Interpretability

AttriBoT: A Bag of Tricks for Efficiently Approximating Leave-One-Out Context Attribution ICLR 2025 Attribute-formed Class-specific Concept Space: Endowing Language Bottleneck Model with Better Interpretability and Scalability CVPR 2025 Attributes Shape the Embedding Space of Face Recognition Models ICML 2025 Attributing Culture-Conditioned Generations to Pretraining Corpora ICLR 2025 Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit AAAI 2025 Attribution and Application of Multiple Neurons in Multimodal Large Language Models EMNLP 2025 Attributive Reasoning for Hallucination Diagnosis of Large Language Models AAAI 2025 Audio-Aware Large Language Models as Judges for Speaking Styles EMNLP 2025 AudioGenX: Explainability on Text-to-Audio Generative Models AAAI 2025 Auditing Political Bias in Text Generation by GPT-4 using Sociocultural and Demographic Personas: Case of Bengali Ethnolinguistic Communities AACL 2025 Auditing Prompt Caching in Language Model APIs ICML 2025 AutoBencher: Towards Declarative Benchmark Construction ICLR 2025 AutoCT: Automating Interpretable Clinical Trial Prediction with LLM Agents EMNLP 2025 Autoformalizing Natural Language to First-Order Logic: A Case Study in Logical Fallacy Detection IJCNLP 2025 Automated Claim–Evidence Extraction for Political Discourse Analysis: A Large Language Model Approach to Rodong Sinmun Editorials ACL 2025 Automated, Interpretable, and Scalable Scientific Machine Learning AAAI 2025 Automated Molecular Concept Generation and Labeling with Large Language Models COLING 2025 Automated Proof Generation for Rust Code via Self-Evolution ICLR 2025 Automatically Interpreting Millions of Features in Large Language Models ICML 2025 AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment EMNLP 2025 A Variational Information Theoretic Approach to Out-of-Distribution Detection ICML 2025 A Versatile Influence Function for Data Attribution with Non-Decomposable Loss ICML 2025 Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts ICML 2025 AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders ICML 2025 Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models EMNLP 2025