Large Language Models (LLMs) have demonstrated promising capabilities as
automatic evaluators in assessing the quality of generated natural language.
However, LLMs still exhibit biases in evaluation and often struggle to generate
coherent evaluations that align with human assessments. In this work, we first
conduct a systematic study of the misalignment between LLM evaluators and human
judgement, revealing that existing calibration methods aimed at mitigating
biases are insufficient for effectively aligning LLM evaluators. Inspired by
the use of preference data in RLHF, we formulate the evaluation as a ranking
problem and introduce Pairwise-preference Search (PAIRS), an uncertainty-guided
search method that employs LLMs to conduct pairwise comparisons and efficiently
ranks candidate texts. PAIRS achieves state-of-the-art performance on
representative evaluation tasks and demonstrates significant improvements over
direct scoring. Furthermore, we provide insights into the role of pairwise
preference in quantifying the transitivity of LLMs and demonstrate how PAIRS
benefits from calibration.

使用 Pairwise-preference Search（PAIRS）方法，通过对比评估候选文本，解决了大型语言模型（LLMs）在评估中出现的偏差与不连贯问题。