Interpretability

On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons NAACL 2024 On the Posterior Distribution in Denoising: Application to Uncertainty Quantification ICLR 2024 On the Power and Limitations of Examples for Description Logic Concepts IJCAI 2024 On the Relationship between Skill Neurons and Robustness in Prompt Tuning COLING 2024 On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations ACL 2024 On the Role of Context in Reading Time Prediction EMNLP 2024 On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task EMNLP 2024 On the Universal Truthfulness Hyperplane Inside LLMs EMNLP 2024 On the Use of Plausible Arguments in Explainable Conversational AI Interspeech 2024 On the Worst Prompt Performance of Large Language Models NeurIPS 2024 Opening the Black Box: Unraveling the Classroom Dialogue Analysis (Student Abstract) AAAI 2024 Optimal ablation for interpretability NeurIPS 2024 Optimal and efficient text counterfactuals using Graph Neural Networks EMNLP 2024 Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning NeurIPS 2024 Out-of-Distribution Detection via Deep Multi-Comprehension Ensemble ICML 2024 Out-of-Distribution Detection with Negative Prompts ICLR 2024 Out-of-distribution generalisation in spoken language understanding Interspeech 2024 Overcoming the Optimizer’s Curse: Obtaining Realistic Prescriptions from Neural Networks ICML 2024 Overconfidence is Key: Verbalized Uncertainty Evaluation in Large Language and Vision-Language Models NAACL 2024 Over-Reasoning and Redundant Calculation of Large Language Models EACL 2024 Overthinking the Truth: Understanding how Language Models Process False Demonstrations ICLR 2024 Overview of the MEDIQA-CORR 2024 Shared Task on Medical Error Detection and Correction NAACL 2024 PaCE: Parsimonious Concept Engineering for Large Language Models NeurIPS 2024 PAC Prediction Sets Under Label Shift ICLR 2024 PAD: A Robustness Enhancement Ensemble Method via Promoting Attention Diversity COLING 2024