Bayesian Calibration of Win Rate Estimation with LLM Evaluators
This work addresses the need for more reliable automatic evaluation in NLP, particularly for researchers and practitioners using LLMs to assess text quality, though it is incremental as it builds on existing Bayesian inference techniques.
The paper tackles the problem of unreliable win rate estimation when using LLM evaluators for text generation tasks by proposing Bayesian calibration methods, resulting in improved accuracy across six datasets including story generation, summarization, and instruction following.
Recent advances in large language models (LLMs) show the potential of using LLMs as evaluators for assessing the quality of text generations from LLMs. However, applying LLM evaluators naively to compare or judge between different systems can lead to unreliable results due to the intrinsic win rate estimation bias of LLM evaluators. In order to mitigate this problem, we propose two calibration methods, Bayesian Win Rate Sampling (BWRS) and Bayesian Dawid-Skene, both of which leverage Bayesian inference to more accurately infer the true win rate of generative language models. We empirically validate our methods on six datasets covering story generation, summarization, and instruction following tasks. We show that both our methods are effective in improving the accuracy of win rate estimation using LLMs as evaluators, offering a promising direction for reliable automatic text quality evaluation.