Interpretability

Conditional Probabilistic Bipolar Argumentation Framework: Explanations, Complexity and Approximation AAAI 2026 Confidence Estimation for Text-to-SQL in Large Language Models AAAI 2026 Confidence Leaps in LLM Reasoning: Early Stopping and Cross-Model Transfer EACL 2026 ConsensusXAI: A Framework to Examine Class-wise Agreement in Medical Imaging WACV 2026 Constructing Interpretable Features from Compositional Neuron Groups ACL 2026 Continual Out-of-Distribution Detection with Analytic Neural Collapse AAAI 2026 Continuous Interpretive Steering for Scalar Diversity ACL 2026 Contrastive Integrated Gradients: A Feature Attribution-Based Method for Explaining Whole Slide Image Classification WACV 2026 Control Illusion: The Failure of Instruction Hierarchies in Large Language Models AAAI 2026 Controllable Epistemic Sensitivity in Large Language Models: Probing, Benchmarking, and Adaptive Reasoning AAAI 2026 Controllable LLM Reasoning via Sparse Autoencoder-Based Steering ACL 2026 Convergent Demographic Utility Hierarchies: Geometry of Intersectional Values in LLMs ACL 2026 Council of LLMs: Evaluating Capability of Large Language Models to Annotate Propaganda EACL 2026 Counterfactual eXplainable AI (XAI) Method for Deep Learning-Based Multivariate Time Series Classification AAAI 2026 Credal Concept Bottleneck Models for Epistemic–Aleatoric Uncertainty Decomposition ACL 2026 Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining ACL 2026 CTX-Coder: Cross-Attention Architectures Empower LLMs for Long-Context Vulnerability Detection AAAI 2026 DAMASHA: Detecting AI in Mixed Adversarial Texts via Segmentation with Human-interpretable Attribution EACL 2026 DARC: Dual Adjustment Reasoning with Counterfactuals for Trustworthy Chest X-ray Classification CVPR 2026 Debate, Deliberate, Decide (D3): A Cost-Aware Adversarial Framework for Reliable and Interpretable LLM Evaluation EACL 2026 Debiasing Reward Models via Causally Motivated Inference-Time Intervention ACL 2026 Deconstructing Instruction-Following: A New Benchmark for Granular Evaluation of Large Language Model Instruction Compliance Abilities EACL 2026 DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHF AAAI 2026 Decoupling Knowledge and Reasoning in LLMs: An Exploration Using Cognitive Dual-System Theory AAAI 2026 Deep Learning for Liver Disease Stratification: Findings from UKBB MRI MIDL 2026