Evaluating Open-QA Evaluation
This work addresses the need for more reliable automatic evaluation tools in Open-QA, which is crucial for assessing the factuality of large language models, though it is incremental as it builds on existing evaluation challenges.
This study tackles the problem of evaluating Open Question Answering (Open-QA) by introducing a new task, Evaluating QA Evaluation (QA-Eval), and a dataset called EVOUNA to assess the accuracy of AI-generated answers against standard answers, using human-annotated results to measure performance and identify methods with high correlation to human evaluations.
This study focuses on the evaluation of the Open Question Answering (Open-QA) task, which can directly estimate the factuality of large language models (LLMs). Current automatic evaluation methods have shown limitations, indicating that human evaluation still remains the most reliable approach. We introduce a new task, Evaluating QA Evaluation (QA-Eval) and the corresponding dataset EVOUNA, designed to assess the accuracy of AI-generated answers in relation to standard answers within Open-QA. Our evaluation of these methods utilizes human-annotated results to measure their performance. Specifically, the work investigates methods that show high correlation with human evaluations, deeming them more reliable. We also discuss the pitfalls of current methods and methods to improve LLM-based evaluators. We believe this new QA-Eval task and corresponding dataset EVOUNA will facilitate the development of more effective automatic evaluation tools and prove valuable for future research in this area. All resources are available at \url{https://github.com/wangcunxiang/QA-Eval} and it is under the Apache-2.0 License.