Language Modeling

Mapping Cross-Lingual Sentence Representations for Low-Resource Language Pairs Using Pre-trained Language Models COLING 2025 Mask and You Shall Receive: Optimizing Masked Language Modeling For Pretraining BabyLMs EMNLP 2025 Masked Diffusion Language Models with Frequency-Informed Training EMNLP 2025 Masked Language Modeling Becomes Conditional Density Estimation for Tabular Data Synthesis AAAI 2025 MC2: A Minimum-Coverage and Dataset-Agnostic Framework for Compositional Generalization of LLMs on Semantic Parsing EMNLP 2025 Measuring and Benchmarking Large Language Models’ Capabilities to Generate Persuasive Language NAACL 2025 MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented Generation ACL 2025 Memorization or Reasoning? Exploring the Idiom Understanding of LLMs EMNLP 2025 MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer EMNLP 2025 MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space ACL 2025 MIND: Math Informed syNthetic Dialogues for Pretraining LLMs ICLR 2025 Mind the Gap: Gender-based Differences in Occupational Embeddings ACL 2025 Mind the Gap: How BabyLMs Learn Filler-Gap Dependencies EMNLP 2025 MissRAG: Addressing the Missing Modality Challenge in Multimodal Large Language Models ICCV 2025 Mitigate Position Bias in LLMs via Scaling a Single Hidden States Channel ACL 2025 Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs EMNLP 2025 Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling NAACL 2025 Mixing Inference-time Experts for Enhancing LLM Reasoning EMNLP 2025 MixMin: Finding Data Mixtures via Convex Minimization ICML 2025 Mixture of Experts Made Intrinsically Interpretable ICML 2025 ModeLing: A Novel Dataset for Testing Linguistic Reasoning in Language Models NAACL 2025 Modeling Chinese L2 Writing Development: The LLM-Surprisal Perspective NAACL 2025 Modeling Subjectivity in Cognitive Appraisal with Language Models EMNLP 2025 Modular Arithmetic: Language Models Solve Math Digit by Digit IJCNLP 2025 MoLEx: Mixture of Layer Experts for Fine-tuning with Sparse Upcycling ICLR 2025