IAO prompting: Forcing Large Language Models to Show their Reasoning through an Input-Action-Output Template

Anonymous

Abstract: The effectiveness of Large Language Models (LLMs) in tackling diverse reasoning problems is further improved by chain-of-thought prompting, which makes explicit the intermediate reasoning steps. Additionally, recent research has proved the importance of explicitly structuring the reasoning procedure. In this work, we introduce IAO (input-action-output) prompting, a straightforward template based prompting method that allows the complex reasoning process to be explicitly modelled in a structured manner.IAO autonomously breaks down problems into a series of simpler reasoning steps and then solves them in sequence, each with explicit input information, action applied, and intermediate output. The solved steps inform the subsequent steps, facilitating progressive reasoning. This explicit structure not only amplifies reasoning performance but also fosters enhanced interpretability and transparency. Extensive experiments across various reasoning tasks demonstrate IAO's strong zero-shot capabilities, showcasing its effectiveness in unlocking and leveraging the true power of LLM reasoning.

Paper Type: long

Research Area: Semantics: Sentence-level Semantics, Textual Inference and Other areas

Contribution Types: NLP engineering experiment

Languages Studied: English