Introduces BonaFide benchmark of 3,066 ground-truth labeled CoTs showing most faithfulness metrics perform near chance with biases and poor scaling to longer chains.
Hovy, and Dan Jurafsky
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
The survey organizes mechanistic interpretability techniques into a Locate-Steer-Improve framework to enable actionable improvements in LLM alignment, capability, and efficiency.
citing papers explorer
-
Faithfulness Metrics Don't Measure Faithfulness: A Meta-Evaluation with Ground Truth
Introduces BonaFide benchmark of 3,066 ground-truth labeled CoTs showing most faithfulness metrics perform near chance with biases and poor scaling to longer chains.
-
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
The survey organizes mechanistic interpretability techniques into a Locate-Steer-Improve framework to enable actionable improvements in LLM alignment, capability, and efficiency.