Natural Language Processing › Generation ›

Language Modeling

1624 directly classified papers

Papers per year

Papers

BabyLMs for isiXhosa: Data-Efficient Language Modelling in a Low-Resource Context COLING 2025

Using tournaments to calculate AUROC for zero-shot classification with LLMs EMNLP 2025

D2CS - Documents Graph Clustering using LLM supervision EMNLP 2025

Thinking Before You Speak: A Proactive Test-time Scaling Approach EMNLP 2025

Predicate-Guided Generation for Mathematical Reasoning EMNLP 2025

From Anger to Joy: How Nationality Personas Shape Emotion Attribution in Large Language Models IJCNLP 2025

Are LLMs Rigorous Logical Reasoners? Empowering Natural Language Proof Generation by Stepwise Decoding with Contrastive Learning IJCNLP 2025

Adapting Large Language Models for Character-based Augmentative and Alternative Communication EMNLP 2025

MANTA: A Scalable Pipeline for Transmuting Massive Web Corpora into Instruction Datasets EMNLP 2025

Ability Transfer Through Language Mixing IJCNLP 2025

Definition Generation for Word Meaning Modeling: Monolingual, Multilingual, and Cross-Lingual Perspectives EMNLP 2025

“Well, Keep Thinking”: Enhancing LLM Reasoning with Adaptive Injection Decoding ACL 2025

Unlocking Recursive Thinking of LLMs: Alignment via Refinement ACL 2025

Language Models are Crossword Solvers NAACL 2025

Revisiting In-Context Learning with Long Context Language Models ACL 2025

MC2: A Minimum-Coverage and Dataset-Agnostic Framework for Compositional Generalization of LLMs on Semantic Parsing EMNLP 2025

Surprise Calibration for Better In-Context Learning EMNLP 2025

Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations NAACL 2025

Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation NAACL 2025

Forest for the Trees: Overarching Prompting Evokes High-Level Reasoning in Large Language Models NAACL 2025

Long-Tail Crisis in Nearest Neighbor Language Models NAACL 2025

Optimizing Hidden Markov Language Models: An Empirical Study of Reparameterization and Initialization Techniques NAACL 2025

EuskañolDS: A Naturally Sourced Corpus for Basque-Spanish Code-Switching NAACL 2025

Are Larger Language Models Better at Disambiguation? NAACL 2025

Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning ACL 2025