faithful explanation

Actionable Interpretability for Churn Classification: A Text Bottleneck Model Case Study at a Major Telecom Provider ACL 2026 Emotion-Coherent Reasoning for Multimodal LLMs via Emotional Rationale Verifier AAAI 2026 FaithLM: Towards Faithful Explanations for Large Language Models EACL 2026 Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization ACL 2026 Making Sense of LLM Decisions: A Prototype-based Framework for Explainable Classification AAAI 2026 REFLEX: Self-Refining Explainable Fact-Checking via Verdict-Anchored Style Control ACL 2026 Rounded or Streamlined Head? Bridging Concept Bottleneck Models and Attribute-Described Object Parts CVPR 2026 Bridging the Faithfulness Gap in Prototypical Models NAACL 2025 Drift: Enhancing LLM Faithfulness in Rationale Generation via Dual-Reward Probabilistic Inference ACL 2025 EMaP: Explainable AI with Manifold-based Perturbations JMLR 2025 Graph-Guided Textual Explanation Generation Framework EMNLP 2025 Higher Order Structures for Graph Explanations AAAI 2025 Models That Are Interpretable But Not Transparent AISTATS 2025 Multi-Level Explanations for Generative Language Models ACL 2025 Soft Local Completeness: Rethinking Completeness in XAI ICCV 2025 Zero-Shot Natural Language Explanations ICLR 2025 Atomic Inference for NLI with Generated Facts as Atoms EMNLP 2024 DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation ICML 2024 Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals ICLR 2024 Sparse and Faithful Explanations Without Sparse Models AISTATS 2024 Towards Faithful Knowledge Graph Explanation Through Deep Alignment in Commonsense Question Answering EMNLP 2024 Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQA AAAI 2024 Wrapper Boxes for Faithful Attribution of Model Predictions to Training Data EMNLP 2024 DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications ACL 2023 Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability NeurIPS 2023