تقرير
Likelihood-based Mitigation of Evaluation Bias in Large Language Models
العنوان: | Likelihood-based Mitigation of Evaluation Bias in Large Language Models |
---|---|
المؤلفون: | Ohi, Masanari, Kaneko, Masahiro, Koike, Ryuto, Loem, Mengsay, Okazaki, Naoaki |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Artificial Intelligence |
الوصف: | 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 highly biased instances as few-shot examples for in-context learning. Our experiments in evaluating the data-to-text 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. Comment: 4 main pages |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2402.15987 |
رقم الأكسشن: | edsarx.2402.15987 |
قاعدة البيانات: | arXiv |
كن أول من يترك تعليقا!