Training-free LLM Verification via Recycling Few-shot Examples

TL;DR

The paper introduces ReFeri, a training-free framework that recycles few-shot examples to verify and select the most accurate LLM outputs, significantly enhancing performance without extra training.

Contribution

ReFeri uniquely uses few-shot examples to evaluate and verify LLM outputs, improving accuracy through a novel scoring method without additional training.

Findings

Achieves an average of 4.8% accuracy gain across tasks

Effective response selection improves LLM performance

Works with multiple LLMs and diverse tasks

Abstract

Although LLMs have achieved remarkable performance, the inherent stochasticity of their reasoning process and varying conclusions present significant challenges. Majority voting or Best-of-N with external verification models has been explored to find the most promising solution among multiple LLM outputs. However, these approaches have certain limitations, such as limited applicability or the cost of an additional training step. To address this problem, we propose a novel and effective framework that Recycles Few-shot examples to verify LLM outputs (ReFeri). Our key idea is to additionally utilize the given few-shot examples to evaluate the candidate outputs of the target query, not only using them to generate outputs as the conventional few-shot prompting setup. Specifically, ReFeri evaluates the generated outputs by combining two different scores, designed motivated from Bayes' rule, and subsequently selects the candidate that is both confidently determined and contextually coherent through a few additional LLM inferences. Experiments with three different LLMs and across seven diverse tasks demonstrate that our framework significantly improves the accuracy of LLMs-achieving an average gain of 4.8%-through effective response selection, without additional training.