Return of EM: Entity-driven Answer Set Expansion for QA Evaluation
This work addresses evaluation challenges in QA for researchers and practitioners, offering a more interpretable and environmentally friendly alternative to LLM-based methods, though it appears incremental as it builds on existing EM techniques.
The paper tackled the problem of evaluating QA models by proposing soft EM with entity-driven answer set expansion to address issues like limited interpretability and high cost in LLM-based methods, achieving results that outperform traditional methods and match LLM-based reliability while offering interpretability and reduced environmental harm.
Recently, directly using large language models (LLMs) has been shown to be the most reliable method to evaluate QA models. However, it suffers from limited interpretability, high cost, and environmental harm. To address these, we propose to use soft EM with entity-driven answer set expansion. Our approach expands the gold answer set to include diverse surface forms, based on the observation that the surface forms often follow particular patterns depending on the entity type. The experimental results show that our method outperforms traditional evaluation methods by a large margin. Moreover, the reliability of our evaluation method is comparable to that of LLM-based ones, while offering the benefits of high interpretability and reduced environmental harm.