinkingConference on Empirical Methods in Natural Language Processing (EMNLP)Zekun Xi, Wenbiao Yin, Jizhan Fang, et al.2025 · 14 citationsPre-training Distillation for Large Language Models: A Design Space ExplorationAnnual Meeting of the Association for Computational Linguistics (ACL)Hao Peng, Xin Lv, Yushi Bai, et al.2025 · 14 citationsRaDeR: Reasoning-aware Dense Retrieval ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Debrup Das, Sam O'Nuallain, Razieh Rahimi2025 · 14 citationsRAG-Critic: Leveraging Automated Critic-Guided Agentic Workflow for Retrieval Augmented GenerationAnnual Meeting of the Association for Computational Linguistics (ACL)Guanting Dong, Jiajie Jin, Xiaoxi Li, et al.2025 · 14 citationsShallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMsConference on Empirical Methods in Natural Language Processing (EMNLP)Xiaofeng Zhang, Yihao Quan, Chen Shen, et al.2025 · 14 citationsTowards Inclusive Arabic LLMs: A Culturally Aligned Benchmark in Arabic Large Language Model EvaluationWorkshop on Language Models for Low-Resource LanguagesOmer Nacar, Serry Taiseer Sibaee, Samar Ahmed, et al.2025 · 14 citationsTowards Knowledge Checking in Retrieval-augmented Generation: A Representation PerspectiveConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Shenglai Zeng, Jiankun Zhang, Bingheng Li, et al.2025 · 14 citationsTurBLiMP: A Turkish Benchmark of Linguistic Minimal PairsConference on Empirical Methods in Natural Language Processing (EMNLP)Ezgi Başar, Francesca Padovani, Jaap Jumelet, et al.2025 · 14 citationsUnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs' MemorizationAnnual Meeting of the Association for Computational Linguistics (ACL)Md Nayem Uddin, Amir Saeidi, Divij Handa, et al.2025 · 14 citationsUORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Xueyan Zhang, Jinman Zhao, Zhifei Yang, et al.2025 · 14 citationsA Reality Check on Context Utilisation for Retrieval-Augmented GenerationAnnual Meeting of the Association for Computational Linguistics (ACL)Lovisa Hagström, Sara Vera Marjanovic, Haeun Yu, et al.2025 · 13 citationsADI-20: Arabic Dialect Identification dataset and modelsInterspeechHaroun Elleuch, Salima Mdhaffar, Yannick Esteve, et al.2025 · 13 citationsAFRIDOC-MT: Document-level MT Corpus for African LanguagesConference on Empirical Methods in Natural Language Processing (EMNLP)Jesujoba Oluwadara Alabi, Israel Abebe Azime, Miaoran Zhang, et al.2025 · 13 citationsAlignment for Efficient Tool Calling of Large Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Hongshen Xu, Zihan Wang, Zichen Zhu, et al.2025 · 13 citationsAn Annotated Corpus of Arabic Tweets for Hate Speech AnalysisRecent Advances in Natural Language Processing (RANLP)Wajdi Zaghouani, Md. Rafiul Biswas2025 · 13 citationsCan a Single Model Master Both Multi-turn Conversations and Tool Use? CoALM: A Unified Conversational Agentic Language ModelAnnual Meeting of the Association for Computational Linguistics (ACL)Emre Can Acikgoz, Jeremiah Greer, Akul Datta, et al.2025 · 13 citationsCan We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging TasksAnnual Meeting of the Association for Computational Linguistics (ACL)Xingxuan Li, Weiwen Xu, Ruochen Zhao, et al.2025 · 13 citationsCausal Interventions Reveal Shared Structure Across English Filler–Gap ConstructionsSasha Boguraev, Christopher Potts, Kyle MahowaldEnglish · 13 citationsConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement LearningConference on Empirical Methods in Natural Language Processing (EMNLP)Changtai Zhu, Siyin Wang, Ruijun Feng, et al.2025 · 13 citationsCrowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-JudgeAnnual Meeting of the Association for Computational Linguistics (ACL)Qiyuan Zhang, Yufei Wang, Yuxin Jiang, et al.2025 · 13 citationsDecoding Echo Chambers: LLM-Powered Simulations Revealing Polarization in Social NetworksInternational Conference on Computational Linguistics (COLING)Chenxi Wang, Zongfang Liu, Dequan Yang, et al.2025 · 13 citationsDo Construction Distributions Shape Formal Language Learning In German BabyLMs?Conference on Computational Natural Language Learning (CoNLL)Bastian Bunzeck, Daniel Duran, Sina Zarrieß2025 · 13 citationsDRAMA: Diverse Augmentation from Large Language Models to Smaller Dense RetrieversAnnual Meeting of the Association for Computational Linguistics (ACL)Xueguang Ma, Xi Victoria Lin, Barlas Oguz, et al.2025 · 13 citationsDynamic Parallel Tree Search for Efficient LLM ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Yifu Ding, Wentao Jiang, Shunyu Liu, et al.2025 · 13 citationsEfficient Tool Use with Chain-of-Abstraction ReasoningInternational Conference on Computational Linguistics (COLING)Silin Gao, Jane Dwivedi-Yu, Ping Yu, et al.2025 · 13 citationsEmbracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based AgentsAnnual Meeting of the Association for Computational Linguistics (ACL)Tao Wu, Jingyuan Chen, Wang Lin, et al.2025 · 13 citationsEnhancing Arabic Automated Essay Scoring with Synthetic Data and Error InjectionWorkshop on Innovative Use of NLP for Building Educational Applications (BEA)Chatrine Qwaider, Bashar Alhafni, Kirill Chirkunov, et al.2025 · 13 citationsEnhancing Automated Interpretability with Output-Centric Feature DescriptionsAnnual Meeting of the Association for Computational Linguistics (ACL)Yoav Gur-Arieh, Roy Mayan, Chen Agassy, et al.2025 · 13 citationsFinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and ChallengingAnnual Meeting of the Association for Computational Linguistics (ACL)Zichen Tang, Haihong E, Ziyan Ma, et al.2025 · 13 citationsImageEval 2025: The First Arabic Image Captioning Shared TaskArabic Natural Language Processing Conference (ArabicNLP)Ahlam Bashiti, Alaa Aljabari, Hadi Hamoud, et al.2025 · 13 citationsLarge Language Model-Based Event Relation Extraction with RationalesInternational Conference on Computational Linguistics (COLING)Zhilei Hu, Zixuan Li, Xiaolong Jin, et al.2025 · 13 citationsLearning to Refuse: Towards Mitigating Privacy Risks in LLMsInternational Conference on Computational Linguistics (COLING)Zhenhua Liu, Tong Zhu, Chuanyuan Tan, et al.2025 · 13 citations← prev 1 … 5 6 7 … 10 … 18 next →↑ back to topThis page in Markdown → https://md.research.elamur.ai/free/en/papers/2025/page/6/