A four-stage, PC-algorithm-based prompting pipeline raises OpenAI o3-mini's F1 on the Corr2Cause benchmark from 66.28 to 83.83, a new high for in-context causal discovery.
Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Causal Reasoning in Pieces: Modular In-Context Learning for Causal Discovery
A four-stage, PC-algorithm-based prompting pipeline raises OpenAI o3-mini's F1 on the Corr2Cause benchmark from 66.28 to 83.83, a new high for in-context causal discovery.