Interpretability

DocScript: Document-level Script Event Prediction COLING 2024 Does ChatGPT Know That It Does Not Know? Evaluating the Black-Box Calibration of ChatGPT COLING 2024 Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations? EMNLP 2024 Does Large Language Model Contain Task-Specific Neurons? EMNLP 2024 Do Language Models Know When They’re Hallucinating References? EACL 2024 Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates ICML 2024 Do Large Language Models Know How Much They Know? EMNLP 2024 Do Large Language Models Latently Perform Multi-Hop Reasoning? ACL 2024 Do LLMs Build World Representations? Probing Through the Lens of State Abstraction NeurIPS 2024 Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models EMNLP 2024 Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations EMNLP 2024 Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks NAACL 2024 Domain-Agnostic Adapter Architecture for Deception Detection: Extensive Evaluations with the DIFrauD Benchmark COLING 2024 Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations ICML 2024 Do Neural Language Models Inferentially Compose Concepts the Way Humans Can? COLING 2024 Don’t Go To Extremes: Revealing the Excessive Sensitivity and Calibration Limitations of LLMs in Implicit Hate Speech Detection ACL 2024 Don’t trust your eyes: on the (un)reliability of feature visualizations ICML 2024 Do Pre-Trained Language Models Detect and Understand Semantic Underspecification? Ask the DUST! ACL 2024 DORY: Deliberative Prompt Recovery for LLM ACL 2024 Do Zombies Understand? A Choose-Your-Own-Adventure Exploration of Machine Cognition ACL 2024 Driving Through the Concept Gridlock: Unraveling Explainability Bottlenecks in Automated Driving WACV 2024 Dual Process Masking for Dialogue Act Recognition EMNLP 2024 Dynamic Multi-granularity Attribution Network for Aspect-based Sentiment Analysis EMNLP 2024 DynSyn: Dynamical Synergistic Representation for Efficient Learning and Control in Overactuated Embodied Systems ICML 2024 Early Prediction of Causes (not Effects) in Healthcare by Long-Term Clinical Time Series Forecasting MLHC 2024