Interpretability

RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation ICML 2025 Robust Native Language Identification through Agentic Decomposition EMNLP 2025 RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs ACL 2025 Route Sparse Autoencoder to Interpret Large Language Models EMNLP 2025 RPMIL: Rethinking Uncertainty-Aware Probabilistic Multiple Instance Learning for Whole Slide Pathology Diagnosis IJCAI 2025 RRInf: Efficient Influence Function Estimation via Ridge Regression for Large Language Models and Text-to-Image Diffusion Models EMNLP 2025 RuAG: Learned-rule-augmented Generation for Large Language Models ICLR 2025 Rubrik’s Cube: Testing a New Rubric for Evaluating Explanations on the CUBE dataset ACL 2025 RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios ACL 2025 Rule-Guided Graph Neural Networks for Explainable Knowledge Graph Reasoning AAAI 2025 Rule-Guided Reinforcement Learning Policy Evaluation and Improvement IJCAI 2025 Run Like a Neural Network, Explain Like k-Nearest Neighbor IJCAI 2025 SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization EMNLP 2025 SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability ICML 2025 SAEs Are Good for Steering – If You Select the Right Features EMNLP 2025 SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models EMNLP 2025 SAE-V: Interpreting Multimodal Models for Enhanced Alignment ICML 2025 SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs EMNLP 2025 Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification ACL 2025 SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning EMNLP 2025 SafeQuant: LLM Safety Analysis via Quantized Gradient Inspection NAACL 2025 SafetyAnalyst: Interpretable, Transparent, and Steerable Safety Moderation for AI Behavior ICML 2025 Safety Layers in Aligned Large Language Models: The Key to LLM Security ICLR 2025 SAFR: Neuron Redistribution for Interpretability NAACL 2025 SAGI: Semantically Aligned and Uncertainty Guided AI Image Inpainting ICCV 2025