Interpretability

Are Large Language Models Consistent over Value-laden Questions? EMNLP 2024 Are LLM-based Evaluators Confusing NLG Quality Criteria? ACL 2024 Are Logistic Models Really Interpretable? IJCAI 2024 A Reproducibility Study on Quantifying Language Similarity: The Impact of Missing Values in the URIEL Knowledge Base NAACL 2024 Are self-explanations from Large Language Models faithful? ACL 2024 Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensics IJCAI 2024 Argument-Based Sentiment Analysis on Forward-Looking Statements ACL 2024 AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties NeurIPS 2024 A Self-explaining Neural Architecture for Generalizable Concept Learning IJCAI 2024 A Self-verified Method for Exploring Simile Knowledge from Pre-trained Language Models COLING 2024 A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Texts ACL 2024 Ask Again, Then Fail: Large Language Models’ Vacillations in Judgment ACL 2024 Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications ICML 2024 Assessing the Significance of Encoded Information in Contextualized Representations to Word Sense Disambiguation EACL 2024 A Study on How Attention Scores in the BERT Model Are Aware of Lexical Categories in Syntactic and Semantic Tasks on the GLUE Benchmark COLING 2024 A Survey of Confidence Estimation and Calibration in Large Language Models NAACL 2024 A Survey of Robotic Language Grounding: Tradeoffs between Symbols and Embeddings IJCAI 2024 A Survey on Natural Language Counterfactual Generation EMNLP 2024 A Systematic Analysis of Large Language Models as Soft Reasoners: The Case of Syllogistic Inferences EMNLP 2024 A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations EMNLP 2024 A theoretical design of concept sets: improving the predictability of concept bottleneck models NeurIPS 2024 A Theory of Interpretable Approximations COLT 2024 Atomic Inference for NLI with Generated Facts as Atoms EMNLP 2024 Attack-free Evaluating and Enhancing Adversarial Robustness on Categorical Data ICML 2024 Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers EMNLP 2024