Interpretability

Better Call CLAUSE: A Discrepancy Benchmark for Auditing LLMs Legal Reasoning Capabilities EACL 2026 Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks AAAI 2026 Beyond I’m Sorry, I Can’t: Dissecting Large-Language-Model Refusal AAAI 2026 Beyond Math: Stories as a Testbed for Memorization-Constrained Reasoning in LLMs EACL 2026 Beyond Multiple Choice: Evaluating Steering Vectors for Summarization EACL 2026 Beyond Neuron-Level Sparsity: Achieving Faithful and Interpretable LLMs with Mixture of Decoders AAAI 2026 Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions AAAI 2026 Beyond Patches: Mining Interpretable Part-Prototypes for Explainable AI AAAI 2026 Beyond Plain Demos: A Demo-Centric Anchoring Paradigm for In-Context Learning in Alzheimer’s Disease Detection AAAI 2026 Beyond Single-View Detection: A Dual-Space Reasoning Framework for Interpretable Harmful Meme Understanding ACL 2026 Beyond the Black Box: Demystifying Multi-Turn LLM Reasoning with VISTA AAAI 2026 Beyond the Global Scores: Fine-Grained Token Grounding as a Robust Detector of LVLM Hallucinations CVPR 2026 Beyond the Token: Correcting the Tokenization Bias in XAI via Morphologically-Aligned Projection EACL 2026 Beyond Top Activations: Efficient and Reliable Crowdsourced Evaluation of Automated Interpretability CVPR 2026 Beyond Transcription: Mechanistic Interpretability in ASR AAAI 2026 Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-Sorts ACL 2026 Beyond Verdicts: Evaluating Language Model Moral Competence AAAI 2026 Beyond World Models: Rethinking Understanding in AI Models AAAI 2026 Bias in the Ear of the Listener: Assessing Sensitivity in Audio Language Models Across Linguistic, Demographic, and Positional Variations EACL 2026 Bi-ICE: An Inner Interpretable Framework for Image Classification via Bi-directional Interactions between Concept and Input Embeddings WACV 2026 BLM-Guard: Explainable Multimodal Ad Moderation with Chain-of-Thought and Policy-Aligned Rewards AAAI 2026 Bonsai: Interpretable Tree-Adaptive Grounded Reasoning AAAI 2026 BrainHGT: A Hierarchical Graph Transformer for Interpretable Brain Network Analysis AAAI 2026 BrainLMM: A Label-Free Framework for Mapping Multi-Semantic Representation in the Human Visual Cortex AAAI 2026 Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models EACL 2026