Interpretability

Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty EMNLP 2025 Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector CVPR 2025 Rethinking Visual Counterfactual Explanations Through Region Constraint ICLR 2025 Retrieval Head Mechanistically Explains Long-Context Factuality ICLR 2025 Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models ACL 2025 Retrieve to Explain: Evidence-driven Predictions for Explainable Drug Target Identification ACL 2025 Revealing and Mitigating Over-Attention in Knowledge Editing ICLR 2025 Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing EMNLP 2025 Revealing Hidden Mechanisms of Cross-Country Content Moderation with Natural Language Processing ACL 2025 Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing ACL 2025 Revealing the Unwritten: Visual Investigation of Beam Search Trees to Address Language Model Prompting Challenges ACL 2025 Revelio: Interpreting and leveraging semantic information in diffusion models ICCV 2025 Reversed Attention: On The Gradient Descent Of Attention Layers In GPT NAACL 2025 Reverse Question Answering: Can an LLM Write a Question so Hard (or Bad) that it Can’t Answer? NAACL 2025 Reverse Region-to-Entity Annotation for Pixel-Level Visual Entity Linking AAAI 2025 REVISE: A Framework for Revising OCRed text in Practical Information Systems with Data Contamination Strategy ACL 2025 Revisiting Adversarial Patch Defenses on Object Detectors: Unified Evaluation, Large-Scale Dataset, and New Insights ICCV 2025 Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models’ Uncertainty? ACL 2025 Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective COLING 2025 Revisiting LLM Value Probing Strategies: Are They Robust and Expressive? EMNLP 2025 Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results ACL 2025 REVIVING YOUR MNEME: Predicting The Side Effects of LLM Unlearning and Fine-Tuning via Sparse Model Diffing EMNLP 2025 Rewarding Explainability in Drug Repurposing with Knowledge Graphs IJCAI 2025 ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniques AAAI 2025 Riemannian-Geometric Fingerprints of Generative Models ICCV 2025