Large Language Models Are Self-Taught Reasoners: Enhancing LLM Applications via Tailored Problem-Solving Demonstrations

TL;DR

This paper introduces SELF-TAUGHT, a framework for automatically generating tailored, high-quality demonstrations for large language models, improving their reasoning and problem-solving abilities across diverse tasks without human effort.

Contribution

The paper presents a novel automatic demonstration creation method that aligns with target instances, enhancing LLM performance in a zero-shot setting, especially in specialized domains.

Findings

SELF-TAUGHT outperforms strong baselines across 15 tasks.

It generalizes well to various prompting methods and LLMs.

It improves the quality of intermediate reasoning steps.

Abstract

Guiding large language models with a selected set of human-authored demonstrations is a common practice for improving LLM applications. However, human effort can be costly, especially in specialized domains (e.g., clinical diagnosis), and does not guarantee optimal performance due to the potential discrepancy of target skills between selected demonstrations and real test instances. Motivated by these, this paper explores the automatic creation of customized demonstrations, whose target skills align with the given target instance. We present SELF-TAUGHT, a problem-solving framework, which facilitates demonstrations that are "tailored" to the target problem and "filtered" for better quality (i.e., correctness) in a zero-shot manner. In 15 tasks of multiple-choice questions of diverse domains and the diagnosis of Alzheimer's disease (AD) with real-world patients, SELF-TAUGHT achieves superior performance to strong baselines (e.g., Few-shot CoT, Plan-and-Solve, Auto-CoT). We conduct comprehensive analyses on SELF-TAUGHT, including its generalizability to existing prompting methods and different LLMs, the quality of its intermediate generation, and more.