Generation

Avoidance Decoding for Diverse Multi-Branch Story Generation EMNLP 2025 A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding NAACL 2025 Babies Learn to Look Ahead: Multi-Token Prediction in Small LMs EMNLP 2025 BabyLM’s First Constructions: Causal interventions provide a signal of learning EMNLP 2025 BabyLM’s First Words: Word Segmentation as a Phonological Probing Task CoNLL 2025 BabyLMs for isiXhosa: Data-Efficient Language Modelling in a Low-Resource Context COLING 2025 Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations NAACL 2025 BAGELS: Benchmarking the Automated Generation and Extraction of Limitations from Scholarly Text EMNLP 2025 bAI-bAI: A Context-Aware Transliteration System for Baybayin Scripts COLING 2025 Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation ACL 2025 Balancing Privacy and Utility in Personal LLM Writing Tasks: An Automated Pipeline for Evaluating Anonymizations NAACL 2025 BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms ICML 2025 BanglaTalk: Towards Real-Time Speech Assistance for Bengali Regional Dialects AACL 2025 Barrier Breakers at BLP-2025 Task 2: Enhancing LLM Code Generation Capabilities through Test-Driven Development and Code Interpreter AACL 2025 Batch-wise Convergent Pre-training: Step-by-Step Learning Inspired by Child Language Development EMNLP 2025 BDA-UC3M @ BioLaySumm: Efficient Lay Summarization with Small-Scale SoTA LLMs ACL 2025 bea-jh at BEA 2025 Shared Task: Evaluating AI-powered Tutors through Pedagogically-Informed Reasoning ACL 2025 BeefBot: Harnessing Advanced LLM and RAG Techniques for Providing Scientific and Technology Solutions to Beef Producers COLING 2025 Behavioral Analysis of Information Salience in Large Language Models ACL 2025 BehaviorBox: Automated Discovery of Fine-Grained Performance Differences Between Language Models ACL 2025 Behavior-SD: Behaviorally Aware Spoken Dialogue Generation with Large Language Models NAACL 2025 Benchmarking Critical Questions Generation: A Challenging Reasoning Task for Large Language Models EMNLP 2025 Benchmarking Language Model Creativity: A Case Study on Code Generation NAACL 2025 Benchmarking LLMs on Semantic Overlap Summarization EMNLP 2025 Benchmarking Multimodal Models for Ukrainian Language Understanding Across Academic and Cultural Domains ACL 2025