Interpretability

What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation ICML 2024 What Rotary Position Embedding Can Tell Us: Identifying Query and Key Weights Corresponding to Basic Syntactic or High-level Semantic Information NeurIPS 2024 What Sketch Explainability Really Means for Downstream Tasks? CVPR 2024 What’s wrong with your model? A Quantitative Analysis of Relation Classification NAACL 2024 What Will My Model Forget? Forecasting Forgotten Examples in Language Model Refinement ICML 2024 When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards ACL 2024 When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations ICLR 2024 When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models NAACL 2024 When Parts Are Greater Than Sums: Individual LLM Components Can Outperform Full Models EMNLP 2024 When to Trust LLMs: Aligning Confidence with Response Quality ACL 2024 Where does In-context Learning Happen in Large Language Models? NeurIPS 2024 Where We Have Arrived in Proving the Emergence of Sparse Interaction Primitives in DNNs ICLR 2024 Which Information Matters? Dissecting Human-written Multi-document Summaries with Partial Information Decomposition ACL 2024 Which Sense Dominates Multisensory Semantic Understanding? A Brain Decoding Study COLING 2024 Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models ICML 2024 Whispers of Doubt Amidst Echoes of Triumph in NLP Robustness NAACL 2024 Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models EMNLP 2024 Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2) NeurIPS 2024 Who's asking? User personas and the mechanics of latent misalignment NeurIPS 2024 ‘Why Didn’t You Allocate This Task to Them?’ Negotiation-Aware Task Allocation and Contrastive Explanation Generation AAAI 2024 Why Does New Knowledge Create Messy Ripple Effects in LLMs? EMNLP 2024 Why Larger Language Models Do In-context Learning Differently? ICML 2024 WikiSQE: A Large-Scale Dataset for Sentence Quality Estimation in Wikipedia AAAI 2024 Word Boundary Information Isn’t Useful for Encoder Language Models ACL 2024 Working Memory Identifies Reasoning Limits in Language Models EMNLP 2024