Incantory
Sign in
Text promptMITNot scanned

Indirect Reasoning with LLMs

Zhang et al. (2024) recently proposed an indirect reasoning method to strengthen the reasoning power of LLMs. It employs the logic of contrapositives and contradictions to tackle IR tasks such as…

Prompt Engineering Guidev10 stars · 0 forks · 0 makes≈118 tokens

Scores by version

No eval runs reported yet. Incantory never runs prompts: owners report results from their own CI.

Datasets

No datasets.

All runs and datasets