Interpretability

AIM: Amending Inherent Interpretability via Self-Supervised Masking ICCV 2025 A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning IJCAI 2025 AIRepr: An Analyst-Inspector Framework for Evaluating Reproducibility of LLMs in Data Science EMNLP 2025 A Knowledge Distillation-Based Approach to Enhance Transparency of Classifier Models AAAI 2025 Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race ACL 2025 Aligning Constraint Generation with Design Intent in Parametric CAD ICCV 2025 Aligning Large Language Models with Human Opinions through Persona Selection and Value–Belief–Norm Reasoning COLING 2025 Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations EMNLP 2025 ALiiCE: Evaluating Positional Fine-grained Citation Generation NAACL 2025 All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens EMNLP 2025 All Roads Lead to Rome: Graph-Based Confidence Estimation for Large Language Model Reasoning EMNLP 2025 Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing ACL 2025 A Logic of General Attention Using Edge-Conditioned Event Models IJCAI 2025 Ambiguity and Disagreement in Abstract Meaning Representation COLING 2025 Ambiguity Detection and Uncertainty Calibration for Question Answering with Large Language Models NAACL 2025 A.M.P at SciHal2025: Automated Hallucination Detection in Scientific Content via LLMs and Prompt Engineering ACL 2025 Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation? EMNLP 2025 Analytical Lyapunov Function Discovery: An RL-based Generative Approach ICML 2025 Analyze Feature Flow to Enhance Interpretation and Steering in Language Models ICML 2025 Analyzing Finetuning Representation Shift for Multimodal LLMs Steering ICCV 2025 Analyzing (In)Abilities of SAEs via Formal Languages NAACL 2025 Analyzing Memorization in Large Language Models through the Lens of Model Attribution NAACL 2025 Analyzing Political Bias in LLMs via Target-Oriented Sentiment Classification ACL 2025 Analyzing the Attention Heads for Pronoun Disambiguation in Context-aware Machine Translation Models COLING 2025 Analyzing the Inner Workings of Transformers in Compositional Generalization NAACL 2025