DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answering Article Swipe
Zijian Hei
,
Weiling Liu
,
Wenjie Ou
,
Juyi Qiao
,
Junming Jiao
,
Zhiqing Zhu
,
Guowen Song
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2406.07348
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2406.07348
Retrieval-Augmented Generation (RAG) has recently demonstrated the performance of Large Language Models (LLMs) in the knowledge-intensive tasks such as Question-Answering (QA). RAG expands the query context by incorporating external knowledge bases to enhance the response accuracy. However, it would be inefficient to access LLMs multiple times for each query and unreliable to retrieve all the relevant documents by a single query. We have found that even though there is low relevance between some critical documents and query, it is possible to retrieve the remaining documents by combining parts of the documents with the query. To mine the relevance, a two-stage retrieval framework called Dynamic-Relevant Retrieval-Augmented Generation (DR-RAG) is proposed to improve document retrieval recall and the accuracy of answers while maintaining efficiency. Additionally, a compact classifier is applied to two different selection strategies to determine the contribution of the retrieved documents to answering the query and retrieve the relatively relevant documents. Meanwhile, DR-RAG call the LLMs only once, which significantly improves the efficiency of the experiment. The experimental results on multi-hop QA datasets show that DR-RAG can significantly improve the accuracy of the answers and achieve new progress in QA systems.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2406.07348
- https://arxiv.org/pdf/2406.07348
- OA Status
- green
- Cited By
- 3
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4399694203
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4399694203Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2406.07348Digital Object Identifier
- Title
-
DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-AnsweringWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-06-11Full publication date if available
- Authors
-
Zijian Hei, Weiling Liu, Wenjie Ou, Juyi Qiao, Junming Jiao, Zhiqing Zhu, Guowen SongList of authors in order
- Landing page
-
https://arxiv.org/abs/2406.07348Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2406.07348Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2406.07348Direct OA link when available
- Concepts
-
Relevance (law), Information retrieval, Computer science, Question answering, Political science, LawTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
3Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 3Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4399694203 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2406.07348 |
| ids.doi | https://doi.org/10.48550/arxiv.2406.07348 |
| ids.openalex | https://openalex.org/W4399694203 |
| fwci | |
| type | preprint |
| title | DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answering |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10028 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9969000220298767 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Topic Modeling |
| topics[1].id | https://openalex.org/T11902 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9689000248908997 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Intelligent Tutoring Systems and Adaptive Learning |
| topics[2].id | https://openalex.org/T10181 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9072999954223633 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Natural Language Processing Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C158154518 |
| concepts[0].level | 2 |
| concepts[0].score | 0.852056622505188 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q7310970 |
| concepts[0].display_name | Relevance (law) |
| concepts[1].id | https://openalex.org/C23123220 |
| concepts[1].level | 1 |
| concepts[1].score | 0.6227714419364929 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q816826 |
| concepts[1].display_name | Information retrieval |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.5494630932807922 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C44291984 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5016295909881592 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1074173 |
| concepts[3].display_name | Question answering |
| concepts[4].id | https://openalex.org/C17744445 |
| concepts[4].level | 0 |
| concepts[4].score | 0.0867328941822052 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[4].display_name | Political science |
| concepts[5].id | https://openalex.org/C199539241 |
| concepts[5].level | 1 |
| concepts[5].score | 0.0 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[5].display_name | Law |
| keywords[0].id | https://openalex.org/keywords/relevance |
| keywords[0].score | 0.852056622505188 |
| keywords[0].display_name | Relevance (law) |
| keywords[1].id | https://openalex.org/keywords/information-retrieval |
| keywords[1].score | 0.6227714419364929 |
| keywords[1].display_name | Information retrieval |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.5494630932807922 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/question-answering |
| keywords[3].score | 0.5016295909881592 |
| keywords[3].display_name | Question answering |
| keywords[4].id | https://openalex.org/keywords/political-science |
| keywords[4].score | 0.0867328941822052 |
| keywords[4].display_name | Political science |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2406.07348 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2406.07348 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2406.07348 |
| locations[1].id | doi:10.48550/arxiv.2406.07348 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2406.07348 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5099136788 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Zijian Hei |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Hei, Zijian |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5091341521 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Weiling Liu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Liu, Weiling |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5012846747 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Wenjie Ou |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Ou, Wenjie |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5099136789 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Juyi Qiao |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Qiao, Juyi |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5104328414 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Junming Jiao |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Jiao, Junming |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5029109844 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Zhiqing Zhu |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Zhu, Zhiqing |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5113252928 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Guowen Song |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Song, Guowen |
| authorships[6].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2406.07348 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-06-15T00:00:00 |
| display_name | DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answering |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10028 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9969000220298767 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Topic Modeling |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2748952813, https://openalex.org/W2384605597, https://openalex.org/W2387743295, https://openalex.org/W2115758952, https://openalex.org/W3082787378, https://openalex.org/W1967370444, https://openalex.org/W2157408137, https://openalex.org/W2150136235, https://openalex.org/W4312252109 |
| cited_by_count | 3 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 3 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2406.07348 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2406.07348 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2406.07348 |
| primary_location.id | pmh:oai:arXiv.org:2406.07348 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2406.07348 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2406.07348 |
| publication_date | 2024-06-11 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 58, 98, 123 |
| abstract_inverted_index.QA | 171, 189 |
| abstract_inverted_index.To | 94 |
| abstract_inverted_index.We | 61 |
| abstract_inverted_index.as | 18 |
| abstract_inverted_index.be | 39 |
| abstract_inverted_index.by | 26, 57, 85 |
| abstract_inverted_index.in | 13, 188 |
| abstract_inverted_index.is | 68, 78, 107, 126 |
| abstract_inverted_index.it | 37, 77 |
| abstract_inverted_index.of | 8, 88, 117, 137, 163, 181 |
| abstract_inverted_index.on | 169 |
| abstract_inverted_index.to | 31, 41, 51, 80, 109, 128, 133, 141 |
| abstract_inverted_index.RAG | 21 |
| abstract_inverted_index.The | 166 |
| abstract_inverted_index.all | 53 |
| abstract_inverted_index.and | 49, 75, 114, 145, 184 |
| abstract_inverted_index.can | 176 |
| abstract_inverted_index.for | 46 |
| abstract_inverted_index.has | 3 |
| abstract_inverted_index.low | 69 |
| abstract_inverted_index.new | 186 |
| abstract_inverted_index.the | 6, 14, 23, 33, 54, 82, 89, 92, 96, 115, 135, 138, 143, 147, 154, 161, 164, 179, 182 |
| abstract_inverted_index.two | 129 |
| abstract_inverted_index.LLMs | 43, 155 |
| abstract_inverted_index.call | 153 |
| abstract_inverted_index.each | 47 |
| abstract_inverted_index.even | 65 |
| abstract_inverted_index.have | 62 |
| abstract_inverted_index.mine | 95 |
| abstract_inverted_index.only | 156 |
| abstract_inverted_index.show | 173 |
| abstract_inverted_index.some | 72 |
| abstract_inverted_index.such | 17 |
| abstract_inverted_index.that | 64, 174 |
| abstract_inverted_index.with | 91 |
| abstract_inverted_index.(QA). | 20 |
| abstract_inverted_index.(RAG) | 2 |
| abstract_inverted_index.Large | 9 |
| abstract_inverted_index.bases | 30 |
| abstract_inverted_index.found | 63 |
| abstract_inverted_index.once, | 157 |
| abstract_inverted_index.parts | 87 |
| abstract_inverted_index.query | 24, 48, 144 |
| abstract_inverted_index.tasks | 16 |
| abstract_inverted_index.there | 67 |
| abstract_inverted_index.times | 45 |
| abstract_inverted_index.which | 158 |
| abstract_inverted_index.while | 119 |
| abstract_inverted_index.would | 38 |
| abstract_inverted_index.(LLMs) | 12 |
| abstract_inverted_index.DR-RAG | 152, 175 |
| abstract_inverted_index.Models | 11 |
| abstract_inverted_index.access | 42 |
| abstract_inverted_index.called | 102 |
| abstract_inverted_index.query, | 76 |
| abstract_inverted_index.query. | 60, 93 |
| abstract_inverted_index.recall | 113 |
| abstract_inverted_index.single | 59 |
| abstract_inverted_index.though | 66 |
| abstract_inverted_index.achieve | 185 |
| abstract_inverted_index.answers | 118, 183 |
| abstract_inverted_index.applied | 127 |
| abstract_inverted_index.between | 71 |
| abstract_inverted_index.compact | 124 |
| abstract_inverted_index.context | 25 |
| abstract_inverted_index.enhance | 32 |
| abstract_inverted_index.expands | 22 |
| abstract_inverted_index.improve | 110, 178 |
| abstract_inverted_index.results | 168 |
| abstract_inverted_index.(DR-RAG) | 106 |
| abstract_inverted_index.However, | 36 |
| abstract_inverted_index.Language | 10 |
| abstract_inverted_index.accuracy | 116, 180 |
| abstract_inverted_index.critical | 73 |
| abstract_inverted_index.datasets | 172 |
| abstract_inverted_index.document | 111 |
| abstract_inverted_index.external | 28 |
| abstract_inverted_index.improves | 160 |
| abstract_inverted_index.multiple | 44 |
| abstract_inverted_index.possible | 79 |
| abstract_inverted_index.progress | 187 |
| abstract_inverted_index.proposed | 108 |
| abstract_inverted_index.recently | 4 |
| abstract_inverted_index.relevant | 55, 149 |
| abstract_inverted_index.response | 34 |
| abstract_inverted_index.retrieve | 52, 81, 146 |
| abstract_inverted_index.systems. | 190 |
| abstract_inverted_index.accuracy. | 35 |
| abstract_inverted_index.answering | 142 |
| abstract_inverted_index.combining | 86 |
| abstract_inverted_index.determine | 134 |
| abstract_inverted_index.different | 130 |
| abstract_inverted_index.documents | 56, 74, 84, 90, 140 |
| abstract_inverted_index.framework | 101 |
| abstract_inverted_index.knowledge | 29 |
| abstract_inverted_index.multi-hop | 170 |
| abstract_inverted_index.relevance | 70 |
| abstract_inverted_index.remaining | 83 |
| abstract_inverted_index.retrieval | 100, 112 |
| abstract_inverted_index.retrieved | 139 |
| abstract_inverted_index.selection | 131 |
| abstract_inverted_index.two-stage | 99 |
| abstract_inverted_index.Generation | 1, 105 |
| abstract_inverted_index.Meanwhile, | 151 |
| abstract_inverted_index.classifier | 125 |
| abstract_inverted_index.documents. | 150 |
| abstract_inverted_index.efficiency | 162 |
| abstract_inverted_index.relatively | 148 |
| abstract_inverted_index.relevance, | 97 |
| abstract_inverted_index.strategies | 132 |
| abstract_inverted_index.unreliable | 50 |
| abstract_inverted_index.efficiency. | 121 |
| abstract_inverted_index.experiment. | 165 |
| abstract_inverted_index.inefficient | 40 |
| abstract_inverted_index.maintaining | 120 |
| abstract_inverted_index.performance | 7 |
| abstract_inverted_index.contribution | 136 |
| abstract_inverted_index.demonstrated | 5 |
| abstract_inverted_index.experimental | 167 |
| abstract_inverted_index.Additionally, | 122 |
| abstract_inverted_index.incorporating | 27 |
| abstract_inverted_index.significantly | 159, 177 |
| abstract_inverted_index.Dynamic-Relevant | 103 |
| abstract_inverted_index.Question-Answering | 19 |
| abstract_inverted_index.Retrieval-Augmented | 0, 104 |
| abstract_inverted_index.knowledge-intensive | 15 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile |