causal mediation analysis

Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection CVPR 2026 Fixed-Confidence Best-Arm Identification for Causal Mediation Analysis UAI 2026 Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization ACL 2026 Mechanisms of Object Localization in Vision-Language Models CVPR 2026 Patches of Nonlinearity: Instruction Vectors in Large Language Models ACL 2026 Understanding Counting Mechanisms in Large Language and Vision-Language Models CVPR 2026 Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension ability ICLR 2025 CodeSCM: Causal Analysis for Multi-Modal Code Generation NAACL 2025 Decomposition of Probabilities of Causation with Two Mediators UAI 2025 SHA256 at SemEval-2025 Task 4: Selective Amnesia – Constrained Unlearning for Large Language Models via Knowledge Isolation SemEval 2025 Telling Peer Direct Effects from Indirect Effects in Observational Network Data ICML 2025 Understanding and Mitigating Hallucination in Large Vision-Language Models via Modular Attribution and Intervention ICLR 2025 CMA-R: Causal Mediation Analysis for Explaining Rumour Detection EACL 2024 Deciphering the Interplay of Parametric and Non-parametric Memory in Retrieval-augmented Language Models EMNLP 2024 Function Vectors in Large Language Models ICLR 2024 Identifying and Mitigating Annotation Bias in Natural Language Understanding using Causal Mediation Analysis ACL 2024 Images Speak Louder than Words: Understanding and Mitigating Bias in Vision-Language Model from a Causal Mediation Perspective EMNLP 2024 Localizing and Editing Knowledge In Text-to-Image Generative Models ICLR 2024 Locating and Extracting Relational Concepts in Large Language Models ACL 2024 Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning EMNLP 2024 A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis EMNLP 2023 Disentangled Representation for Causal Mediation Analysis AAAI 2023 Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model EMNLP 2023 Rigorously Assessing Natural Language Explanations of Neurons EMNLP 2023 DeepMed: Semiparametric Causal Mediation Analysis with Debiased Deep Learning NeurIPS 2022