Interpretability

Conceptual Pacts for Reference Resolution Using Small, Dynamically Constructed Language Models: A Study in Puzzle Building Dialogues COLING 2024 Conditions for parameter unidentifiability of linear ARX systems for enhancing security L4DC 2024 Confidence Regulation Neurons in Language Models NeurIPS 2024 Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models ACL 2024 Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees NeurIPS 2024 Conformalized Credal Set Predictors NeurIPS 2024 Conformalized Multiple Testing after Data-dependent Selection NeurIPS 2024 Conformal Prediction Sets Improve Human Decision Making ICML 2024 CoNLL#: Fine-grained Error Analysis and a Corrected Test Set for CoNLL-03 English COLING 2024 Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data NeurIPS 2024 Considering Human Interaction and Variability in Automatic Text Simplification EMNLP 2024 Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answering CVPR 2024 Constructing Concept-based Models to Mitigate Spurious Correlations with Minimal Human Effort ECCV 2024 Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons COLING 2024 Context-Aware Testing: A New Paradigm for Model Testing with Large Language Models NeurIPS 2024 ContextCite: Attributing Model Generation to Context NeurIPS 2024 Contextual Feature Selection with Conditional Stochastic Gates ICML 2024 Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning ICML 2024 Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation EMNLP 2024 Context versus Prior Knowledge in Language Models ACL 2024 Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving NeurIPS 2024 ContraSim – Analyzing Neural Representations Based on Contrastive Learning NAACL 2024 Contrastive Decoding Reduces Hallucinations in Large Multilingual Machine Translation Models EACL 2024 ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees EMNLP 2024 Conversational Drug Editing Using Retrieval and Domain Feedback ICLR 2024