Aftina: enhancing stability and preventing hallucination in AI-based Islamic fatwa generation using LLMs and RAG Article Swipe
Marryam Yahya Mohammed
,
Shafaqat Ali
,
Salma Khaled Ali
,
Abdul Majeed
,
Ensaf Hussein Mohamed
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1007/s00521-025-11229-y
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1007/s00521-025-11229-y
Question–answering (QA) systems face considerable challenges when involved in Islamic fatwas due to the complexity and sensitivity of the data. Such problems involve providing accurate and reliable responses, managing hallucinations and inaccurate responses, and maintaining the stability of the generated responses. Prior studies have concentrated mainly on collecting and preprocessing Islamic datasets or developing retrieval-based QA systems, overlooking the precision and reliability required for fatwa issuance. To address this issue, we propose a QA approach utilizing advanced retrieval-augmented generation (RAG), which is enhanced by a re-ranker to increase response stability, eliminate hallucinations, and prioritize the most appropriate and exact answer. This enhancement significantly improves response stability and reduces hallucinations by improving the data used for answer generation. We conducted experiments across three setups: (1) base LLM, (2) LLM with RAG, and (3) LLM with RAG and re-ranker. The third method of LLM with RAG includes a re-ranker for knowledge retrieval, which improves the process and ensures relevant and trustworthy data. This differentiates it from the second method, which uses a retrieval model. The Flash re-ranker retrieves the most relevant data, which increases the response stability and trustworthiness. Evaluations using BERTScore, hallucination, completeness, and irrelevance metrics demonstrated that the third experiment LLM with RAG and re-ranker outperformed other setups, providing precise, stable, and dependable answers. This research contributes a robust methodology to improve AI-driven fatwa systems, guaranteeing higher precision and trustworthiness in Islamic QA systems.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1007/s00521-025-11229-y
- https://link.springer.com/content/pdf/10.1007/s00521-025-11229-y.pdf
- OA Status
- hybrid
- Cited By
- 1
- References
- 27
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4410953402
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4410953402Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1007/s00521-025-11229-yDigital Object Identifier
- Title
-
Aftina: enhancing stability and preventing hallucination in AI-based Islamic fatwa generation using LLMs and RAGWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-06-02Full publication date if available
- Authors
-
Marryam Yahya Mohammed, Shafaqat Ali, Salma Khaled Ali, Abdul Majeed, Ensaf Hussein MohamedList of authors in order
- Landing page
-
https://doi.org/10.1007/s00521-025-11229-yPublisher landing page
- PDF URL
-
https://link.springer.com/content/pdf/10.1007/s00521-025-11229-y.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://link.springer.com/content/pdf/10.1007/s00521-025-11229-y.pdfDirect OA link when available
- Concepts
-
Computational Science and Engineering, Islam, Stability (learning theory), Islamic finance, Computer science, Econometrics, Mathematics, Machine learning, Philosophy, TheologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- References (count)
-
27Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4410953402 |
|---|---|
| doi | https://doi.org/10.1007/s00521-025-11229-y |
| ids.doi | https://doi.org/10.1007/s00521-025-11229-y |
| ids.openalex | https://openalex.org/W4410953402 |
| fwci | 4.81974515 |
| type | article |
| title | Aftina: enhancing stability and preventing hallucination in AI-based Islamic fatwa generation using LLMs and RAG |
| biblio.issue | 25 |
| biblio.volume | 37 |
| biblio.last_page | 20982 |
| biblio.first_page | 20957 |
| grants[0].funder | https://openalex.org/F4320330006 |
| grants[0].award_id | |
| grants[0].funder_display_name | Nile University |
| topics[0].id | https://openalex.org/T13702 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9728999733924866 |
| 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 | Machine Learning in Healthcare |
| topics[1].id | https://openalex.org/T11995 |
| topics[1].field.id | https://openalex.org/fields/14 |
| topics[1].field.display_name | Business, Management and Accounting |
| topics[1].score | 0.9358999729156494 |
| topics[1].domain.id | https://openalex.org/domains/2 |
| topics[1].domain.display_name | Social Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1404 |
| topics[1].subfield.display_name | Management Information Systems |
| topics[1].display_name | FinTech, Crowdfunding, Digital Finance |
| topics[2].id | https://openalex.org/T10028 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9235000014305115 |
| 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 | Topic Modeling |
| funders[0].id | https://openalex.org/F4320330006 |
| funders[0].ror | https://ror.org/03cg7cp61 |
| funders[0].display_name | Nile University |
| is_xpac | False |
| apc_list.value | 2390 |
| apc_list.currency | EUR |
| apc_list.value_usd | 2990 |
| apc_paid.value | 2390 |
| apc_paid.currency | EUR |
| apc_paid.value_usd | 2990 |
| concepts[0].id | https://openalex.org/C68597687 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8548296689987183 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q362601 |
| concepts[0].display_name | Computational Science and Engineering |
| concepts[1].id | https://openalex.org/C4445939 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5640653967857361 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q432 |
| concepts[1].display_name | Islam |
| concepts[2].id | https://openalex.org/C112972136 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5637063384056091 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q7595718 |
| concepts[2].display_name | Stability (learning theory) |
| concepts[3].id | https://openalex.org/C2991718497 |
| concepts[3].level | 3 |
| concepts[3].score | 0.4871787428855896 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q457753 |
| concepts[3].display_name | Islamic finance |
| concepts[4].id | https://openalex.org/C41008148 |
| concepts[4].level | 0 |
| concepts[4].score | 0.3669859766960144 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[4].display_name | Computer science |
| concepts[5].id | https://openalex.org/C149782125 |
| concepts[5].level | 1 |
| concepts[5].score | 0.34684500098228455 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q160039 |
| concepts[5].display_name | Econometrics |
| concepts[6].id | https://openalex.org/C33923547 |
| concepts[6].level | 0 |
| concepts[6].score | 0.2418803870677948 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[6].display_name | Mathematics |
| concepts[7].id | https://openalex.org/C119857082 |
| concepts[7].level | 1 |
| concepts[7].score | 0.20183348655700684 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[7].display_name | Machine learning |
| concepts[8].id | https://openalex.org/C138885662 |
| concepts[8].level | 0 |
| concepts[8].score | 0.09549513459205627 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[8].display_name | Philosophy |
| concepts[9].id | https://openalex.org/C27206212 |
| concepts[9].level | 1 |
| concepts[9].score | 0.07120898365974426 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q34178 |
| concepts[9].display_name | Theology |
| keywords[0].id | https://openalex.org/keywords/computational-science-and-engineering |
| keywords[0].score | 0.8548296689987183 |
| keywords[0].display_name | Computational Science and Engineering |
| keywords[1].id | https://openalex.org/keywords/islam |
| keywords[1].score | 0.5640653967857361 |
| keywords[1].display_name | Islam |
| keywords[2].id | https://openalex.org/keywords/stability |
| keywords[2].score | 0.5637063384056091 |
| keywords[2].display_name | Stability (learning theory) |
| keywords[3].id | https://openalex.org/keywords/islamic-finance |
| keywords[3].score | 0.4871787428855896 |
| keywords[3].display_name | Islamic finance |
| keywords[4].id | https://openalex.org/keywords/computer-science |
| keywords[4].score | 0.3669859766960144 |
| keywords[4].display_name | Computer science |
| keywords[5].id | https://openalex.org/keywords/econometrics |
| keywords[5].score | 0.34684500098228455 |
| keywords[5].display_name | Econometrics |
| keywords[6].id | https://openalex.org/keywords/mathematics |
| keywords[6].score | 0.2418803870677948 |
| keywords[6].display_name | Mathematics |
| keywords[7].id | https://openalex.org/keywords/machine-learning |
| keywords[7].score | 0.20183348655700684 |
| keywords[7].display_name | Machine learning |
| keywords[8].id | https://openalex.org/keywords/philosophy |
| keywords[8].score | 0.09549513459205627 |
| keywords[8].display_name | Philosophy |
| keywords[9].id | https://openalex.org/keywords/theology |
| keywords[9].score | 0.07120898365974426 |
| keywords[9].display_name | Theology |
| language | en |
| locations[0].id | doi:10.1007/s00521-025-11229-y |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S147897268 |
| locations[0].source.issn | 0941-0643, 1433-3058 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 0941-0643 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | Neural Computing and Applications |
| locations[0].source.host_organization | https://openalex.org/P4310319900 |
| locations[0].source.host_organization_name | Springer Science+Business Media |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310319900 |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://link.springer.com/content/pdf/10.1007/s00521-025-11229-y.pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Neural Computing and Applications |
| locations[0].landing_page_url | https://doi.org/10.1007/s00521-025-11229-y |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5117799884 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Marryam Yahya Mohammed |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Marryam Yahya Mohammed |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5086539587 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-3773-5196 |
| authorships[1].author.display_name | Shafaqat Ali |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Sama Ayman Ali |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5074378065 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Salma Khaled Ali |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Salma Khaled Ali |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5051422193 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-8270-6706 |
| authorships[3].author.display_name | Abdul Majeed |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Ayad Abdul Majeed |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5042351049 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-1615-0236 |
| authorships[4].author.display_name | Ensaf Hussein Mohamed |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Ensaf Hussein Mohamed |
| authorships[4].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://link.springer.com/content/pdf/10.1007/s00521-025-11229-y.pdf |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Aftina: enhancing stability and preventing hallucination in AI-based Islamic fatwa generation using LLMs and RAG |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T13702 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9728999733924866 |
| 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 | Machine Learning in Healthcare |
| related_works | https://openalex.org/W638761397, https://openalex.org/W3024564412, https://openalex.org/W3007943912, https://openalex.org/W2008417212, https://openalex.org/W2590610713, https://openalex.org/W1517153957, https://openalex.org/W2622054280, https://openalex.org/W3090021945, https://openalex.org/W2800377841, https://openalex.org/W2735344339 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 1 |
| best_oa_location.id | doi:10.1007/s00521-025-11229-y |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S147897268 |
| best_oa_location.source.issn | 0941-0643, 1433-3058 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 0941-0643 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | Neural Computing and Applications |
| best_oa_location.source.host_organization | https://openalex.org/P4310319900 |
| best_oa_location.source.host_organization_name | Springer Science+Business Media |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310319900 |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://link.springer.com/content/pdf/10.1007/s00521-025-11229-y.pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Neural Computing and Applications |
| best_oa_location.landing_page_url | https://doi.org/10.1007/s00521-025-11229-y |
| primary_location.id | doi:10.1007/s00521-025-11229-y |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S147897268 |
| primary_location.source.issn | 0941-0643, 1433-3058 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 0941-0643 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | Neural Computing and Applications |
| primary_location.source.host_organization | https://openalex.org/P4310319900 |
| primary_location.source.host_organization_name | Springer Science+Business Media |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310319900 |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://link.springer.com/content/pdf/10.1007/s00521-025-11229-y.pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Neural Computing and Applications |
| primary_location.landing_page_url | https://doi.org/10.1007/s00521-025-11229-y |
| publication_date | 2025-06-02 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W4387817020, https://openalex.org/W4387776256, https://openalex.org/W4400528237, https://openalex.org/W3159843954, https://openalex.org/W4401445178, https://openalex.org/W3007345084, https://openalex.org/W4402371950, https://openalex.org/W6822655377, https://openalex.org/W6601700763, https://openalex.org/W3090081112, https://openalex.org/W3039092485, https://openalex.org/W4396518017, https://openalex.org/W4327953388, https://openalex.org/W3178077565, https://openalex.org/W4391294261, https://openalex.org/W4412888148, https://openalex.org/W6600210674, https://openalex.org/W6600077625, https://openalex.org/W6600001191, https://openalex.org/W6601100789, https://openalex.org/W4317898419, https://openalex.org/W6600585467, https://openalex.org/W6892633411, https://openalex.org/W4412544568, https://openalex.org/W2101105183, https://openalex.org/W6600686112, https://openalex.org/W4412945639 |
| referenced_works_count | 27 |
| abstract_inverted_index.a | 73, 85, 146, 170, 218 |
| abstract_inverted_index.QA | 56, 74, 233 |
| abstract_inverted_index.To | 67 |
| abstract_inverted_index.We | 118 |
| abstract_inverted_index.by | 84, 110 |
| abstract_inverted_index.in | 9, 231 |
| abstract_inverted_index.is | 82 |
| abstract_inverted_index.it | 163 |
| abstract_inverted_index.of | 18, 38, 141 |
| abstract_inverted_index.on | 47 |
| abstract_inverted_index.or | 53 |
| abstract_inverted_index.to | 13, 87, 221 |
| abstract_inverted_index.we | 71 |
| abstract_inverted_index.(1) | 124 |
| abstract_inverted_index.(2) | 127 |
| abstract_inverted_index.(3) | 132 |
| abstract_inverted_index.LLM | 128, 133, 142, 201 |
| abstract_inverted_index.RAG | 135, 144, 203 |
| abstract_inverted_index.The | 138, 173 |
| abstract_inverted_index.and | 16, 26, 31, 34, 49, 61, 93, 98, 107, 131, 136, 155, 158, 186, 193, 204, 212, 229 |
| abstract_inverted_index.due | 12 |
| abstract_inverted_index.for | 64, 115, 148 |
| abstract_inverted_index.the | 14, 19, 36, 39, 59, 95, 112, 153, 165, 177, 183, 198 |
| abstract_inverted_index.(QA) | 2 |
| abstract_inverted_index.LLM, | 126 |
| abstract_inverted_index.RAG, | 130 |
| abstract_inverted_index.Such | 21 |
| abstract_inverted_index.This | 101, 161, 215 |
| abstract_inverted_index.base | 125 |
| abstract_inverted_index.data | 113 |
| abstract_inverted_index.face | 4 |
| abstract_inverted_index.from | 164 |
| abstract_inverted_index.have | 44 |
| abstract_inverted_index.most | 96, 178 |
| abstract_inverted_index.that | 197 |
| abstract_inverted_index.this | 69 |
| abstract_inverted_index.used | 114 |
| abstract_inverted_index.uses | 169 |
| abstract_inverted_index.when | 7 |
| abstract_inverted_index.with | 129, 134, 143, 202 |
| abstract_inverted_index.Flash | 174 |
| abstract_inverted_index.Prior | 42 |
| abstract_inverted_index.data, | 180 |
| abstract_inverted_index.data. | 20, 160 |
| abstract_inverted_index.exact | 99 |
| abstract_inverted_index.fatwa | 65, 224 |
| abstract_inverted_index.other | 207 |
| abstract_inverted_index.third | 139, 199 |
| abstract_inverted_index.three | 122 |
| abstract_inverted_index.using | 189 |
| abstract_inverted_index.which | 81, 151, 168, 181 |
| abstract_inverted_index.(RAG), | 80 |
| abstract_inverted_index.across | 121 |
| abstract_inverted_index.answer | 116 |
| abstract_inverted_index.fatwas | 11 |
| abstract_inverted_index.higher | 227 |
| abstract_inverted_index.issue, | 70 |
| abstract_inverted_index.mainly | 46 |
| abstract_inverted_index.method | 140 |
| abstract_inverted_index.model. | 172 |
| abstract_inverted_index.robust | 219 |
| abstract_inverted_index.second | 166 |
| abstract_inverted_index.Islamic | 10, 51, 232 |
| abstract_inverted_index.address | 68 |
| abstract_inverted_index.answer. | 100 |
| abstract_inverted_index.ensures | 156 |
| abstract_inverted_index.improve | 222 |
| abstract_inverted_index.involve | 23 |
| abstract_inverted_index.method, | 167 |
| abstract_inverted_index.metrics | 195 |
| abstract_inverted_index.process | 154 |
| abstract_inverted_index.propose | 72 |
| abstract_inverted_index.reduces | 108 |
| abstract_inverted_index.setups, | 208 |
| abstract_inverted_index.setups: | 123 |
| abstract_inverted_index.stable, | 211 |
| abstract_inverted_index.studies | 43 |
| abstract_inverted_index.systems | 3 |
| abstract_inverted_index.Abstract | 0 |
| abstract_inverted_index.accurate | 25 |
| abstract_inverted_index.advanced | 77 |
| abstract_inverted_index.answers. | 214 |
| abstract_inverted_index.approach | 75 |
| abstract_inverted_index.datasets | 52 |
| abstract_inverted_index.enhanced | 83 |
| abstract_inverted_index.improves | 104, 152 |
| abstract_inverted_index.includes | 145 |
| abstract_inverted_index.increase | 88 |
| abstract_inverted_index.involved | 8 |
| abstract_inverted_index.managing | 29 |
| abstract_inverted_index.precise, | 210 |
| abstract_inverted_index.problems | 22 |
| abstract_inverted_index.relevant | 157, 179 |
| abstract_inverted_index.reliable | 27 |
| abstract_inverted_index.required | 63 |
| abstract_inverted_index.research | 216 |
| abstract_inverted_index.response | 89, 105, 184 |
| abstract_inverted_index.systems, | 57, 225 |
| abstract_inverted_index.systems. | 234 |
| abstract_inverted_index.AI-driven | 223 |
| abstract_inverted_index.conducted | 119 |
| abstract_inverted_index.eliminate | 91 |
| abstract_inverted_index.generated | 40 |
| abstract_inverted_index.improving | 111 |
| abstract_inverted_index.increases | 182 |
| abstract_inverted_index.issuance. | 66 |
| abstract_inverted_index.knowledge | 149 |
| abstract_inverted_index.precision | 60, 228 |
| abstract_inverted_index.providing | 24, 209 |
| abstract_inverted_index.re-ranker | 86, 147, 175, 205 |
| abstract_inverted_index.retrieval | 171 |
| abstract_inverted_index.retrieves | 176 |
| abstract_inverted_index.stability | 37, 106, 185 |
| abstract_inverted_index.utilizing | 76 |
| abstract_inverted_index.BERTScore, | 190 |
| abstract_inverted_index.challenges | 6 |
| abstract_inverted_index.collecting | 48 |
| abstract_inverted_index.complexity | 15 |
| abstract_inverted_index.dependable | 213 |
| abstract_inverted_index.developing | 54 |
| abstract_inverted_index.experiment | 200 |
| abstract_inverted_index.generation | 79 |
| abstract_inverted_index.inaccurate | 32 |
| abstract_inverted_index.prioritize | 94 |
| abstract_inverted_index.re-ranker. | 137 |
| abstract_inverted_index.responses, | 28, 33 |
| abstract_inverted_index.responses. | 41 |
| abstract_inverted_index.retrieval, | 150 |
| abstract_inverted_index.stability, | 90 |
| abstract_inverted_index.Evaluations | 188 |
| abstract_inverted_index.appropriate | 97 |
| abstract_inverted_index.contributes | 217 |
| abstract_inverted_index.enhancement | 102 |
| abstract_inverted_index.experiments | 120 |
| abstract_inverted_index.generation. | 117 |
| abstract_inverted_index.irrelevance | 194 |
| abstract_inverted_index.maintaining | 35 |
| abstract_inverted_index.methodology | 220 |
| abstract_inverted_index.overlooking | 58 |
| abstract_inverted_index.reliability | 62 |
| abstract_inverted_index.sensitivity | 17 |
| abstract_inverted_index.trustworthy | 159 |
| abstract_inverted_index.concentrated | 45 |
| abstract_inverted_index.considerable | 5 |
| abstract_inverted_index.demonstrated | 196 |
| abstract_inverted_index.guaranteeing | 226 |
| abstract_inverted_index.outperformed | 206 |
| abstract_inverted_index.completeness, | 192 |
| abstract_inverted_index.preprocessing | 50 |
| abstract_inverted_index.significantly | 103 |
| abstract_inverted_index.differentiates | 162 |
| abstract_inverted_index.hallucination, | 191 |
| abstract_inverted_index.hallucinations | 30, 109 |
| abstract_inverted_index.hallucinations, | 92 |
| abstract_inverted_index.retrieval-based | 55 |
| abstract_inverted_index.trustworthiness | 230 |
| abstract_inverted_index.trustworthiness. | 187 |
| abstract_inverted_index.retrieval-augmented | 78 |
| abstract_inverted_index.Question–answering | 1 |
| cited_by_percentile_year.max | 95 |
| cited_by_percentile_year.min | 91 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile.value | 0.95078032 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |