Interpretability

Quality-Informed Segment-Level Error Correction Using Natural Language Explanations from xTower and Large Language Models EMNLP 2025 Quantifying Generalization Complexity for Large Language Models ICLR 2025 Quantifying Knowledge Distillation using Partial Information Decomposition AISTATS 2025 Quantifying Logical Consistency in Transformers via Query-Key Alignment EMNLP 2025 Quantifying Memory Utilization with Effective State-Size ICML 2025 Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answering EMNLP 2025 Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMs EMNLP 2025 Racing Thoughts: Explaining Contextualization Errors in Large Language Models NAACL 2025 RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs EMNLP 2025 RadEval: A framework for radiology text evaluation EMNLP 2025 RAG-Zeval: Enhancing RAG Responses Evaluator through End-to-End Reasoning and Ranking-Based Reinforcement Learning EMNLP 2025 Randomized Smoothing Meets Vision-Language Models EMNLP 2025 Ranked from Within: Ranking Large Multimodal Models Without Labels ICML 2025 Ranking Over Scoring: Towards Reliable and Robust Automated Evaluation of LLM-Generated Medical Explanatory Arguments COLING 2025 RAP: A Metric for Balancing Repetition and Performance in Open-Source Large Language Models NAACL 2025 Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-Time CVPR 2025 RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals ICML 2025 Rating AI Models for Robustness Through a Causal Lens IJCAI 2025 Rating Roulette: Self-Inconsistency in LLM-As-A-Judge Frameworks EMNLP 2025 Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability ACL 2025 RATT: A Thought Structure for Coherent and Correct LLM Reasoning AAAI 2025 RAVEN++: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoning EMNLP 2025 RCI: A Score for Evaluating Global and Local Reasoning in Multimodal Benchmarks EMNLP 2025 REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing EMNLP 2025 Read Your Own Mind: Reasoning Helps Surface Self-Confidence Signals in LLMs EMNLP 2025