SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Xinping, Li, Dongfang, Zhong, Yan, Hu, Boren, Chen, Yibin, Hu, Baotian, Zhang, Min
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914973132783616
author Zhao, Xinping
Li, Dongfang
Zhong, Yan
Hu, Boren
Chen, Yibin
Hu, Baotian
Zhang, Min
author_facet Zhao, Xinping
Li, Dongfang
Zhong, Yan
Hu, Boren
Chen, Yibin
Hu, Baotian
Zhang, Min
contents Recent studies in Retrieval-Augmented Generation (RAG) have investigated extracting evidence from retrieved passages to reduce computational costs and enhance the final RAG performance, yet it remains challenging. Existing methods heavily rely on heuristic-based augmentation, encountering several issues: (1) Poor generalization due to hand-crafted context filtering; (2) Semantics deficiency due to rule-based context chunking; (3) Skewed length due to sentence-wise filter learning. To address these issues, we propose a model-based evidence extraction learning framework, SEER, optimizing a vanilla model as an evidence extractor with desired properties through self-aligned learning. Extensive experiments show that our method largely improves the final RAG performance, enhances the faithfulness, helpfulness, and conciseness of the extracted evidence, and reduces the evidence length by 9.25 times. The code will be available at https://github.com/HITsz-TMG/SEER.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11315
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation
Zhao, Xinping
Li, Dongfang
Zhong, Yan
Hu, Boren
Chen, Yibin
Hu, Baotian
Zhang, Min
Computation and Language
Recent studies in Retrieval-Augmented Generation (RAG) have investigated extracting evidence from retrieved passages to reduce computational costs and enhance the final RAG performance, yet it remains challenging. Existing methods heavily rely on heuristic-based augmentation, encountering several issues: (1) Poor generalization due to hand-crafted context filtering; (2) Semantics deficiency due to rule-based context chunking; (3) Skewed length due to sentence-wise filter learning. To address these issues, we propose a model-based evidence extraction learning framework, SEER, optimizing a vanilla model as an evidence extractor with desired properties through self-aligned learning. Extensive experiments show that our method largely improves the final RAG performance, enhances the faithfulness, helpfulness, and conciseness of the extracted evidence, and reduces the evidence length by 9.25 times. The code will be available at https://github.com/HITsz-TMG/SEER.
title SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation
topic Computation and Language
url https://arxiv.org/abs/2410.11315