Predicting the Benefit of Retrieval Augmentation in Open-Domain Question Answering

Abstract:While retrieval augmented generation has become a common approach for enhancing question answering systems, retrieval is not universally advantageous. We study the problem of predicting whether incorporating external retrieved information is likely to improve response quality for a given question. To this end, we evaluate a range of prediction methods that are based on retrieval signals, answer characteristics, and semantic consistency between generated responses and retrieved passages. We further devise a predictor that probes the LLM's internal state. Its prediction performance significantly narrows the performance gap between post-generation methods which are computationally demanding and pre-generation (post-retrieval) methods. We use the prediction methods to devise a selective retrieval framework that dynamically chooses between retrieval and non-retrieval generation modes per question. Experimental results demonstrate that selectively applying retrieval augmentation yields answer quality that transcends that of using retrieval for all queries.

17 pages. 4 figures. 3 tables

Computation and Language (cs.CL); Information Retrieval (cs.IR)

arXiv:2604.07985 [cs.CL]

(or arXiv:2604.07985v3 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2604.07985 Focus to learn more arXiv-issued DOI via DataCite

https://doi.org/10.1145/3799682.3840689 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.