Large Language Models

ParaRev : Building a dataset for Scientific Paragraph Revision annotated with revision instruction COLING 2025 Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging ICML 2025 PARM: Multi-Objective Test-Time Alignment via Preference-Aware Autoregressive Reward Model ICML 2025 Passing the Driving Knowledge Test ICCV 2025 Patent-CR: A Dataset for Patent Claim Revision NAACL 2025 PatentScore: Multi-dimensional Evaluation of LLM-Generated Patent Claims EMNLP 2025 Path Drift in Large Reasoning Models: How First-Person Commitments Override Safety EMNLP 2025 Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline EMNLP 2025 PAT: Pruning-Aware Tuning for Large Language Models AAAI 2025 Pattern Recognition or Medical Knowledge? The Problem with Multiple-Choice Questions in Medicine ACL 2025 PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization EMNLP 2025 PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization NAACL 2025 PCoT: Persuasion-Augmented Chain of Thought for Detecting Fake News and Social Media Disinformation ACL 2025 PDC & DM-SFT: A Road for LLM SQL Bug-Fix Enhancing COLING 2025 PDE-Controller: LLMs for Autoformalization and Reasoning of PDEs ICML 2025 PEACE: Empowering Geologic Map Holistic Understanding with MLLMs CVPR 2025 PEARL: Parallel Speculative Decoding with Adaptive Draft Length ICLR 2025 PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement ACL 2025 PENCIL: Long Thoughts with Short Memory ICML 2025 PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion ICML 2025 Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios NAACL 2025 Perception in Reflection ICML 2025 Performance and Limitations of Fine-Tuned LLMs in SPARQL Query Generation COLING 2025 Peri-LN: Revisiting Normalization Layer in the Transformer Architecture ICML 2025 Periodical Moving Average Accelerates Gradient Accumulation for Post-Training UAI 2025