Strategy-Induct induces task-level instructions from question-only examples by generating reasoning strategies first, then using those pairs to create a guiding instruction.
ArXiv, abs/2212.10923
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CL 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
A single LLM rewrite of skill descriptions using false positive and negative cases matches manual optimization performance in production, with most other pipeline components adding little value.
DIP generates multiple diverse rationales, elaborates them into draft plans, and induces a final plan to improve zero-shot reasoning accuracy in LLMs without heavy sampling.
citing papers explorer
-
Strategy-Induct: Task-Level Strategy Induction for Instruction Generation
Strategy-Induct induces task-level instructions from question-only examples by generating reasoning strategies first, then using those pairs to create a guiding instruction.
-
A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimization
A single LLM rewrite of skill descriptions using false positive and negative cases matches manual optimization performance in production, with most other pipeline components adding little value.
-
Diverge to Induce Prompting: Multi-Rationale Induction for Zero-Shot Reasoning
DIP generates multiple diverse rationales, elaborates them into draft plans, and induces a final plan to improve zero-shot reasoning accuracy in LLMs without heavy sampling.