Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment Article Swipe
Jiongxiao Wang
,
Jiazhao Li
,
Yiquan Li
,
Xiangyu Qi
,
Muhao Chen
,
Junjie Hu
,
Yixuan Li
,
Bo Li
,
Chaowei Xiao
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2402.14968
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2402.14968
Despite the general capabilities of Large Language Models (LLM), these models still request fine-tuning or adaptation with customized data when meeting specific business demands. However, this process inevitably introduces new threats, particularly against the Fine-tuning based Jailbreak Attack (FJAttack) under the setting of Language-Model-as-a-Service (LMaaS), where the model's safety has been significantly compromised by fine-tuning users' uploaded examples contain just a few harmful examples. Though potential defenses have been proposed that the service providers can integrate safety examples into the fine-tuning dataset to reduce safety issues, such approaches require incorporating a substantial amount of data, making it inefficient. To effectively defend against the FJAttack with limited safety examples under LMaaS, we propose the Backdoor Enhanced Safety Alignment method inspired by an analogy with the concept of backdoor attacks. In particular, service providers will construct prefixed safety examples with a secret prompt, acting as a "backdoor trigger". By integrating prefixed safety examples into the fine-tuning dataset, the subsequent fine-tuning process effectively acts as the "backdoor attack", establishing a strong correlation between the secret prompt and safety generations. Consequently, safe responses are ensured once service providers prepend this secret prompt ahead of any user input during inference. Our comprehensive experiments demonstrate that through the Backdoor Enhanced Safety Alignment with adding as few as 11 prefixed safety examples, the maliciously fine-tuned LLMs will achieve similar safety performance as the original aligned models without harming the benign performance. Furthermore, we also present the effectiveness of our method in a more practical setting where the fine-tuning data consists of both FJAttack examples and the fine-tuning task data.
Related Topics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2402.14968
- https://arxiv.org/pdf/2402.14968
- OA Status
- green
- Cited By
- 2
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4392181875
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4392181875Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2402.14968Digital Object Identifier
- Title
-
Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety AlignmentWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-02-22Full publication date if available
- Authors
-
Jiongxiao Wang, Jiazhao Li, Yiquan Li, Xiangyu Qi, Muhao Chen, Junjie Hu, Yixuan Li, Bo Li, Chaowei XiaoList of authors in order
- Landing page
-
https://arxiv.org/abs/2402.14968Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2402.14968Direct 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/2402.14968Direct OA link when available
- Concepts
-
Backdoor, Computer science, Computer security, BusinessTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 2Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4392181875 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2402.14968 |
| ids.doi | https://doi.org/10.48550/arxiv.2402.14968 |
| ids.openalex | https://openalex.org/W4392181875 |
| fwci | |
| type | preprint |
| title | Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11241 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9970999956130981 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1711 |
| topics[0].subfield.display_name | Signal Processing |
| topics[0].display_name | Advanced Malware Detection Techniques |
| topics[1].id | https://openalex.org/T12034 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9919000267982483 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1710 |
| topics[1].subfield.display_name | Information Systems |
| topics[1].display_name | Digital and Cyber Forensics |
| topics[2].id | https://openalex.org/T11689 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9869999885559082 |
| 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 | Adversarial Robustness in Machine Learning |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2781045450 |
| concepts[0].level | 2 |
| concepts[0].score | 0.995915412902832 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q254569 |
| concepts[0].display_name | Backdoor |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.43683695793151855 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C38652104 |
| concepts[2].level | 1 |
| concepts[2].score | 0.4139575958251953 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[2].display_name | Computer security |
| concepts[3].id | https://openalex.org/C144133560 |
| concepts[3].level | 0 |
| concepts[3].score | 0.3603193461894989 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q4830453 |
| concepts[3].display_name | Business |
| keywords[0].id | https://openalex.org/keywords/backdoor |
| keywords[0].score | 0.995915412902832 |
| keywords[0].display_name | Backdoor |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.43683695793151855 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/computer-security |
| keywords[2].score | 0.4139575958251953 |
| keywords[2].display_name | Computer security |
| keywords[3].id | https://openalex.org/keywords/business |
| keywords[3].score | 0.3603193461894989 |
| keywords[3].display_name | Business |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2402.14968 |
| 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/2402.14968 |
| 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/2402.14968 |
| locations[1].id | doi:10.48550/arxiv.2402.14968 |
| 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.2402.14968 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5009277751 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Jiongxiao Wang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Wang, Jiongxiao |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5023356394 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Jiazhao Li |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Li, Jiazhao |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5063566397 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Yiquan Li |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Li, Yiquan |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5036739334 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Xiangyu Qi |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Qi, Xiangyu |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5102861481 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-0118-3147 |
| authorships[4].author.display_name | Muhao Chen |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Chen, Muhao |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5103151628 |
| authorships[5].author.orcid | https://orcid.org/0009-0009-7622-0011 |
| authorships[5].author.display_name | Junjie Hu |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Hu, Junjie |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5100443482 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-4725-7586 |
| authorships[6].author.display_name | Yixuan Li |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Li, Yixuan |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5100374415 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-3226-388X |
| authorships[7].author.display_name | Bo Li |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Li, Bo |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5005843046 |
| authorships[8].author.orcid | https://orcid.org/0000-0002-7043-4926 |
| authorships[8].author.display_name | Chaowei Xiao |
| authorships[8].author_position | last |
| authorships[8].raw_author_name | Xiao, Chaowei |
| authorships[8].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/2402.14968 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-02-27T00:00:00 |
| display_name | Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11241 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9970999956130981 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1711 |
| primary_topic.subfield.display_name | Signal Processing |
| primary_topic.display_name | Advanced Malware Detection Techniques |
| related_works | https://openalex.org/W2748952813, https://openalex.org/W4320031223, https://openalex.org/W3015678314, https://openalex.org/W4281902577, https://openalex.org/W4200629851, https://openalex.org/W3009072493, https://openalex.org/W4386185023, https://openalex.org/W4317672133, https://openalex.org/W3140988292, https://openalex.org/W4386080799 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 2 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2402.14968 |
| 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/2402.14968 |
| 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/2402.14968 |
| primary_location.id | pmh:oai:arXiv.org:2402.14968 |
| 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/2402.14968 |
| 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/2402.14968 |
| publication_date | 2024-02-22 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 60, 90, 138, 143, 166, 244 |
| abstract_inverted_index.11 | 211 |
| abstract_inverted_index.By | 146 |
| abstract_inverted_index.In | 128 |
| abstract_inverted_index.To | 98 |
| abstract_inverted_index.an | 120 |
| abstract_inverted_index.as | 142, 161, 208, 210, 224 |
| abstract_inverted_index.by | 53, 119 |
| abstract_inverted_index.in | 243 |
| abstract_inverted_index.it | 96 |
| abstract_inverted_index.of | 4, 42, 93, 125, 189, 240, 253 |
| abstract_inverted_index.or | 14 |
| abstract_inverted_index.to | 82 |
| abstract_inverted_index.we | 110, 235 |
| abstract_inverted_index.Our | 195 |
| abstract_inverted_index.and | 173, 257 |
| abstract_inverted_index.any | 190 |
| abstract_inverted_index.are | 179 |
| abstract_inverted_index.can | 74 |
| abstract_inverted_index.few | 61, 209 |
| abstract_inverted_index.has | 49 |
| abstract_inverted_index.new | 29 |
| abstract_inverted_index.our | 241 |
| abstract_inverted_index.the | 1, 33, 40, 46, 71, 79, 102, 112, 123, 152, 155, 162, 170, 201, 215, 225, 231, 238, 249, 258 |
| abstract_inverted_index.LLMs | 218 |
| abstract_inverted_index.acts | 160 |
| abstract_inverted_index.also | 236 |
| abstract_inverted_index.been | 50, 68 |
| abstract_inverted_index.both | 254 |
| abstract_inverted_index.data | 18, 251 |
| abstract_inverted_index.have | 67 |
| abstract_inverted_index.into | 78, 151 |
| abstract_inverted_index.just | 59 |
| abstract_inverted_index.more | 245 |
| abstract_inverted_index.once | 181 |
| abstract_inverted_index.safe | 177 |
| abstract_inverted_index.such | 86 |
| abstract_inverted_index.task | 260 |
| abstract_inverted_index.that | 70, 199 |
| abstract_inverted_index.this | 25, 185 |
| abstract_inverted_index.user | 191 |
| abstract_inverted_index.when | 19 |
| abstract_inverted_index.will | 132, 219 |
| abstract_inverted_index.with | 16, 104, 122, 137, 206 |
| abstract_inverted_index.Large | 5 |
| abstract_inverted_index.ahead | 188 |
| abstract_inverted_index.based | 35 |
| abstract_inverted_index.data, | 94 |
| abstract_inverted_index.data. | 261 |
| abstract_inverted_index.input | 192 |
| abstract_inverted_index.still | 11 |
| abstract_inverted_index.these | 9 |
| abstract_inverted_index.under | 39, 108 |
| abstract_inverted_index.where | 45, 248 |
| abstract_inverted_index.(LLM), | 8 |
| abstract_inverted_index.Attack | 37 |
| abstract_inverted_index.LMaaS, | 109 |
| abstract_inverted_index.Models | 7 |
| abstract_inverted_index.Safety | 115, 204 |
| abstract_inverted_index.Though | 64 |
| abstract_inverted_index.acting | 141 |
| abstract_inverted_index.adding | 207 |
| abstract_inverted_index.amount | 92 |
| abstract_inverted_index.benign | 232 |
| abstract_inverted_index.defend | 100 |
| abstract_inverted_index.during | 193 |
| abstract_inverted_index.making | 95 |
| abstract_inverted_index.method | 117, 242 |
| abstract_inverted_index.models | 10, 228 |
| abstract_inverted_index.prompt | 172, 187 |
| abstract_inverted_index.reduce | 83 |
| abstract_inverted_index.safety | 48, 76, 84, 106, 135, 149, 174, 213, 222 |
| abstract_inverted_index.secret | 139, 171, 186 |
| abstract_inverted_index.strong | 167 |
| abstract_inverted_index.users' | 55 |
| abstract_inverted_index.Despite | 0 |
| abstract_inverted_index.achieve | 220 |
| abstract_inverted_index.against | 32, 101 |
| abstract_inverted_index.aligned | 227 |
| abstract_inverted_index.analogy | 121 |
| abstract_inverted_index.between | 169 |
| abstract_inverted_index.concept | 124 |
| abstract_inverted_index.contain | 58 |
| abstract_inverted_index.dataset | 81 |
| abstract_inverted_index.ensured | 180 |
| abstract_inverted_index.general | 2 |
| abstract_inverted_index.harmful | 62 |
| abstract_inverted_index.harming | 230 |
| abstract_inverted_index.issues, | 85 |
| abstract_inverted_index.limited | 105 |
| abstract_inverted_index.meeting | 20 |
| abstract_inverted_index.model's | 47 |
| abstract_inverted_index.prepend | 184 |
| abstract_inverted_index.present | 237 |
| abstract_inverted_index.process | 26, 158 |
| abstract_inverted_index.prompt, | 140 |
| abstract_inverted_index.propose | 111 |
| abstract_inverted_index.request | 12 |
| abstract_inverted_index.require | 88 |
| abstract_inverted_index.service | 72, 130, 182 |
| abstract_inverted_index.setting | 41, 247 |
| abstract_inverted_index.similar | 221 |
| abstract_inverted_index.through | 200 |
| abstract_inverted_index.without | 229 |
| abstract_inverted_index.(LMaaS), | 44 |
| abstract_inverted_index.Backdoor | 113, 202 |
| abstract_inverted_index.Enhanced | 114, 203 |
| abstract_inverted_index.FJAttack | 103, 255 |
| abstract_inverted_index.However, | 24 |
| abstract_inverted_index.Language | 6 |
| abstract_inverted_index.attack", | 164 |
| abstract_inverted_index.attacks. | 127 |
| abstract_inverted_index.backdoor | 126 |
| abstract_inverted_index.business | 22 |
| abstract_inverted_index.consists | 252 |
| abstract_inverted_index.dataset, | 154 |
| abstract_inverted_index.defenses | 66 |
| abstract_inverted_index.demands. | 23 |
| abstract_inverted_index.examples | 57, 77, 107, 136, 150, 256 |
| abstract_inverted_index.inspired | 118 |
| abstract_inverted_index.original | 226 |
| abstract_inverted_index.prefixed | 134, 148, 212 |
| abstract_inverted_index.proposed | 69 |
| abstract_inverted_index.specific | 21 |
| abstract_inverted_index.threats, | 30 |
| abstract_inverted_index.uploaded | 56 |
| abstract_inverted_index."backdoor | 144, 163 |
| abstract_inverted_index.Alignment | 116, 205 |
| abstract_inverted_index.Jailbreak | 36 |
| abstract_inverted_index.construct | 133 |
| abstract_inverted_index.examples, | 214 |
| abstract_inverted_index.examples. | 63 |
| abstract_inverted_index.integrate | 75 |
| abstract_inverted_index.potential | 65 |
| abstract_inverted_index.practical | 246 |
| abstract_inverted_index.providers | 73, 131, 183 |
| abstract_inverted_index.responses | 178 |
| abstract_inverted_index.trigger". | 145 |
| abstract_inverted_index.(FJAttack) | 38 |
| abstract_inverted_index.adaptation | 15 |
| abstract_inverted_index.approaches | 87 |
| abstract_inverted_index.customized | 17 |
| abstract_inverted_index.fine-tuned | 217 |
| abstract_inverted_index.inevitably | 27 |
| abstract_inverted_index.inference. | 194 |
| abstract_inverted_index.introduces | 28 |
| abstract_inverted_index.subsequent | 156 |
| abstract_inverted_index.Fine-tuning | 34 |
| abstract_inverted_index.compromised | 52 |
| abstract_inverted_index.correlation | 168 |
| abstract_inverted_index.demonstrate | 198 |
| abstract_inverted_index.effectively | 99, 159 |
| abstract_inverted_index.experiments | 197 |
| abstract_inverted_index.fine-tuning | 13, 54, 80, 153, 157, 250, 259 |
| abstract_inverted_index.integrating | 147 |
| abstract_inverted_index.maliciously | 216 |
| abstract_inverted_index.particular, | 129 |
| abstract_inverted_index.performance | 223 |
| abstract_inverted_index.substantial | 91 |
| abstract_inverted_index.Furthermore, | 234 |
| abstract_inverted_index.capabilities | 3 |
| abstract_inverted_index.establishing | 165 |
| abstract_inverted_index.generations. | 175 |
| abstract_inverted_index.inefficient. | 97 |
| abstract_inverted_index.particularly | 31 |
| abstract_inverted_index.performance. | 233 |
| abstract_inverted_index.Consequently, | 176 |
| abstract_inverted_index.comprehensive | 196 |
| abstract_inverted_index.effectiveness | 239 |
| abstract_inverted_index.incorporating | 89 |
| abstract_inverted_index.significantly | 51 |
| abstract_inverted_index.Language-Model-as-a-Service | 43 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 9 |
| citation_normalized_percentile |