Interpretability

Is the Top Still Spinning? Evaluating Subjectivity in Narrative Understanding EMNLP 2025 Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs ICML 2025 Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist ICLR 2025 Is Your Video Language Model a Reliable Judge? ICLR 2025 Iterative Learning of Computable Phenotypes for Treatment Resistant Hypertension using Large Language Models MLHC 2025 It Helps to Take a Second Opinion: Teaching Smaller LLMs To Deliberate Mutually via Selective Rationale Optimisation ICLR 2025 “I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents EMNLP 2025 Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations ICML 2025 Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models ICLR 2025 Joint Enhancement of Relational Reasoning for Long-Context LLMs EMNLP 2025 Joint Localization and Activation Editing for Low-Resource Fine-Tuning ICML 2025 JoPA: Explaining Large Language Model’s Generation via Joint Prompt Attribution ACL 2025 Judge and Improve: Towards a Better Reasoning of Knowledge Graphs with Large Language Models EMNLP 2025 Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models ACL 2025 JudgeBench: A Benchmark for Evaluating LLM-Based Judges ICLR 2025 JUDGEBERT: Assessing Legal Meaning Preservation Between Sentences EMNLP 2025 Judging It, Washing It: Scoring and Greenwashing Corporate Climate Disclosures using Large Language Models ACL 2025 Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge IJCNLP 2025 JU_NLP at SemEval-2025 Task 7: Leveraging Transformer-Based Models for Multilingual & Crosslingual Fact-Checked Claim Retrieval SemEval 2025 JUREX-4E: Juridical Expert-Annotated Four-Element Knowledge Base for Legal Reasoning EMNLP 2025 keepitsimple at SemEval-2025 Task 3: LLM-Uncertainty based Approach for Multilingual Hallucination Span Detection SemEval 2025 Keys to Robust Edits: From Theoretical Insights to Practical Advances ACL 2025 KLAAD: Refining Attention Mechanisms to Reduce Societal Bias in Generative Language Models EMNLP 2025 Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion ACL 2025 Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language Models ACL 2025