Large Language Models

LoCt-Instruct: An Automatic Pipeline for Constructing Datasets of Logical Continuous Instructions EMNLP 2025 LOFT: Scalable and More Realistic Long-Context Evaluation NAACL 2025 Logarithmic Regret for Online KL-Regularized Reinforcement Learning ICML 2025 Logical forms complement probability in understanding language model (and human) performance ACL 2025 Logical Reasoning with Outcome Reward Models for Test-Time Scaling EMNLP 2025 Logic Distillation: Learning from Code Function by Function for Decision-making Tasks IJCAI 2025 LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models ACL 2025 Logic: Long-form Outline Generation via Imitative and Critical Self-refinement EMNLP 2025 Logic-Regularized Verifier Elicits Reasoning from LLMs ACL 2025 LogicTree: Structured Proof Exploration for Coherent and Rigorous Logical Reasoning with Large Language Models EMNLP 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 LOGO — Long cOntext aliGnment via efficient preference Optimization ICML 2025 LoGU: Long-form Generation with Uncertainty Expressions ACL 2025 Long Chain-of-Thought Fine-tuning via Understanding-to-Reasoning Transition EMNLP 2025 LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information ACL 2025 LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data ACL 2025 Long-Form Information Alignment Evaluation Beyond Atomic Facts EMNLP 2025 LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models ACL 2025 LongRoPE2: Near-Lossless LLM Context Window Scaling ICML 2025 LongSafety: Enhance Safety for Long-Context LLMs ACL 2025 LongSafety: Evaluating Long-Context Safety of Large Language Models ACL 2025 Long-Short Alignment for Effective Long-Context Modeling in LLMs ICML 2025 LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding ICML 2025 LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability EMNLP 2025