Interpretability

Precise In-Parameter Concept Erasure in Large Language Models EMNLP 2025 Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs ICLR 2025 Prediction models that learn to avoid missing values ICML 2025 Prediction via Shapley Value Regression ICML 2025 Predictive Modeling of Human Developers’ Evaluative Judgment of Generated Code as a Decision Process EMNLP 2025 Preemptive Detection and Correction of Misaligned Actions in LLM Agents EMNLP 2025 Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance EMNLP 2025 Priority Guided Explanation for Knowledge Tracing with Dual Ranking and Similarity Consistency IJCAI 2025 PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-Encoder ACL 2025 PrivateEye: In-Sensor Privacy Preservation Through Optical Feature Separation WACV 2025 Probabilistic Explanations for Linear Models AAAI 2025 Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models ICLR 2025 Probe-Free Low-Rank Activation Intervention NAACL 2025 Probing and Boosting Large Language Models Capabilities via Attention Heads EMNLP 2025 Probing for Arithmetic Errors in Language Models EMNLP 2025 Probing Internal Representations of Multi-Word Verbs in Large Language Models NAACL 2025 Probing LLM World Models: Enhancing Guesstimation with Wisdom of Crowds Decoding EMNLP 2025 Probing Narrative Morals: A New Character-Focused MFT Framework for Use with Large Language Models EMNLP 2025 Probing Political Ideology in Large Language Models: How Latent Political Representations Generalize Across Tasks EMNLP 2025 Probing Subphonemes in Morphology Models ACL 2025 Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks ACL 2025 Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models ICLR 2025 Processing and acquisition traces in visual encoders: What does CLIP know about your camera? ICCV 2025 ProcTag: Process Tagging for Assessing the Efficacy of Document Instruction Data AAAI 2025 Prof. Robot: Differentiable Robot Rendering Without Static and Self-Collisions CVPR 2025