model interpretability

An Empirical Study on How Video-LLMs Answer Video Questions CVPR 2026 Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models CVPR 2026 Beyond Multiple Choice: Evaluating Steering Vectors for Summarization EACL 2026 Building a Bridge Between the Shapley Value, Prime Implicants and Counterfactual Explanations: a Theoretical Analysis UAI 2026 Can You Trust Your Model? Constructing Uncertainty Approximations Guaranteeing Validity of Glioma Segmentation Explanations MIDL 2026 ConsensusXAI: A Framework to Examine Class-wise Agreement in Medical Imaging WACV 2026 Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining ACL 2026 Decomposing Direct and Indirect Biases in Linear Models Under Demographic Parity Constraint (Student Abstract) AAAI 2026 Deconstructing Instruction-Following: A New Benchmark for Granular Evaluation of Large Language Model Instruction Compliance Abilities EACL 2026 DeformAR: A Visual Analytics Framework for Evaluation of Arabic Named Entity Recognition EACL 2026 Digital Forensic AI You Can Explain: A Case Study on Video Source Camera Identification WACV 2026 Exact Shapley Attributions in Quadratic-time for FANOVA Gaussian Processes AAAI 2026 Explanations for Sequential Decision-Making – an Overview AAAI 2026 Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs AAAI 2026 From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition CVPR 2026 Improving Implicit Discourse Relation Recognition with Natural Language Explanations from LLMs AAAI 2026 Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation ACL 2026 Interpreto: An Explainability Library for Transformers ACL 2026 Learning-Augmented Heuristics: Simple Yet Smart, Robust and Interpretable Cache Eviction OSDI 2026 Learning complete and explainable visual representations from itemized text supervision CVPR 2026 LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-step Arithmetics EACL 2026 Make it SING: Analyzing Semantic Invariants in Classifiers CVPR 2026 PRISMA: Preference-Reinforced Self-Training Approach for Interpretable Emotionally Intelligent Negotiation Dialogues ACL 2026 Punctuations and Predicates in Language Models EACL 2026 Select, Hypothesize and Verify: Towards Verified Neuron Concept Interpretation CVPR 2026