Simple LLM Prompting is State-of-the-Art for Robust and Multilingual Dialogue Evaluation
This addresses the problem of evaluating dialogues in multiple languages and ensuring metric robustness for researchers and developers in dialogue systems, representing a significant advancement rather than an incremental improvement.
The paper tackled the lack of robust and multilingual automatic dialogue evaluation metrics by proposing a framework that combines existing evaluation models with LLM prompting, achieving state-of-the-art results with top rankings in DSTC11 Track 4 tasks.
Despite significant research effort in the development of automatic dialogue evaluation metrics, little thought is given to evaluating dialogues other than in English. At the same time, ensuring metrics are invariant to semantically similar responses is also an overlooked topic. In order to achieve the desired properties of robustness and multilinguality for dialogue evaluation metrics, we propose a novel framework that takes advantage of the strengths of current evaluation models with the newly-established paradigm of prompting Large Language Models (LLMs). Empirical results show our framework achieves state of the art results in terms of mean Spearman correlation scores across several benchmarks and ranks first place on both the Robust and Multilingual tasks of the DSTC11 Track 4 "Automatic Evaluation Metrics for Open-Domain Dialogue Systems", proving the evaluation capabilities of prompted LLMs.