Large Language Models

Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models ACL 2025 ProAPO: Progressively Automatic Prompt Optimization for Visual Classification CVPR 2025 Probability-Consistent Preference Optimization for Enhanced LLM Reasoning ACL 2025 Probe-Free Low-Rank Activation Intervention NAACL 2025 Probing and Boosting Large Language Models Capabilities via Attention Heads EMNLP 2025 Probing Gender Bias in Multilingual LLMs: A Case Study of Stereotypes in Persian EMNLP 2025 Probing Internal Representations of Multi-Word Verbs in Large Language Models NAACL 2025 Probing LLMs for Multilingual Discourse Generalization Through a Unified Label Set ACL 2025 Probing LLM World Models: Enhancing Guesstimation with Wisdom of Crowds Decoding EMNLP 2025 Probing Logical Reasoning of MLLMs in Scientific Diagrams EMNLP 2025 Probing Narrative Morals: A New Character-Focused MFT Framework for Use with Large Language Models EMNLP 2025 Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval NAACL 2025 Probing Subphonemes in Morphology Models ACL 2025 Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks ACL 2025 Probing Visual Language Priors in VLMs ICML 2025 Process-Supervised Reinforcement Learning for Code Generation EMNLP 2025 Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertise EMNLP 2025 ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations ACL 2025 ProCut: LLM Prompt Compression via Attribution Estimation EMNLP 2025 ProcWorld: Benchmarking Large Model Planning in Reachability-Constrained Environments EMNLP 2025 Product of Experts with LLMs: Boosting Performance on ARC Is a Matter of Perspective ICML 2025 Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis EMNLP 2025 Profiling News Media for Factuality and Bias Using LLMs and the Fact-Checking Methodology of Human Experts ACL 2025 ProgCo: Program Helps Self-Correction of Large Language Models ACL 2025 Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale ICML 2025