Interpretability

THCM-CAL: Temporal-Hierarchical Causal Modelling with Conformal Calibration for Clinical Risk Prediction EMNLP 2025 The AI Co-Ethnographer: How Far Can Automation Take Qualitative Research? NAACL 2025 The Anatomy of Evidence: An Investigation Into Explainable ICD Coding ACL 2025 The Art of Deception: Color Visual Illusions and Diffusion Models CVPR 2025 The Benefits of Being Uncertain: Perplexity as a Signal for Naturalness in Multilingual Machine Translation EMNLP 2025 The Computational Complexity of Circuit Discovery for Inner Interpretability ICLR 2025 The Confidence Paradox: Can LLM Know When It’s Wrong? IJCNLP 2025 The Delta of Thought: Channeling Rivers of Commonsense Knowledge in the Sea of Metaphorical Interpretations IJCAI 2025 The discordance between embedded ethics and cultural inference in large language models EMNLP 2025 The Geometry of Categorical and Hierarchical Concepts in Large Language Models ICLR 2025 The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence ICML 2025 The Good, the Bad and the Constructive: Automatically Measuring Peer Review’s Utility for Authors EMNLP 2025 The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions ICML 2025 The Illusion of Progress: Re-evaluating Hallucination Detection in LLMs EMNLP 2025 The Impact of Negated Text on Hallucination with Large Language Models EMNLP 2025 The Knowledge Microscope: Features as Better Analytical Lenses than Neurons ACL 2025 The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination ACL 2025 The Limits of Predicting Agents from Behaviour ICML 2025 The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units NAACL 2025 Theorem-of-Thought: A Multi-Agent Framework for Abductive, Deductive, and Inductive Reasoning in Language Models ACL 2025 Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoning EMNLP 2025 The Progress Illusion: Revisiting meta-evaluation standards of LLM evaluators EMNLP 2025 The Reader is the Metric: How Textual Features and Reader Profiles Explain Conflicting Evaluations of AI Creative Writing ACL 2025 The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction ACL 2025 There’s No Such Thing as Simple Reasoning for LLMs ACL 2025