A conformal interpretability method labels LLM agent states step-by-step and extracts linearly separable temporal concept directions aligned with task success on ScienceWorld and AlfWorld.
A unified approach to interpreting model predictions.Advances in neural informa- tion processing systems, 30, 2017
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents
A conformal interpretability method labels LLM agent states step-by-step and extracts linearly separable temporal concept directions aligned with task success on ScienceWorld and AlfWorld.