Interpretability

Attention Meets Post-hoc Interpretability: A Mathematical Perspective ICML 2024 Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models ICLR 2024 AttEXplore: Attribution for Explanation with model parameters eXploration ICLR 2024 AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers ICML 2024 Attribute First, then Generate: Locally-attributable Grounded Text Generation ACL 2024 Attribute or Abstain: Large Language Models as Long Document Assistants EMNLP 2024 Attribution Patching Outperforms Automated Circuit Discovery EMNLP 2024 Attribution Quality Metrics with Magnitude Alignment IJCAI 2024 A Typology of Errors for User Utterances in Chatbots COLING 2024 Auditing Local Explanations is Hard NeurIPS 2024 AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement CVPR 2024 AuRoRA: A One-for-all Platform for Augmented Reasoning and Refining with Task-Adaptive Chain-of-Thought Prompting COLING 2024 AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models ICLR 2024 AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models EMNLP 2024 AutoHallusion: Automatic Generation of Hallucination Benchmarks for Vision-Language Models EMNLP 2024 Automated Assessment of Fidelity and Interpretability: An Evaluation Framework for Large Language Models’ Explanations (Student Abstract) AAAI 2024 Automated Detection and Analysis of Data Practices Using A Real-World Corpus ACL 2024 Automated Justification Production for Claim Veracity in Fact Checking: A Survey on Architectures and Approaches ACL 2024 Automated Natural Language Explanation of Deep Visual Neurons with Large Models (Student Abstract) AAAI 2024 Automated Statistical Model Discovery with Language Models ICML 2024 Automatic Bug Detection in LLM-Powered Text-Based Games Using LLMs ACL 2024 Automatic Extraction of Disease Risk Factors from Medical Publications ACL 2024 Automatic Generation of Model and Data Cards: A Step Towards Responsible AI NAACL 2024 Automatic Quote Attribution in Chinese Literary Works ACL 2024 Autonomous Policy Explanations for Effective Human-Machine Teaming AAAI 2024