🔗 Who cites «Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?»

59 papers of our library cite it (of the 141,840 whose bibliographies we read) · 7 with a page here, the most cited first · ← back to «Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?»

Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought PromptingConference on Neural Information Processing Systems (NeurIPS)Miles Turpin, Julian Michael, Ethan Perez, et al.2023 · 568 citations
Measuring Association Between Labels and Free-Text RationalesConference on Empirical Methods in Natural Language Processing (EMNLP)Sarah Wiegreffe, Ana Marasović, Noah A. Smith2021 · 215 citations
SCOTT: Self-Consistent Chain-of-Thought DistillationAnnual Meeting of the Association for Computational Linguistics (ACL)Peifeng Wang, Zhengyang Wang, Zheng Li, et al.2023 · 145 citations
Evaluating Explanations: How Much Do Explanations from the Teacher Aid Students?Transactions of the Association for Computational Linguistics (TACL)Danish Pruthi, Rachit Bansal, Bhuwan Dhingra, et al.2022 · 107 citations
Faithfulness Tests for Natural Language ExplanationsAnnual Meeting of the Association for Computational Linguistics (ACL)Pepa Atanasova, Oana-Maria Camburu, Christina Lioma, et al.2023 · 92 citations
Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought ReasoningFindings of the Association for Computational LinguisticsDebjit Paul, Robert West, Antoine Bosselut, et al.2024 · 77 citations
1. Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-TuningarXiv:2402.00530Ming Li, Yong Zhang, Shwai He, et al.2024 · 60 citations

52 more papers of our library cite it; they have no page here yet.

This page in Markdown → https://md.research.elamur.ai/free/en/papers/hase-2020-leakage-adjusted-simulatability-can-models/cited-by/