Interpretability

Linear Explanations for Individual Neurons ICML 2024 Linearity of Relation Decoding in Transformer Language Models ICLR 2024 Linguistically Communicating Uncertainty in Patient-Facing Risk Prediction Models EACL 2024 Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination EMNLP 2024 Linguistic Calibration of Long-Form Generations ICML 2024 LipSim: A Provably Robust Perceptual Similarity Metric ICLR 2024 Listenable Maps for Zero-Shot Audio Classifiers NeurIPS 2024 LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses ICLR 2024 LJPCheck: Functional Tests for Legal Judgment Prediction ACL 2024 LLaGA: Large Language and Graph Assistant ICML 2024 LLaNA: Large Language and NeRF Assistant NeurIPS 2024 LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation CVPR 2024 LLM-Check: Investigating Detection of Hallucinations in Large Language Models NeurIPS 2024 LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations NAACL 2024 LLM Explainability via Attributive Masking Learning EMNLP 2024 LLM Factoscope: Uncovering LLMs’ Factual Discernment through Measuring Inner States ACL 2024 LLM Internal States Reveal Hallucination Risk Faced With a Query EMNLP 2024 LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback NAACL 2024 LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs AAAI 2024 LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts ACL 2024 LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing EMNLP 2024 LLMs Can Find Mathematical Reasoning Mistakes by Pedagogical Chain-of-Thought IJCAI 2024 LLMs cannot find reasoning errors, but can correct them given the error location ACL 2024 LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints EMNLP 2024 LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study EMNLP 2024