Interpretability

Region-Level Data Attribution for Text-to-Image Generative Models ICCV 2025 Regretful Decisions under Label Noise ICLR 2025 Reinforced Learning Explicit Circuit Representations for Quantum State Characterization from Local Measurements ICML 2025 RelationalCoder: Rethinking Complex Tables via Programmatic Relational Transformation ACL 2025 Reliability Crisis of Reference-free Metrics for Grammatical Error Correction EMNLP 2025 Reliable and Scalable Variable Importance Estimation via Warm-start and Early Stopping AISTATS 2025 Reliable Uncertainty Quantification in Machine Learning via Conformal Prediction AAAI 2025 REPEAT: Improving Uncertainty Estimation in Representation Learning Explainability AAAI 2025 Repetition Neurons: How Do Language Models Produce Repetitions? NAACL 2025 Representational Similarity via Interpretable Visual Concepts ICLR 2025 Representations of Fact, Fiction and Forecast in Large Language Models: Epistemics and Attitudes ACL 2025 Representing and Clustering Errors in Offensive Language Detection NAACL 2025 Reproducing the Argument Quality Prediction of Project Debater ACL 2025 ReproHum #0031-01: Reproducing the Human Evaluation of Readability from “It is AI’s Turn to Ask Humans a Question” ACL 2025 ReproHum #0729-04: Human Evaluation Reproduction Report for “MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes” ACL 2025 ReproHum #0744-02: A Reproduction of the Human Evaluation of Meaning Preservation in “Factorising Meaning and Form for Intent-Preserving Paraphrasing” ACL 2025 Residualized Similarity for Faithfully Explainable Authorship Verification EMNLP 2025 Residual Stream Analysis with Multi-Layer SAEs ICLR 2025 Restyling Unsupervised Concept Based Interpretable Networks with Generative Models ICLR 2025 ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuning EMNLP 2025 Rethinking and Improving Autoformalization: Towards a Faithful Metric and a Dependency Retrieval-based Approach ICLR 2025 Rethinking Backdoor Detection Evaluation for Language Models EMNLP 2025 Rethinking Diverse Human Preference Learning through Principal Component Analysis ACL 2025 Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approach CVPR 2025 Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words ICLR 2025