Efficient In-Domain Question Answering for Resource-Constrained Environments Article Swipe
Isaac Chung
,
P. Vo
,
Arman C. Kizilkale
,
Aaron Reite
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2409.17648
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2409.17648
Retrieval Augmented Generation (RAG) is a common method for integrating external knowledge into pretrained Large Language Models (LLMs) to enhance accuracy and relevancy in question answering (QA) tasks. However, prompt engineering and resource efficiency remain significant bottlenecks in developing optimal and robust RAG solutions for real-world QA applications. Recent studies have shown success in using fine tuning to address these problems; in particular, Retrieval Augmented Fine Tuning (RAFT) applied to smaller 7B models has demonstrated superior performance compared to RAG setups with much larger models such as GPT-3.5. The combination of RAFT with parameter-efficient fine tuning (PEFT) techniques, such as Low-Rank Adaptation (LoRA), promises an even more efficient solution, yet remains an unexplored area. In this work, we combine RAFT with LoRA to reduce fine tuning and storage requirements and gain faster inference times while maintaining comparable RAG performance. This results in a more compute-efficient RAFT, or CRAFT, which is particularly useful for knowledge-intensive QA tasks in resource-constrained environments where internet access may be restricted and hardware resources limited.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2409.17648
- https://arxiv.org/pdf/2409.17648
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4403851294
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4403851294Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2409.17648Digital Object Identifier
- Title
-
Efficient In-Domain Question Answering for Resource-Constrained EnvironmentsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-09-26Full publication date if available
- Authors
-
Isaac Chung, P. Vo, Arman C. Kizilkale, Aaron ReiteList of authors in order
- Landing page
-
https://arxiv.org/abs/2409.17648Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2409.17648Direct 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/2409.17648Direct OA link when available
- Concepts
-
Question answering, Domain (mathematical analysis), Resource (disambiguation), Computer science, Information retrieval, Mathematics, Mathematical analysis, Computer networkTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4403851294 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2409.17648 |
| ids.doi | https://doi.org/10.48550/arxiv.2409.17648 |
| ids.openalex | https://openalex.org/W4403851294 |
| fwci | |
| type | preprint |
| title | Efficient In-Domain Question Answering for Resource-Constrained Environments |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10715 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9538000226020813 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1705 |
| topics[0].subfield.display_name | Computer Networks and Communications |
| topics[0].display_name | Distributed and Parallel Computing Systems |
| topics[1].id | https://openalex.org/T11714 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9282000064849854 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Multimodal Machine Learning Applications |
| topics[2].id | https://openalex.org/T10906 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9165999889373779 |
| 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 | AI-based Problem Solving and Planning |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C44291984 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7134819030761719 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1074173 |
| concepts[0].display_name | Question answering |
| concepts[1].id | https://openalex.org/C36503486 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6100528836250305 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q11235244 |
| concepts[1].display_name | Domain (mathematical analysis) |
| concepts[2].id | https://openalex.org/C206345919 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5715937614440918 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q20380951 |
| concepts[2].display_name | Resource (disambiguation) |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.5108608603477478 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C23123220 |
| concepts[4].level | 1 |
| concepts[4].score | 0.32270270586013794 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q816826 |
| concepts[4].display_name | Information retrieval |
| concepts[5].id | https://openalex.org/C33923547 |
| concepts[5].level | 0 |
| concepts[5].score | 0.09566465020179749 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[5].display_name | Mathematics |
| concepts[6].id | https://openalex.org/C134306372 |
| concepts[6].level | 1 |
| concepts[6].score | 0.0 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[6].display_name | Mathematical analysis |
| concepts[7].id | https://openalex.org/C31258907 |
| concepts[7].level | 1 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q1301371 |
| concepts[7].display_name | Computer network |
| keywords[0].id | https://openalex.org/keywords/question-answering |
| keywords[0].score | 0.7134819030761719 |
| keywords[0].display_name | Question answering |
| keywords[1].id | https://openalex.org/keywords/domain |
| keywords[1].score | 0.6100528836250305 |
| keywords[1].display_name | Domain (mathematical analysis) |
| keywords[2].id | https://openalex.org/keywords/resource |
| keywords[2].score | 0.5715937614440918 |
| keywords[2].display_name | Resource (disambiguation) |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.5108608603477478 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/information-retrieval |
| keywords[4].score | 0.32270270586013794 |
| keywords[4].display_name | Information retrieval |
| keywords[5].id | https://openalex.org/keywords/mathematics |
| keywords[5].score | 0.09566465020179749 |
| keywords[5].display_name | Mathematics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2409.17648 |
| 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/2409.17648 |
| 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/2409.17648 |
| locations[1].id | doi:10.48550/arxiv.2409.17648 |
| 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.2409.17648 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5042595859 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Isaac Chung |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Chung, Isaac |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5048661449 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-7805-3143 |
| authorships[1].author.display_name | P. Vo |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Vo, Phat |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5114438839 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Arman C. Kizilkale |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Kizilkale, Arman C. |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5059409041 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Aaron Reite |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Reite, Aaron |
| authorships[3].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/2409.17648 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Efficient In-Domain Question Answering for Resource-Constrained Environments |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10715 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9538000226020813 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1705 |
| primary_topic.subfield.display_name | Computer Networks and Communications |
| primary_topic.display_name | Distributed and Parallel Computing Systems |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2384605597, https://openalex.org/W2387743295, https://openalex.org/W3082787378, https://openalex.org/W2136007095, https://openalex.org/W2366230879, https://openalex.org/W3208425359, https://openalex.org/W2349927912 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2409.17648 |
| 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/2409.17648 |
| 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/2409.17648 |
| primary_location.id | pmh:oai:arXiv.org:2409.17648 |
| 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/2409.17648 |
| 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/2409.17648 |
| publication_date | 2024-09-26 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 5, 142 |
| abstract_inverted_index.7B | 71 |
| abstract_inverted_index.In | 114 |
| abstract_inverted_index.QA | 46, 154 |
| abstract_inverted_index.an | 104, 111 |
| abstract_inverted_index.as | 86, 99 |
| abstract_inverted_index.be | 163 |
| abstract_inverted_index.in | 23, 37, 53, 61, 141, 156 |
| abstract_inverted_index.is | 4, 149 |
| abstract_inverted_index.of | 90 |
| abstract_inverted_index.or | 146 |
| abstract_inverted_index.to | 18, 57, 69, 78, 122 |
| abstract_inverted_index.we | 117 |
| abstract_inverted_index.RAG | 42, 79, 137 |
| abstract_inverted_index.The | 88 |
| abstract_inverted_index.and | 21, 31, 40, 126, 129, 165 |
| abstract_inverted_index.for | 8, 44, 152 |
| abstract_inverted_index.has | 73 |
| abstract_inverted_index.may | 162 |
| abstract_inverted_index.yet | 109 |
| abstract_inverted_index.(QA) | 26 |
| abstract_inverted_index.Fine | 65 |
| abstract_inverted_index.LoRA | 121 |
| abstract_inverted_index.RAFT | 91, 119 |
| abstract_inverted_index.This | 139 |
| abstract_inverted_index.even | 105 |
| abstract_inverted_index.fine | 55, 94, 124 |
| abstract_inverted_index.gain | 130 |
| abstract_inverted_index.have | 50 |
| abstract_inverted_index.into | 12 |
| abstract_inverted_index.more | 106, 143 |
| abstract_inverted_index.much | 82 |
| abstract_inverted_index.such | 85, 98 |
| abstract_inverted_index.this | 115 |
| abstract_inverted_index.with | 81, 92, 120 |
| abstract_inverted_index.(RAG) | 3 |
| abstract_inverted_index.Large | 14 |
| abstract_inverted_index.RAFT, | 145 |
| abstract_inverted_index.area. | 113 |
| abstract_inverted_index.shown | 51 |
| abstract_inverted_index.tasks | 155 |
| abstract_inverted_index.these | 59 |
| abstract_inverted_index.times | 133 |
| abstract_inverted_index.using | 54 |
| abstract_inverted_index.where | 159 |
| abstract_inverted_index.which | 148 |
| abstract_inverted_index.while | 134 |
| abstract_inverted_index.work, | 116 |
| abstract_inverted_index.(LLMs) | 17 |
| abstract_inverted_index.(PEFT) | 96 |
| abstract_inverted_index.(RAFT) | 67 |
| abstract_inverted_index.CRAFT, | 147 |
| abstract_inverted_index.Models | 16 |
| abstract_inverted_index.Recent | 48 |
| abstract_inverted_index.Tuning | 66 |
| abstract_inverted_index.access | 161 |
| abstract_inverted_index.common | 6 |
| abstract_inverted_index.faster | 131 |
| abstract_inverted_index.larger | 83 |
| abstract_inverted_index.method | 7 |
| abstract_inverted_index.models | 72, 84 |
| abstract_inverted_index.prompt | 29 |
| abstract_inverted_index.reduce | 123 |
| abstract_inverted_index.remain | 34 |
| abstract_inverted_index.robust | 41 |
| abstract_inverted_index.setups | 80 |
| abstract_inverted_index.tasks. | 27 |
| abstract_inverted_index.tuning | 56, 95, 125 |
| abstract_inverted_index.useful | 151 |
| abstract_inverted_index.(LoRA), | 102 |
| abstract_inverted_index.address | 58 |
| abstract_inverted_index.applied | 68 |
| abstract_inverted_index.combine | 118 |
| abstract_inverted_index.enhance | 19 |
| abstract_inverted_index.optimal | 39 |
| abstract_inverted_index.remains | 110 |
| abstract_inverted_index.results | 140 |
| abstract_inverted_index.smaller | 70 |
| abstract_inverted_index.storage | 127 |
| abstract_inverted_index.studies | 49 |
| abstract_inverted_index.success | 52 |
| abstract_inverted_index.GPT-3.5. | 87 |
| abstract_inverted_index.However, | 28 |
| abstract_inverted_index.Language | 15 |
| abstract_inverted_index.Low-Rank | 100 |
| abstract_inverted_index.accuracy | 20 |
| abstract_inverted_index.compared | 77 |
| abstract_inverted_index.external | 10 |
| abstract_inverted_index.hardware | 166 |
| abstract_inverted_index.internet | 160 |
| abstract_inverted_index.limited. | 168 |
| abstract_inverted_index.promises | 103 |
| abstract_inverted_index.question | 24 |
| abstract_inverted_index.resource | 32 |
| abstract_inverted_index.superior | 75 |
| abstract_inverted_index.Augmented | 1, 64 |
| abstract_inverted_index.Retrieval | 0, 63 |
| abstract_inverted_index.answering | 25 |
| abstract_inverted_index.efficient | 107 |
| abstract_inverted_index.inference | 132 |
| abstract_inverted_index.knowledge | 11 |
| abstract_inverted_index.problems; | 60 |
| abstract_inverted_index.relevancy | 22 |
| abstract_inverted_index.resources | 167 |
| abstract_inverted_index.solution, | 108 |
| abstract_inverted_index.solutions | 43 |
| abstract_inverted_index.Adaptation | 101 |
| abstract_inverted_index.Generation | 2 |
| abstract_inverted_index.comparable | 136 |
| abstract_inverted_index.developing | 38 |
| abstract_inverted_index.efficiency | 33 |
| abstract_inverted_index.pretrained | 13 |
| abstract_inverted_index.real-world | 45 |
| abstract_inverted_index.restricted | 164 |
| abstract_inverted_index.unexplored | 112 |
| abstract_inverted_index.bottlenecks | 36 |
| abstract_inverted_index.combination | 89 |
| abstract_inverted_index.engineering | 30 |
| abstract_inverted_index.integrating | 9 |
| abstract_inverted_index.maintaining | 135 |
| abstract_inverted_index.particular, | 62 |
| abstract_inverted_index.performance | 76 |
| abstract_inverted_index.significant | 35 |
| abstract_inverted_index.techniques, | 97 |
| abstract_inverted_index.demonstrated | 74 |
| abstract_inverted_index.environments | 158 |
| abstract_inverted_index.particularly | 150 |
| abstract_inverted_index.performance. | 138 |
| abstract_inverted_index.requirements | 128 |
| abstract_inverted_index.applications. | 47 |
| abstract_inverted_index.compute-efficient | 144 |
| abstract_inverted_index.knowledge-intensive | 153 |
| abstract_inverted_index.parameter-efficient | 93 |
| abstract_inverted_index.resource-constrained | 157 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |