Interpretability

Induction Heads as an Essential Mechanism for Pattern Matching in In-context Learning NAACL 2025 Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models ICML 2025 Inferring Functionality of Attention Heads from their Parameters ACL 2025 Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models NAACL 2025 Information-theoretic Distinctions Between Deception and Confusion IJCNLP 2025 Inherent and emergent liability issues in LLM-based agentic systems: a principal-agent perspective ACL 2025 Inner Information Analysis Algorithm for Deep Neural Network based on Community ICLR 2025 Input Space Mode Connectivity in Deep Neural Networks ICLR 2025 In Search of Trees: Decision-Tree Policy Synthesis for Black-Box Systems via Search AAAI 2025 Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct ICLR 2025 InstaJudge: Aligning Judgment Bias of LLM-as-Judge with Humans in Industry Applications EMNLP 2025 InstaSHAP: Interpretable Additive Models Explain Shapley Values Instantly ICLR 2025 InteDisUX: Intepretation-Guided Discriminative User-Centric Explanation for Time Series AAAI 2025 Integrative Decoding: Improving Factuality via Implicit Self-consistency ICLR 2025 Intention Analysis Makes LLMs A Good Jailbreak Defender COLING 2025 Interactive Medical Image Analysis with Concept-based Similarity Reasoning CVPR 2025 Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment ICLR 2025 Interlocking-free Selective Rationalization Through Genetic-based Learning ACL 2025 INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling ICCV 2025 Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors ICML 2025 Internal Chain-of-Thought: Empirical Evidence for Layer‐wise Subtask Scheduling in LLMs EMNLP 2025 Internal states before wait modulate reasoning patterns EMNLP 2025 Internal Value Alignment in Large Language Models through Controlled Value Vector Activation ACL 2025 Interpolating Neural Network-Tensor Decomposition (INN-TD): a scalable and interpretable approach for large-scale physics-based problems ICML 2025 Interpretability Analysis of Arithmetic In-Context Learning in Large Language Models EMNLP 2025