Interpretability

Reasoning’s Razor: Reasoning Improves Accuracy but Hurts Recall at Critical Operating Points in Safety and Hallucination Detection EACL 2026 Reasoning Traces Shape Outputs but Models Won’t Say So ACL 2026 RECoRD: A Multi-Agent LLM Framework for Reverse Engineering Codebase to Relational Diagram AAAI 2026 Recursive numeral systems are highly regular and easy to process EACL 2026 ReFINE: A Reward-Based Framework for Interpretable and Nuanced Evaluation of Radiology Report Generation AAAI 2026 REMIND: Memorization and Unlearning in LLMs Through the Lens of Input Loss Landscapes ACL 2026 Res-Bench: Benchmarking the Robustness of Multimodal Large Language Models to Dynamic Resolution Input AAAI 2026 Rethinking Concept Bottleneck Models: From Pitfalls to Solutions CVPR 2026 Rethinking Explanation Evaluation Under the Retraining Scheme AAAI 2026 Rethinking Saliency Maps: A Cognitive Human Aligned Taxonomy and Evaluation Framework for Explanations AAAI 2026 RetouchAgent: Towards Interactive and Explainable Image Retouching with MLLM Agents AAAI 2026 Retrieval Heads are Dynamic ACL 2026 Revealing Procedural Reasoning Structures in Chain-of-Thought Training via Span-Level Gradient Organization ACL 2026 Revealing Redundant Syntax in Large Language Models through Multi-Hop Dependency Paths EACL 2026 Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models ACL 2026 RFI: Rectified Flow Intervention for Mitigating Object Hallucination in Large Vision-Language Models AAAI 2026 Rhetorical Questions in LLM Representations: A Linear Probing Study ACL 2026 Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding AAAI 2026 RotBench: Evaluating Multi-modal Large Language Models on Identifying Image Rotation EACL 2026 Rounded or Streamlined Head? Bridging Concept Bottleneck Models and Attribute-Described Object Parts CVPR 2026 RPTS: Tree-Structured Reasoning Process Scoring for Faithful Multimodal Evaluation AAAI 2026 Runtime Safety and Reach-avoid Prediction of Stochastic Systems via Observation-aware Barrier Functions AAAI 2026 RV-HATE: Reinforced Multi-Module Voting for Implicit Hate Speech Detection ACL 2026 S³-MSD: Large Vision-Language Model for Explainable and Generalizable Multi-modal Sarcasm Detection AAAI 2026 Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis ACL 2026