Large Language Models

Priority on High-Quality: Selecting Instruction Data via Consistency Verification of Noise Injection EMNLP 2025 Prior Prompt Engineering for Reinforcement Fine-Tuning EMNLP 2025 PRISM: Efficient Long-Range Reasoning With Short-Context LLMs EMNLP 2025 Privacy Checklist: Privacy Violation Detection Grounding on Contextual Integrity Theory NAACL 2025 Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training ACL 2025 Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models ACL 2025 Probability-Consistent Preference Optimization for Enhanced LLM Reasoning ACL 2025 Probing and Boosting Large Language Models Capabilities via Attention Heads EMNLP 2025 Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set ACL 2025 Probing Logical Reasoning of MLLMs in Scientific Diagrams EMNLP 2025 Probing the Limits of Multilingual Language Understanding: Low-Resource Language Proverbs as LLM Benchmark for AI Wisdom EMNLP 2025 Problem Solved? Information Extraction Design Space for Layout-Rich Documents using LLMs EMNLP 2025 Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoning ACL 2025 Programming by Example meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction ACL 2025 Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale ICML 2025 Progressive Prefix-Memory Tuning for Complex Logical Query Answering on Knowledge Graphs IJCAI 2025 Progress or Regress? Self-Improvement Reversal in Post-training ICLR 2025 ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges ICCV 2025 ProLongVid: A Simple but Strong Baseline for Long-context Video Instruction Tuning EMNLP 2025 ProMALex: Progressive Modular Adapters for Multi-Jurisdictional Legal Language Modeling ACL 2025 Promote, Suppress, Iterate: How Language Models Answer One-to-Many Factual Queries EMNLP 2025 PROM: Pivoted and Regulated Optimization for Multilingual Instruction Learning NAACL 2025 Prompt and circumstance: A word-by-word LLM prompting approach to interlinear glossing for low-resource languages NAACL 2025 Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation ACL 2025 Prompt Compression for Large Language Models: A Survey NAACL 2025