Language Modeling

Learning to vary: Teaching LMs to reproduce human linguistic variability in next-word prediction EMNLP 2025 Learn to Memorize: Scalable Continual Learning in Semiparametric Models with Mixture-of-Neighbors Induction Memory ACL 2025 Lemma Dilemma: On Lemma Generation Without Domain- or Language-Specific Training Data EMNLP 2025 Leveraging Dictionaries and Grammar Rules for the Creation of Educational Materials for Indigenous Languages NAACL 2025 Linear Decoding of Morphology Relations in Language Models (Student Abstract) AAAI 2025 Linear Recency Bias During Training Improves Transformers’ Fit to Reading Times COLING 2025 Linguistic Units as Tokens: Intrinsic and Extrinsic Evaluation with BabyLM EMNLP 2025 LLäMmlein: Transparent, Compact and Competitive German-Only Language Models from Scratch ACL 2025 LLMs for Extremely Low-Resource Finno-Ugric Languages NAACL 2025 LM-Pub-Quiz: A Comprehensive Framework for Zero-Shot Evaluation of Relational Knowledge in Language Models NAACL 2025 LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning EMNLP 2025 Logits are All We Need to Adapt Closed Models ICML 2025 LoGU: Long-form Generation with Uncertainty Expressions ACL 2025 LOLA – An Open-Source Massively Multilingual Large Language Model COLING 2025 Long-Form Speech Generation with Spoken Language Models ICML 2025 Long-Short Alignment for Effective Long-Context Modeling in LLMs ICML 2025 Long-Tail Crisis in Nearest Neighbor Language Models NAACL 2025 LongTail-Swap: benchmarking language models’ abilities on rare words EMNLP 2025 Looking Beyond the Top-1: Transformers Determine Top Tokens in Order ICML 2025 Loss Functions and Operators Generated by f-Divergences ICML 2025 Machine Translation Using Grammar Materials for LLM Post-Correction NAACL 2025 MAGNET: Augmenting Generative Decoders with Representation Learning and Infilling Capabilities ACL 2025 MAIN: Mutual Alignment Is Necessary for instruction tuning EMNLP 2025 MALAMUTE: A Multilingual, Highly-granular, Template-free, Education-based Probing Dataset ACL 2025 MANTA: A Scalable Pipeline for Transmuting Massive Web Corpora into Instruction Datasets EMNLP 2025