Interpretability

Towards LLMs Robustness to Changes in Prompt Format Styles NAACL 2025 Towards Multi-Perspective NLP Systems: A Thesis Proposal ACL 2025 Towards Objective Fine-tuning: How LLMs’ Prior Knowledge Causes Potential Poor Calibration? ACL 2025 Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control ICLR 2025 Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration ICML 2025 Towards Robust Influence Functions with Flat Validation Minima ICML 2025 Towards Robust Knowledge Representations in Multilingual LLMs for Equivalence and Inheritance based Consistent Reasoning NAACL 2025 Towards Robustness and Explainability of Automatic Algorithm Selection ICML 2025 Towards Robust Visual Question Answering via Prompt-Driven Geometric Harmonization AAAI 2025 Towards Safer and Understandable Driver Intention Prediction ICCV 2025 Towards Scalable Newborn Screening: Automated General Movement Assessment in Uncontrolled Settings MLHC 2025 (Towards) Scalable Reliable Automated Evaluation with Large Language Models ACL 2025 Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models ICML 2025 Towards Statistical Factuality Guarantee for Large Vision-Language Models EMNLP 2025 Towards Synergistic Path-based Explanations for Knowledge Graph Completion: Exploration and Evaluation ICLR 2025 Towards Trustable SHAP Scores AAAI 2025 Towards Trustworthy Knowledge Graph Reasoning: An Uncertainty Aware Perspective AAAI 2025 Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation CVPR 2025 Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis ICML 2025 Towards Understanding How Knowledge Evolves in Large Vision-Language Models CVPR 2025 Towards Understanding Multi-Task Learning (Generalization) of LLMs via Detecting and Exploring Task-Specific Neurons COLING 2025 Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It ICLR 2025 Towards Unifying Evaluation of Counterfactual Explanations: Leveraging Large Language Models for Human-Centric Assessments AAAI 2025 Towards Universal AI-Generated Image Detection by Variational Information Bottleneck Network CVPR 2025 Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures ICLR 2025