2023 ActiveRetrievalAugmentedGenerat
- (Jiang, Xu et al., 2023) ⇒ Zhengbao Jiang, Frank F Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. (2023). “Active Retrieval Augmented Generation.” In: arXiv preprint arXiv:2305.06983. doi:10.48550/arXiv.2305.06983
Subject Headings: Forward-Looking Active REtrieval Augmented Generation (FLARE), RAG Method.
Notes
Cited By
Quotes
Abstract
Despite the remarkable ability of large language models (LMs) to comprehend and generate language, they have a tendency to hallucinate and create factually inaccurate output. Augmenting LMs by retrieving information from external knowledge resources is one promising solution. Most existing retrieval-augmented LMs employ a retrieve-and-generate setup that only retrieves information once based on the input. This is limiting, however, in more general scenarios involving generation of long texts, where continually gathering information throughout the generation process is essential. There have been some past efforts to retrieve information multiple times while generating outputs, which mostly retrieve documents at fixed intervals using the previous context as queries. In this work, we provide a generalized view of active retrieval augmented generation, methods that actively decide when and what to retrieve across the course of the generation. We propose Forward-Looking Active REtrieval augmented generation (FLARE), a generic retrieval-augmented generation method which iteratively uses a prediction of the upcoming sentence to anticipate future content, which is then utilized as a query to retrieve relevant documents to regenerate the sentence if it contains low-confidence tokens. We test FLARE along with baselines comprehensively over 4 long-form knowledge-intensive generation tasks/datasets. FLARE achieves superior or competitive performance on all tasks, demonstrating the effectiveness of our method. Code and datasets are available at this https URL.
References
;
| Author | volume | Date Value | title | type | journal | titleUrl | doi | note | year | |
|---|---|---|---|---|---|---|---|---|---|---|
| 2023 ActiveRetrievalAugmentedGenerat | Yiming Yang Qian Liu Graham Neubig Zhengbao Jiang Jane Dwivedi-Yu Frank F Xu Luyu Gao Zhiqing Sun Jamie Callan | Active Retrieval Augmented Generation | 10.48550/arXiv.2305.06983 | 2023 |