Likelihood-based Mitigation of Evaluation Bias in Large Language Models

Anonymous

TL;DR: We define a "likelihood bias" in LLM-based evaluation. We propose a method that quantifies and mitigate the bias.

Abstract: Large Language Models (LLMs) are widely used to evaluate natural language generation tasks as automated metrics. However, the likelihood, a measure of LLM's plausibility for a sentence, can vary due to superficial differences in sentences, such as word order and sentence structure. It is therefore possible that there might be a likelihood bias if LLMs are used for evaluation: they might overrate sentences with higher likelihoods while underrating those with lower likelihoods. In this paper, we investigate the presence and impact of likelihood bias in LLM-based evaluators. We also propose a method to mitigate the likelihood bias. Our method utilizes high-biased instances as few-shot examples for in-context learning. Our experiments in evaluating the Data2Text and grammatical error correction tasks reveal that several LLMs we test display a likelihood bias. Furthermore, our proposed method successfully mitigates this bias, also improving evaluation performance (in terms of correlation of models with human scores) significantly.

Paper Type: short

Research Area: NLP Applications

Contribution Types: NLP engineering experiment

Languages Studied: English