Interpretability

From Disagreement to Understanding: The Case for Ambiguity Detection in NLI EMNLP 2025 From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge EMNLP 2025 From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networks ICLR 2025 From Imitation to Innovation: The Emergence of AI's Unique Artistic Styles and the Challenge of Copyright Protection ICCV 2025 From Imitation to Introspection: Probing Self-Consciousness in Language Models ACL 2025 From Input Perception to Predictive Insight: Modeling Model Blind Spots Before They Become Errors EMNLP 2025 From Insight to Exploit: Leveraging LLM Collaboration for Adaptive Adversarial Text Generation EMNLP 2025 From Keyterms to Context: Exploring Topic Description Generation in Scientific Corpora EMNLP 2025 From Language to Cognition: How LLMs Outgrow the Human Language Network EMNLP 2025 From Lists to Emojis: How Format Bias Affects Model Alignment ACL 2025 From Mechanistic Interpretability to Mechanistic Biology: Training, Evaluating, and Interpreting Sparse Autoencoders on Protein Language Models ICML 2025 From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic Reasoning ICCV 2025 From Parameters to Performance: A Data-Driven Study on LLM Structure and Development EMNLP 2025 From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection ICML 2025 From Prejudice to Parity: A New Approach to Debiasing Large Language Model Word Embeddings COLING 2025 From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models EMNLP 2025 From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks NAACL 2025 From Regulation to Interaction: Expert Views on Aligning Explainable AI with the EU AI Act EMNLP 2025 From Search to Sampling: Generative Models for Robust Algorithmic Recourse ICLR 2025 From Shortcuts to Balance: Attribution Analysis of Speech-Text Feature Utilization in Distinguishing Original from Machine-Translated Texts EMNLP 2025 From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs NAACL 2025 From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval EMNLP 2025 From Visual Explanations to Counterfactual Explanations with Latent Diffusion WACV 2025 From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models Interspeech 2025 Functional Alignment Can Mislead: Examining Model Stitching ICML 2025