llms

AAAR-1.0: Assessing AI’s Potential to Assist Research ICML 2025 Aligning LLMs by Predicting Preferences from User Writing Samples ICML 2025 am-ELO: A Stable Framework for Arena-based LLM Evaluation ICML 2025 any4: Learned 4-bit Numeric Representation for LLMs ICML 2025 AnyEdit: Edit Any Knowledge Encoded in Language Models ICML 2025 A Reasoning-Based Approach to Cryptic Crossword Clue Solving ICML 2025 Automated Red Teaming with GOAT: the Generative Offensive Agent Tester ICML 2025 Automatically Interpreting Millions of Features in Large Language Models ICML 2025 CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance ICML 2025 Compositional Condition Question Answering in Tabular Understanding ICML 2025 DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy ICML 2025 Discovering Symbolic Cognitive Models from Human and Animal Behavior ICML 2025 DiscQuant: A Quantization Method for Neural Networks Inspired by Discrepancy Theory COLT 2025 DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs ICML 2025 Does Domain-Specific Retrieval Augmented Generation Help LLMs Answer Consumer Health Questions? MLHC 2025 Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition ICML 2025 Exploiting Presentative Feature Distributions for Parameter-Efficient Continual Learning of Large Language Models ICML 2025 FactEHR: A Dataset for Evaluating Factuality in Clinical Notes Using LLMs MLHC 2025 FlatQuant: Flatness Matters for LLM Quantization ICML 2025 FlipAttack: Jailbreak LLMs via Flipping ICML 2025 From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline ICML 2025 From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set ICML 2025 From Local Details to Global Context: Advancing Vision-Language Models with Attention-Based Selection ICML 2025 Function-to-Style Guidance of LLMs for Code Translation ICML 2025 How Much Can We Forget about Data Contamination? ICML 2025