@johnschulman2: Bullish on this direction. Having a metric for explanation quality makes it possible to hillclimb, and counterfactual s…

X AI KOLs Timeline Papers

Summary

John Schulman highlights research by Adam Karvonen and colleagues on using counterfactual simulatability as a metric to improve AI explanation quality. They developed a dataset and pipeline that trains models to generate better post-hoc explanations of their own behavior, showing generalization to held-out evaluations.

Bullish on this direction. Having a metric for explanation quality makes it possible to hillclimb, and counterfactual simulatability seems right. Adam et al. created a dataset+pipeline that creates more diverse+realistic test cases than prior work & do interesting exps on it. Can also train models to write better post-hoc explanations of their behavior, as highlighted in this thread.
Original Article
View Cached Full Text

Cached at: 09/06/26, 08:46 AM

Bullish on this direction. Having a metric for explanation quality makes it possible to hillclimb, and counterfactual simulatability seems right. Adam et al. created a dataset+pipeline that creates more diverse+realistic test cases than prior work & do interesting exps on it. Can also train models to write better post-hoc explanations of their behavior, as highlighted in this thread.

Adam Karvonen (@a_karvonen): Can a model learn to explain its behaviors, such as why it ignored a user request or made a coding error?

We trained models on thousands of explanations of their own in-the-wild behaviors.

Training on this single general dataset shows generalization to held-out evals.

🧵

Similar Articles

ExplainBench: Evaluating Code Explanations from Agents

Hugging Face Daily Papers

ExplainBench is a new benchmark for evaluating the trustworthiness of explanations generated by coding agents, revealing that explanation quality is a distinct axis of agent evaluation and that an audit agent can automatically improve explanation reliability.

Effective Explanations Support Planning Under Uncertainty

arXiv cs.CL

This research paper introduces a computational model that evaluates the effectiveness of procedural explanations by simulating how they guide action planning under uncertainty. Through four experiments, the authors demonstrate that explanations scored higher by their model are judged more helpful and lead to better navigation performance.