Papers of 2025 — page 11

Minimal Pair-Based Evaluation of Code-SwitchingAnnual Meeting of the Association for Computational Linguistics (ACL)Igor Sterner, Simone Teufel2025 · 6 citations

OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QAarXiv:2510.06371Firoj Alam, Ali Ezzat Shahroor, Md. Arid Hasan, et al.2025 · 6 citations Pangu Ultra: Pushing the Limits of Dense Large Language Models on Ascend NPUsarXiv:2504.07866Yichun Yin, Wenyong Huang, Kaikai Song, et al.2025 · 6 citations

PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level AdaptationAnnual Meeting of the Association for Computational Linguistics (ACL)Linhai Zhang, Jialong Wu, Deyu Zhou, et al.2025 · 6 citations

R2-MultiOmnia: Leading Multilingual Multimodal Reasoning via Self-TrainingAnnual Meeting of the Association for Computational Linguistics (ACL)Leonardo Ranaldi, Federico Ranaldi, Giulia Pucci2025 · 6 citations

Revisiting Common Assumptions about Arabic Dialects in NLPAnnual Meeting of the Association for Computational Linguistics (ACL)Amr Keleg, Sharon Goldwater, Walid Magdy2025 · 6 citations

Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias ResultsAnnual Meeting of the Association for Computational Linguistics (ACL)Andrea Santilli, Adam Golinski, Michael Kirchhof, et al.2025 · 6 citations

rStar2-Agent: Agentic Reasoning Technical ReportarXiv:2508.20722Ning Shang, Yifei Liu, Yi Zhu, et al.2025 · 6 citations

ShifCon: Enhancing Non-Dominant Language Capabilities with a Shift-based Multilingual Contrastive FrameworkAnnual Meeting of the Association for Computational Linguistics (ACL)Hengyuan Zhang, Chenming Shang, Sizhe Wang, et al.2025 · 6 citations

Skywork-R1V3 Technical ReportarXiv:2507.06167Wei Shen, Jiangbo Pei, Yi Peng, et al.2025 · 6 citations

Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Anshumann, Mohd Abbas Zaidi, Akhil Kedia, et al.2025 · 6 citations

The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate ItConference on Empirical Methods in Natural Language Processing (EMNLP)Leonardo Bertolazzi, Philipp Mondorf, Barbara Plank, et al.2025 · 6 citations

Thinking with Sound: Audio Chain-of-Thought Enables Multimodal Reasoning in Large Audio-Language ModelsarXiv:2509.21749Zhen Xiong, Yujun Cai, Zhecheng Li, et al.2025 · 6 citations

TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship ClassificationAnnual Meeting of the Association for Computational Linguistics (ACL)Junnan Zhu, Min Xiao, Yining Wang, et al.2025 · 6 citations

Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode TheoryConference on Empirical Methods in Natural Language Processing (EMNLP)Ming Li, Nan Zhang, Chenrui Fan, et al.2025 · 6 citations

Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context InjectionConference on Empirical Methods in Natural Language Processing (EMNLP)Miao Ziqi, Yi Ding, Lijun Li, et al.2025 · 6 citations

Weaver: Interweaving SQL and LLM for Table ReasoningConference on Empirical Methods in Natural Language Processing (EMNLP)Rohit Khoja, Devanshu Gupta, Yanjie Fu, et al.2025 · 6 citations

When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMsConference on Empirical Methods in Natural Language Processing (EMNLP)Ammar Khairi, Daniel D'souza, Ye Shen, et al.2025 · 6 citations

A Collection of Question Answering Datasets for NorwegianNordic Conference on Computational Linguistics (NoDaLiDa)Vladislav Mikhailov, Petter Mæhlum, Victoria Ovedie Chruickshank Langø, et al.2025 · 5 citations

A Survey of Idiom Datasets for Psycholinguistic and Computational ResearchConference on Natural Language ProcessingMichael Flor, Xinyi Liu, Anna Feldman2025 · 5 citations

Add-One-In: Incremental Sample Selection for Large Language Models via a Choice-Based Greedy ParadigmConference on Empirical Methods in Natural Language Processing (EMNLP)Zhuo Li, Yuhao Du, Xiaoqi Jiao, et al.2025 · 5 citations

Advancing Arabic Diacritization: Improved Datasets, Benchmarking, and State-of-the-Art ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Abubakr Mohamed, Hamdy Mubarak2025 · 5 citations

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?Conference on Empirical Methods in Natural Language Processing (EMNLP)Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, et al.2025 · 5 citations

ArabJobs: A Multinational Corpus of Arabic Job AdsArabic Natural Language Processing Conference (ArabicNLP)Mo El-Haj2025 · 5 citations

Beyond Gold Standards: Epistemic Ensemble of LLM Judges for Formal Mathematical ReasoningarXiv:2506.10903Lan Zhang, Marco Valentino, Jordan Meadows, et al.2025 · 5 citations Bilingual BSARD: Extending Statutory Article Retrieval to DutchProceedings of the 1st Regulatory NLP Workshop (RegNLP 2025)Ehsan Lotfi, Nikolay Banar, Nerses Yuzbashyan, et al.2025 · 5 citations

BiMediX2 : Bio-Medical EXpert LMM for Diverse Medical ModalitiesFindings of the Association for Computational LinguisticsSahal Shaji Mullappilly, Mohammed Irfan Kurpath, Sara Pieri, et al.2025 · 5 citations

Conflicting Needles in a Haystack: How LLMs behave when faced with contradictory informationConference on Empirical Methods in Natural Language Processing (EMNLP)Murathan Kurfali, Robert Östling2025 · 5 citations

EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language ModelsConference on Empirical Methods in Natural Language Processing (EMNLP)Tao Zou, Xinghua Zhang, Haiyang Yu, et al.2025 · 5 citations

Embedding-Informed Adaptive Retrieval-Augmented Generation of Large Language ModelsInternational Conference on Computational Linguistics (COLING)Chengkai Huang, Yu Xia, Rui Wang, et al.2025 · 5 citations

Feature Engineering is not Dead: A Step Towards State of the Art for Arabic Automated Essay ScoringArabic Natural Language Processing Conference (ArabicNLP)Marwan Sayed, Sohaila Eltanbouly, May Bashendy, et al.2025 · 5 citations

From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical CalculationsConference on Empirical Methods in Natural Language Processing (EMNLP)Benlu Wang, Iris Xia, Yifan Zhang, et al.2025 · 5 citations

GATEAU: Selecting Influential Samples for Long Context AlignmentConference on Empirical Methods in Natural Language Processing (EMNLP)Shuzheng Si, Haozhe Zhao, Gang Chen, et al.2025 · 5 citations

Growing Through Experience: Scaling Episodic Grounding in Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Chunhui Zhang, Sirui Wang, Zhongyu Ouyang, et al.2025 · 5 citations

HypER: Literature-grounded Hypothesis Generation and Distillation with ProvenanceConference on Empirical Methods in Natural Language Processing (EMNLP)Rosni Vasu, Chandrayee Basu, Bhavana Dalvi Mishra, et al.2025 · 5 citations

InductionBench: LLMs Fail in the Simplest Complexity ClassAnnual Meeting of the Association for Computational Linguistics (ACL)Wenyue Hua, Tyler Wong, Fei Sun, et al.2025 · 5 citations

Irony Detection, Reasoning and Understanding in Zero-shot LearningarXiv:2501.16884Peiling Yi, Yuhan Xia, Yunfei Long2025 · 5 citations

It is not a piece of cake for GPT: Explaining Textual Entailment Recognition in the presence of Figurative LanguageInternational Conference on Computational Linguistics (COLING)Giuseppe Gallipoli, Luca Cagliero2025 · 5 citations

Large Language Models and Arabic Content: A ReviewarXiv:2505.08004Haneh Rhel, Dmitri Roussinov2025 · 5 citations

LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-DisjointAnnual Meeting of the Association for Computational Linguistics (ACL)Qianli Ma, Dongrui Liu, Qian Chen, et al.2025 · 5 citations

LLM Alignment for the Arabs: A Homogenous Culture or Diverse OnesWorkshop on Cross-Cultural Considerations in NLPAmr Keleg2025 · 5 citations

LLM Dependency Parsing with In-Context RulesMichael Ginn, Alexis PalmerMova's core list · 5 citations LLMs are Vulnerable to Malicious Prompts Disguised as Scientific LanguagearXiv:2501.14073Yubin Ge, Neeraja Kirtane, Hao Peng, et al.2025 · 5 citations

LLMs can Perform Multi-Dimensional Analytic Writing Assessments: A Case Study of L2 Graduate-Level Academic English WritingAnnual Meeting of the Association for Computational Linguistics (ACL)Zhengxiang Wang, Veronika Makarova, Zhi Li, et al.2025 · 5 citations

Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLMsConference on Empirical Methods in Natural Language Processing (EMNLP)Zhen Xiong, Yujun Cai, Zhecheng Li, et al.2025 · 5 citations

Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large LanguageAnnual Meeting of the Association for Computational Linguistics (ACL)Bo Zeng, Chenyang Lyu, Sinuo Liu, et al.2025 · 5 citations

MASA: LLM-Driven Multi-Agent Systems for AutoformalizationConference on Empirical Methods in Natural Language Processing (EMNLP)Lan Zhang, Marco Valentino, Andre Freitas2025 · 5 citations

ME2-BERT: Are Events and Emotions what you need for Moral Foundation Prediction?International Conference on Computational Linguistics (COLING)Lorenzo Zangari, Candida M. Greco, Davide Picca, et al.2025 · 5 citations

Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive DecodingAnnual Meeting of the Association for Computational Linguistics (ACL)Zikai Xiao, Ziyang Wang, Wen Ma, et al.2025 · 5 citations

MizanQA: Benchmarking Large Language Models on Moroccan Legal Question AnsweringarXiv:2508.16357Adil Bahaj, Mounir Ghogho2025 · 5 citations mR3: Multilingual Rubric-Agnostic Reward Reasoning ModelsarXiv:2510.01146David Anugraha, Shou-Yi Hung, Zilu Tang, et al.2025 · 5 citations

MultiProSE: A Multi-label Arabic Dataset for Propaganda, Sentiment, and Emotion DetectionLecture notes in computer scienceLubna Al-Henaki, Hend Al-Khalifa, Abdulmalik Al-Salman, et al.2025 · 5 citations

Parsing the Switch: LLM-Based UD Annotation for Complex Code-Switched and Low-Resource LanguagesOlga Kellert, Nemika Tyagi, Muhammad Imran, et al.Mova's core list · 5 citations

Recitation over Reasoning: How Cutting-Edge Language Models Can Fail on Elementary School-Level Reasoning Problems?International Joint Conference on Natural Language Processing (IJCNLP)Kai Yan, Yufei Xu, Zhengyin Du, et al.2025 · 5 citations

Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMsarXiv:2506.14731Ling Team, Bin Hu, Cai Chen, et al.2025 · 5 citations

RoCoFT: Efficient Finetuning of Large Language Models with Row-Column UpdatesAnnual Meeting of the Association for Computational Linguistics (ACL)Md Kowsher, Tara Esmaeilbeig, Chun-Nam Yu, et al.2025 · 5 citations

RRHF-V: Ranking Responses to Mitigate Hallucinations in Multimodal Large Language Models with Human FeedbackInternational Conference on Computational Linguistics (COLING)Guoqing Chen, Fu Zhang, Jinghao Lin, et al.2025 · 5 citations

Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation ModelarXiv:2503.07703Lixue Gong, Xiaoxia Hou, Fanshi Li, et al.2025 · 5 citations

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Erxin Yu, Jing Li, Ming Liao, et al.2025 · 5 citations

SubLIME: Subset Selection via Rank Correlation Prediction for Data-Efficient LLM EvaluationAnnual Meeting of the Association for Computational Linguistics (ACL)Gayathri Saranathan, Cong Xu, Mahammad Parwez Alam, et al.2025 · 5 citations

Teach Small Models to Reason by Curriculum DistillationConference on Empirical Methods in Natural Language Processing (EMNLP)Wangyi Jiang, Yaojie Lu, Hongyu Lin, et al.2025 · 5 citations

Text-Attributed Graph Learning with Coupled AugmentationsInternational Conference on Computational Linguistics (COLING)Chuang Zhou, Jiahe Du, Huachi Zhou, et al.2025 · 5 citations

The DISRPT 2025 Shared Task on Elementary Discourse Unit Segmentation, Connective Detection, and Relation ClassificationShared Task on Discourse Relation Parsing and TreebankingChloé Braud, Amir Zeldes, Chuyuan Li, et al.2025 · 5 citations

Towards Context-Robust LLMs: A Gated Representation Fine-tuning ApproachAnnual Meeting of the Association for Computational Linguistics (ACL)Shenglai Zeng, Pengfei He, Kai Guo, et al.2025 · 5 citations

TreeCut: A Synthetic Unanswerable Math Word Problem Dataset for LLM Hallucination EvaluationAnnual Meeting of the Association for Computational Linguistics (ACL)Jialin Ouyang2025 · 5 citations

Uncertainty Distillation: Teaching Language Models to Express Semantic ConfidencearXiv:2503.14749Sophia Hager; David Mueller; Kevin Duh;, Nicholas Andrews2025 · 5 citations

Vulnerability of LLMs to Vertically Aligned Text ManipulationsAnnual Meeting of the Association for Computational Linguistics (ACL)Zhecheng Li, Yiwei Wang, Bryan Hooi, et al.2025 · 5 citations

ZERA: Zero-init Instruction Evolving Refinement Agent – From Zero Instructions to Structured Prompts via Principle-based OptimizationConference on Empirical Methods in Natural Language Processing (EMNLP)Seungyoun Yi, Minsoo Khang, Sungrae Park2025 · 5 citations

A Survey of Machine Learning Models and Datasets for the Multi-label Classification of Textual Hate Speech in EnglishACM Transactions on Knowledge Discovery from DataJulian Baumler, Louis Blocher, Lars-Joel Frey, et al.2025 · 4 citations

Advanced Deep Learning Approaches for Automated Recognition of Cuneiform SymbolsarXiv:2505.04678Shahad Elshehaby, Alavikunhu Panthakkan, Hussain Al-Ahmad, et al.2025 · 4 citations

An Ensemble Classification Approach in A Multi-Layered Large Language Model Framework for Disease PredictionIEEE/ACS International Conference on Computer Systems and Applications (AICCSA)Ali Hamdi, Malak Mohamed, Rokaia Emad, et al.2025 · 4 citations

An Icelandic Linguistic Benchmark for Large Language ModelsNordic Conference on Computational Linguistics (NoDaLiDa)Bjarki Ármannsson, Finnur Ágúst Ingimundarson, Einar Freyr Sigurðsson2025 · 4 citations

Analysis of LLM as a grammatical feature tagger for African American EnglishFindings of the Association for Computational LinguisticsRahul Porwal, Alice Rozet, Jotsna Gowda, et al.2025 · 4 citations

Arabic ASR on the SADA Large-Scale Arabic Speech Corpus with Transformer-Based ModelsLecture notes in computer scienceBranislav Gerazov, Marcello Politi, Sebastien Bratieres2025 · 4 citations

AraFinNews: Arabic Financial Summarisation with Domain-Adapted LLMsIEEE International Conference on Big Data (BigData)Mo El-Haj, Paul Rayson2025 · 4 citations

Are BabyLMs Deaf to Gricean Maxims? A Pragmatic Evaluation of Sample-efficient Language ModelsBabyLM WorkshopRaha Askari, Sina Zarrieß, Özge Alacam, et al.2025 · 4 citations

ATHAR: A High-Quality and Diverse Dataset for Classical Arabic to English TranslationArabic Natural Language Processing Conference (ArabicNLP)Mohammed Sabry Mohammed, Mohammed Khalil2025 · 4 citations

Automatic Speech Recognition of African American English: Lexical and Contextual EffectsInterspeechHamid Mojarad, Kevin Tang2025 · 4 citations

Beyond Base Predictors: Using LLMs to Resolve Ambiguities in Akkadian LemmatizationFrederick RiemenschneiderSemitic languages · 4 citations

Bootstrapping AI: Interdisciplinary Approaches to Assessing OCR Quality in English-Language Historical DocumentsInternational Conference on Natural Language Processing for the Digital HumanitiesSamuel Backer, Louis Hyman2025 · 4 citations

Breaking Bad: Norms for Valence, Arousal, and Dominance for over 10k English Multiword ExpressionsInternational Joint Conference on Natural Language Processing (IJCNLP)Saif M. Mohammad2025 · 4 citations

CAFE: Retrieval Head-based Coarse-to-Fine Information Seeking to Enhance Multi-Document QA CapabilityConference on Empirical Methods in Natural Language Processing (EMNLP)Han Peng, Jinhao Jiang, Zican Dong, et al.2025 · 4 citations

CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation BackdoorConference on Empirical Methods in Natural Language Processing (EMNLP)Zhenhua Xu, Xixiang Zhao, Xubin Yue, et al.2025 · 4 citations

CVPD at QIAS 2025 Shared Task: An Efficient Encoder-Based Approach for Islamic Inheritance ReasoningArabic Natural Language Processing Conference (ArabicNLP)Salah Eddine Bekhouche, Abdellah Zakaria Sellam, Telli Hichem, et al.2025 · 4 citations

DaKultur: Evaluating the Cultural Awareness of Language Models for Danish with Native SpeakersWorkshop on Cross-Cultural Considerations in NLPMax Müller-Eberstein, Mike Zhang, Elisa Bassignana, et al.2025 · 4 citations

DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree TraversalAnnual Meeting of the Association for Computational Linguistics (ACL)Vaibhav Aggarwal, Ojasv Kamal, Abhinav Japesh, et al.2025 · 4 citations

EHSAN: Leveraging ChatGPT in a Hybrid Framework for Arabic Aspect-Based Sentiment Analysis in HealthcareLecture notes in computer scienceEman Alamoudi, Ellis Solaiman2025 · 4 citations

ELYADATA & LIA at NADI 2025: ASR and ADI SubtasksArabic Natural Language Processing Conference (ArabicNLP)Haroun Elleuch, Youssef Saidi, Salima Mdhaffar, et al.2025 · 4 citations

Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM EnrichingConference on Empirical Methods in Natural Language Processing (EMNLP)Songze Li, Zhiqiang Liu, Zhengke Gui, et al.2025 · 4 citations

Evaluating Large Language Models on Health-Related Claims Across Arabic DialectsWorkshop on NLP for Languages Using Arabic ScriptAbdulsalam obaid Alharbi, Abdullah Alsuhaibani, Abdulrahman Abdullah Alalawi, et al.2025 · 4 citations

Evaluating Numeracy of Language Models as a Natural Language Inference TaskFindings of the Association for Computational LinguisticsRahmad Mahendra, Damiano Spina, Lawrence Cavedon, et al.2025 · 4 citations

Evaluating the Effectiveness of Direct Preference Optimization for Personalizing German Automatic Text Simplifications for Persons with Intellectual DisabilitiesarXiv:2507.01479Yingqiang Gao, Kaede Johnson, David Froehlich, et al.2025 · 4 citations Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUsarXiv:2503.05139Ling Team; Binwei Zeng; Chao Huang; Chao Zhang; Changxin Tian; Cong Chen; Dingnan Jin; Feng Yu; Feng Zhu; Feng Yuan; Fakang Wang; Gangshan Wang; Guangyao Zhai; Haitao Zhang; Huizhong Li; Jun Zhou; Jia Liu; Junpeng Fang; Junjie Ou; Jun Hu; Ji Luo; Ji Zhang; Jian Liu; Jian Sha; Jianxue Qian; Jiewei Wu; Junping Zhao; Jianguo Li; Jubao Feng; Jingchao Di; Junming Xu; Jinghua Yao; Kuan Xu; Kewei Du; Longfei Li; Lei Liang; Lu Yu; Li Tang; Lin Ju; Peng Xu; Qing Cui; Song Liu; Shicheng Li; Shun Song; Song Yan; Tengwei Cai; Tianyi Chen; Ting Guo; Ting Huang; Tao Feng; Tao Wu; Wei Wu; Xiaolu Zhang; Xueming Yang; Xin Zhao; Xiaobo Hu; Xin Lin; Yao Zhao; Yilong Wang; Yongzhen Guo; Yuanyuan Wang; Yue Yang; Yang Cao; Yuhao Fu; Yi Xiong; Yanzhe Li; Zhe Li; Zhiqiang Zhang; Ziqi Liu; Zhaoxin Huan; Zujie Wen; Zhenhang Sun; Zhuoxuan Du;, Zhengyu He2025 · 4 citations Exploring the Structure of AI-Induced Language Change in Scientific EnglisharXiv:2506.21817 · The International FLAIRS Conference Proceedings (Vol. 38), 2025Riley Galpin, Bryce Anderson, Tom S. Juzek2025 · 4 citations Generative AI and linguistic diversity in academic writing and publishing: Perspectives from World EnglishesarXiv:2607.28505 · Generative AI and linguistic diversity in academic writing and publishing: Perspectives from World Englishes. Journal of English for Research Publication Purposes, 2025, 6(2), 265-289Kingsley Ugwuanyi, Christian Mair, Sender Dovchin, et al.2025 · 4 citations

HIAST at QIAS 2025: Retrieval-Augmented LLMs with Top-Hit Web Evidence for Arabic Islamic Reasoning QAArabic Natural Language Processing Conference (ArabicNLP)Mohamed Motasim Hamed, Nada Ghneim, Riad Sonbol2025 · 4 citations

IdentifyMe: A Challenging Long-Context Mention Resolution Benchmark for LLMsConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Kawshik Manikantan, Makarand Tapaswi, Vineet Gandhi, et al.2025 · 4 citations

In the LLM era, Word Sense Induction remains unsolvedAnna Mosolova, Marie Candito, Carlos RamischEnglish · 4 citations Kimi-Dev: Agentless Training as Skill Prior for SWE-AgentsarXiv:2509.23045Zonghan Yang, Shengjie Wang, Kelin Fu, et al.2025 · 4 citations Kuwain 1.5B: An Arabic SLM via Language InjectionarXiv:2504.15120Khalil Hennara, Sara Chrouf, Mohamed Motaism Hamed, et al.2025 · 4 citations

← prev 1 … 10 11 12 … 18 next →

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/2025/page/11/

📅 Papers of 2025 — page 11

Papers of 2025 — page 11