Interpretability

Analyzing the Rapid Generalization of SFT via the Perspective of Attention Head Activation Patterns ACL 2025 AnCast++: Document-Level Evaluation of Graph-based Meaning Representations ACL 2025 Anchored Answers: Unravelling Positional Bias in GPT-2’s Multiple-Choice Questions ACL 2025 A Necessary Step toward Faithfulness: Measuring and Improving Consistency in Free-Text Explanations EMNLP 2025 An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4 ACL 2025 An Engorgio Prompt Makes Large Language Model Babble on ICLR 2025 A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability ICML 2025 An Exploration of Interpretable Deep Learning Models for the Assessment of Mild Cognitive Impairment Interspeech 2025 Animate Your Thoughts: Reconstruction of Dynamic Natural Vision from Human Brain Activity ICLR 2025 An in-depth human study of the mathematical reasoning abilities in Large Language Models EMNLP 2025 An Interpretable and Crosslingual Method for Evaluating Second-Language Dialogues NAACL 2025 An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks ICML 2025 An interpretable speech foundation model for depression detection by revealing prediction-relevant acoustic features from long speech Interspeech 2025 A Novel GNN Framework Integrating Neuroimaging and Behavioral Information to Understand Adolescent Psychiatric Disorders MIDL 2025 Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions ICLR 2025 Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception CVPR 2025 An XAI Social Media Platform for Teaching K-12 Students AI-Driven Profiling, Clustering, and Engagement-Based Recommending AAAI 2025 Any-Resolution AI-Generated Image Detection by Spectral Learning CVPR 2025 Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence ICLR 2025 Approximating Latent Manifolds in Neural Networks via Vanishing Ideals ICML 2025 A Practical Method for Generating String Counterfactuals NAACL 2025 A Probabilistic Framework for LLM Hallucination Detection via Belief Tree Propagation NAACL 2025 AraEval: An Arabic Multi-Task Evaluation Suite for Large Language Models EMNLP 2025 AraHalluEval: A Fine-grained Hallucination Evaluation Framework for Arabic LLMs EMNLP 2025 Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models ICML 2025