Interpretability

PRAGWORLD: A Benchmark Evaluating LLMs’ Local World Model Under Minimal Linguistic Alterations and Conversational Dynamics AAAI 2026 Preference Elicitation for Step-Wise Explanations in Logic Puzzles AAAI 2026 Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization ACL 2026 PRISM: Prototype-based Reasoning with Inter-modal Semantic Mining for Interpretable Image Recognition CVPR 2026 Privacy-Preserving Argumentative Explanations (Student Abstract) AAAI 2026 Probabilistic Safety Verification of Neural Policies via Predicate Abstraction AAAI 2026 Probing Bias Formation in Medical LLMs through Activation Steering ACL 2026 Probing for Reading Times ACL 2026 Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models AAAI 2026 Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification ACL 2026 ProtoGMVAE: A Variational Auto-Encoder with True Gaussian Mixture Prior for Prototypical-based Self-Explainability WACV 2026 ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders AAAI 2026 psy detectives at SemEval-2026 Task 10: PsyCoMark – Psycholinguistic Conspiracy Marker Extraction and Detection SemEval 2026 Punctuations and Predicates in Language Models EACL 2026 Quantitative Lect Description: A Case Study of Lemko from the Field Data of 1920s-1930s EACL 2026 Query-Routed Activation Editing with Truth-hierarchical Preference Optimization AAAI 2026 QuMAB: Query-based Multi-annotator Behavior Pattern Learning AAAI 2026 RADAR: A Reasoning-Guided Attribution Framework for Explainable Visual Data Analysis EACL 2026 RAFFLES: Reasoning-based Attribution of Faults for LLM Systems EACL 2026 RAGVUE: A Diagnostic View for Explainable and Automated Evaluation of Retrieval-Augmented Generation EACL 2026 Realist and Pluralist Conceptions of Intelligence and Their Implications on AI Research AAAI 2026 REALITrees: Rashomon Ensemble Active Learning for Interpretable Trees UAI 2026 Reallocating Attention Across Layers to Reduce Multimodal Hallucination CVPR 2026 Reasoning about Uncertainty: Do Reasoning Models Know When They Don’t Know? EACL 2026 Reasoning Fails Where Step Flow Breaks ACL 2026