Attributing Fair Decisions with Attention Interventions Article Swipe
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.18653/v1/2022.trustnlp-1.2
The widespread use of Artificial Intelligence (AI) in consequential domains, such as health-care and parole decision-making systems, has drawn intense scrutiny on the fairness of these methods. However, ensuring fairness is often insufficient as the rationale for a contentious decision needs to be audited, understood, and defended. We propose that the attention mechanism can be used to ensure fair outcomes while simultaneously providing feature attributions to account for how a decision was made. Toward this goal, we design an attention-based model that can be leveraged as an attribution framework. It can identify features responsible for both performance and fairness of the model through attention interventions and attention weight manipulation. Using this attribution framework, we then design a post-processing bias mitigation strategy and compare it with a suite of baselines. We demonstrate the versatility of our approach by conducting experiments on two distinct data types, tabular and textual.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.18653/v1/2022.trustnlp-1.2
- https://aclanthology.org/2022.trustnlp-1.2.pdf
- OA Status
- gold
- Cited By
- 19
- References
- 40
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3198320185
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3198320185Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.18653/v1/2022.trustnlp-1.2Digital Object Identifier
- Title
-
Attributing Fair Decisions with Attention InterventionsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-01-01Full publication date if available
- Authors
-
Ninareh Mehrabi, Umang Gupta, Fred Morstatter, Greg Ver Steeg, Aram GalstyanList of authors in order
- Landing page
-
https://doi.org/10.18653/v1/2022.trustnlp-1.2Publisher landing page
- PDF URL
-
https://aclanthology.org/2022.trustnlp-1.2.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://aclanthology.org/2022.trustnlp-1.2.pdfDirect OA link when available
- Concepts
-
Scrutiny, Attribution, Computer science, Psychological intervention, Suite, Audit, Risk analysis (engineering), Artificial intelligence, Psychology, Social psychology, Business, Political science, Accounting, Psychiatry, LawTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
19Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1, 2024: 3, 2023: 14, 2022: 1Per-year citation counts (last 5 years)
- References (count)
-
40Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3198320185 |
|---|---|
| doi | https://doi.org/10.18653/v1/2022.trustnlp-1.2 |
| ids.doi | https://doi.org/10.18653/v1/2022.trustnlp-1.2 |
| ids.mag | 3198320185 |
| ids.openalex | https://openalex.org/W3198320185 |
| fwci | 5.02391954 |
| type | preprint |
| title | Attributing Fair Decisions with Attention Interventions |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10883 |
| topics[0].field.id | https://openalex.org/fields/33 |
| topics[0].field.display_name | Social Sciences |
| topics[0].score | 0.9990000128746033 |
| topics[0].domain.id | https://openalex.org/domains/2 |
| topics[0].domain.display_name | Social Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/3311 |
| topics[0].subfield.display_name | Safety Research |
| topics[0].display_name | Ethics and Social Impacts of AI |
| topics[1].id | https://openalex.org/T12026 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9940999746322632 |
| 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 | Explainable Artificial Intelligence (XAI) |
| topics[2].id | https://openalex.org/T11636 |
| topics[2].field.id | https://openalex.org/fields/27 |
| topics[2].field.display_name | Medicine |
| topics[2].score | 0.9853000044822693 |
| topics[2].domain.id | https://openalex.org/domains/4 |
| topics[2].domain.display_name | Health Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2718 |
| topics[2].subfield.display_name | Health Informatics |
| topics[2].display_name | Artificial Intelligence in Healthcare and Education |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2776050585 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8093748092651367 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q7439360 |
| concepts[0].display_name | Scrutiny |
| concepts[1].id | https://openalex.org/C143299363 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7440925240516663 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q900584 |
| concepts[1].display_name | Attribution |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.6668825149536133 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C27415008 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6529560089111328 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q7256382 |
| concepts[3].display_name | Psychological intervention |
| concepts[4].id | https://openalex.org/C79581498 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5222102999687195 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1367530 |
| concepts[4].display_name | Suite |
| concepts[5].id | https://openalex.org/C199521495 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4665975570678711 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q181487 |
| concepts[5].display_name | Audit |
| concepts[6].id | https://openalex.org/C112930515 |
| concepts[6].level | 1 |
| concepts[6].score | 0.3667190670967102 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q4389547 |
| concepts[6].display_name | Risk analysis (engineering) |
| concepts[7].id | https://openalex.org/C154945302 |
| concepts[7].level | 1 |
| concepts[7].score | 0.33659207820892334 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[7].display_name | Artificial intelligence |
| concepts[8].id | https://openalex.org/C15744967 |
| concepts[8].level | 0 |
| concepts[8].score | 0.28521543741226196 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[8].display_name | Psychology |
| concepts[9].id | https://openalex.org/C77805123 |
| concepts[9].level | 1 |
| concepts[9].score | 0.1605874001979828 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q161272 |
| concepts[9].display_name | Social psychology |
| concepts[10].id | https://openalex.org/C144133560 |
| concepts[10].level | 0 |
| concepts[10].score | 0.09286642074584961 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q4830453 |
| concepts[10].display_name | Business |
| concepts[11].id | https://openalex.org/C17744445 |
| concepts[11].level | 0 |
| concepts[11].score | 0.07481792569160461 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[11].display_name | Political science |
| concepts[12].id | https://openalex.org/C121955636 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q4116214 |
| concepts[12].display_name | Accounting |
| concepts[13].id | https://openalex.org/C118552586 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q7867 |
| concepts[13].display_name | Psychiatry |
| concepts[14].id | https://openalex.org/C199539241 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[14].display_name | Law |
| keywords[0].id | https://openalex.org/keywords/scrutiny |
| keywords[0].score | 0.8093748092651367 |
| keywords[0].display_name | Scrutiny |
| keywords[1].id | https://openalex.org/keywords/attribution |
| keywords[1].score | 0.7440925240516663 |
| keywords[1].display_name | Attribution |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.6668825149536133 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/psychological-intervention |
| keywords[3].score | 0.6529560089111328 |
| keywords[3].display_name | Psychological intervention |
| keywords[4].id | https://openalex.org/keywords/suite |
| keywords[4].score | 0.5222102999687195 |
| keywords[4].display_name | Suite |
| keywords[5].id | https://openalex.org/keywords/audit |
| keywords[5].score | 0.4665975570678711 |
| keywords[5].display_name | Audit |
| keywords[6].id | https://openalex.org/keywords/risk-analysis |
| keywords[6].score | 0.3667190670967102 |
| keywords[6].display_name | Risk analysis (engineering) |
| keywords[7].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[7].score | 0.33659207820892334 |
| keywords[7].display_name | Artificial intelligence |
| keywords[8].id | https://openalex.org/keywords/psychology |
| keywords[8].score | 0.28521543741226196 |
| keywords[8].display_name | Psychology |
| keywords[9].id | https://openalex.org/keywords/social-psychology |
| keywords[9].score | 0.1605874001979828 |
| keywords[9].display_name | Social psychology |
| keywords[10].id | https://openalex.org/keywords/business |
| keywords[10].score | 0.09286642074584961 |
| keywords[10].display_name | Business |
| keywords[11].id | https://openalex.org/keywords/political-science |
| keywords[11].score | 0.07481792569160461 |
| keywords[11].display_name | Political science |
| language | en |
| locations[0].id | doi:10.18653/v1/2022.trustnlp-1.2 |
| locations[0].is_oa | True |
| locations[0].source | |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://aclanthology.org/2022.trustnlp-1.2.pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-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 | Proceedings of the 2nd Workshop on Trustworthy Natural Language Processing (TrustNLP 2022) |
| locations[0].landing_page_url | https://doi.org/10.18653/v1/2022.trustnlp-1.2 |
| indexed_in | crossref |
| authorships[0].author.id | https://openalex.org/A5056269049 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Ninareh Mehrabi |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I1174212 |
| authorships[0].affiliations[0].raw_affiliation_string | Information Sciences Institute, University of Southern California |
| authorships[0].institutions[0].id | https://openalex.org/I1174212 |
| authorships[0].institutions[0].ror | https://ror.org/03taz7m60 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I1174212 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | University of Southern California |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Ninareh Mehrabi |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Information Sciences Institute, University of Southern California |
| authorships[1].author.id | https://openalex.org/A5081316458 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-1263-8813 |
| authorships[1].author.display_name | Umang Gupta |
| authorships[1].countries | US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I1174212 |
| authorships[1].affiliations[0].raw_affiliation_string | Information Sciences Institute, University of Southern California |
| authorships[1].institutions[0].id | https://openalex.org/I1174212 |
| authorships[1].institutions[0].ror | https://ror.org/03taz7m60 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I1174212 |
| authorships[1].institutions[0].country_code | US |
| authorships[1].institutions[0].display_name | University of Southern California |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Umang Gupta |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Information Sciences Institute, University of Southern California |
| authorships[2].author.id | https://openalex.org/A5002709735 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-0247-4328 |
| authorships[2].author.display_name | Fred Morstatter |
| authorships[2].countries | US |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I1174212 |
| authorships[2].affiliations[0].raw_affiliation_string | Information Sciences Institute, University of Southern California |
| authorships[2].institutions[0].id | https://openalex.org/I1174212 |
| authorships[2].institutions[0].ror | https://ror.org/03taz7m60 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I1174212 |
| authorships[2].institutions[0].country_code | US |
| authorships[2].institutions[0].display_name | University of Southern California |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Fred Morstatter |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Information Sciences Institute, University of Southern California |
| authorships[3].author.id | https://openalex.org/A5075920466 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-0793-141X |
| authorships[3].author.display_name | Greg Ver Steeg |
| authorships[3].countries | US |
| authorships[3].affiliations[0].institution_ids | https://openalex.org/I1174212 |
| authorships[3].affiliations[0].raw_affiliation_string | Information Sciences Institute, University of Southern California |
| authorships[3].institutions[0].id | https://openalex.org/I1174212 |
| authorships[3].institutions[0].ror | https://ror.org/03taz7m60 |
| authorships[3].institutions[0].type | education |
| authorships[3].institutions[0].lineage | https://openalex.org/I1174212 |
| authorships[3].institutions[0].country_code | US |
| authorships[3].institutions[0].display_name | University of Southern California |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Greg Ver Steeg |
| authorships[3].is_corresponding | False |
| authorships[3].raw_affiliation_strings | Information Sciences Institute, University of Southern California |
| authorships[4].author.id | https://openalex.org/A5101715504 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-4215-0886 |
| authorships[4].author.display_name | Aram Galstyan |
| authorships[4].countries | US |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I1174212 |
| authorships[4].affiliations[0].raw_affiliation_string | Information Sciences Institute, University of Southern California |
| authorships[4].institutions[0].id | https://openalex.org/I1174212 |
| authorships[4].institutions[0].ror | https://ror.org/03taz7m60 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I1174212 |
| authorships[4].institutions[0].country_code | US |
| authorships[4].institutions[0].display_name | University of Southern California |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Aram Galstyan |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Information Sciences Institute, University of Southern California |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://aclanthology.org/2022.trustnlp-1.2.pdf |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Attributing Fair Decisions with Attention Interventions |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T10883 |
| primary_topic.field.id | https://openalex.org/fields/33 |
| primary_topic.field.display_name | Social Sciences |
| primary_topic.score | 0.9990000128746033 |
| primary_topic.domain.id | https://openalex.org/domains/2 |
| primary_topic.domain.display_name | Social Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/3311 |
| primary_topic.subfield.display_name | Safety Research |
| primary_topic.display_name | Ethics and Social Impacts of AI |
| related_works | https://openalex.org/W1987888524, https://openalex.org/W2415594679, https://openalex.org/W2111385166, https://openalex.org/W2119108885, https://openalex.org/W3190981800, https://openalex.org/W2967105077, https://openalex.org/W2230884280, https://openalex.org/W1969053466, https://openalex.org/W2082427261, https://openalex.org/W2264921115 |
| cited_by_count | 19 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 3 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 14 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 1 |
| locations_count | 1 |
| best_oa_location.id | doi:10.18653/v1/2022.trustnlp-1.2 |
| best_oa_location.is_oa | True |
| best_oa_location.source | |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://aclanthology.org/2022.trustnlp-1.2.pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | proceedings-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 | Proceedings of the 2nd Workshop on Trustworthy Natural Language Processing (TrustNLP 2022) |
| best_oa_location.landing_page_url | https://doi.org/10.18653/v1/2022.trustnlp-1.2 |
| primary_location.id | doi:10.18653/v1/2022.trustnlp-1.2 |
| primary_location.is_oa | True |
| primary_location.source | |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://aclanthology.org/2022.trustnlp-1.2.pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-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 | Proceedings of the 2nd Workshop on Trustworthy Natural Language Processing (TrustNLP 2022) |
| primary_location.landing_page_url | https://doi.org/10.18653/v1/2022.trustnlp-1.2 |
| publication_date | 2022-01-01 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W3120740533, https://openalex.org/W3105536512, https://openalex.org/W3173593876, https://openalex.org/W2550530154, https://openalex.org/W2517194566, https://openalex.org/W2899477140, https://openalex.org/W2951025380, https://openalex.org/W2904539038, https://openalex.org/W3024669037, https://openalex.org/W2950768109, https://openalex.org/W2530395818, https://openalex.org/W1819662813, https://openalex.org/W2962790618, https://openalex.org/W2100960835, https://openalex.org/W3000576676, https://openalex.org/W2950029751, https://openalex.org/W2934842096, https://openalex.org/W4385245566, https://openalex.org/W3005086430, https://openalex.org/W2626778328, https://openalex.org/W3004315562, https://openalex.org/W1518830021, https://openalex.org/W1904875463, https://openalex.org/W2147427185, https://openalex.org/W3035615001, https://openalex.org/W2970726176, https://openalex.org/W3123374861, https://openalex.org/W2909212904, https://openalex.org/W3181414820, https://openalex.org/W2963926704, https://openalex.org/W4293769992, https://openalex.org/W2963394878, https://openalex.org/W3030081171, https://openalex.org/W2949200088, https://openalex.org/W3023309920, https://openalex.org/W3104142662, https://openalex.org/W1961345416, https://openalex.org/W3173787059, https://openalex.org/W2948140294, https://openalex.org/W2998503299 |
| referenced_works_count | 40 |
| abstract_inverted_index.a | 37, 69, 116, 125 |
| abstract_inverted_index.It | 89 |
| abstract_inverted_index.We | 47, 129 |
| abstract_inverted_index.an | 78, 86 |
| abstract_inverted_index.as | 11, 33, 85 |
| abstract_inverted_index.be | 42, 54, 83 |
| abstract_inverted_index.by | 136 |
| abstract_inverted_index.in | 7 |
| abstract_inverted_index.is | 30 |
| abstract_inverted_index.it | 123 |
| abstract_inverted_index.of | 3, 24, 99, 127, 133 |
| abstract_inverted_index.on | 21, 139 |
| abstract_inverted_index.to | 41, 56, 65 |
| abstract_inverted_index.we | 76, 113 |
| abstract_inverted_index.The | 0 |
| abstract_inverted_index.and | 13, 45, 97, 105, 121, 145 |
| abstract_inverted_index.can | 53, 82, 90 |
| abstract_inverted_index.for | 36, 67, 94 |
| abstract_inverted_index.has | 17 |
| abstract_inverted_index.how | 68 |
| abstract_inverted_index.our | 134 |
| abstract_inverted_index.the | 22, 34, 50, 100, 131 |
| abstract_inverted_index.two | 140 |
| abstract_inverted_index.use | 2 |
| abstract_inverted_index.was | 71 |
| abstract_inverted_index.(AI) | 6 |
| abstract_inverted_index.bias | 118 |
| abstract_inverted_index.both | 95 |
| abstract_inverted_index.data | 142 |
| abstract_inverted_index.fair | 58 |
| abstract_inverted_index.such | 10 |
| abstract_inverted_index.that | 49, 81 |
| abstract_inverted_index.then | 114 |
| abstract_inverted_index.this | 74, 110 |
| abstract_inverted_index.used | 55 |
| abstract_inverted_index.with | 124 |
| abstract_inverted_index.Using | 109 |
| abstract_inverted_index.drawn | 18 |
| abstract_inverted_index.goal, | 75 |
| abstract_inverted_index.made. | 72 |
| abstract_inverted_index.model | 80, 101 |
| abstract_inverted_index.needs | 40 |
| abstract_inverted_index.often | 31 |
| abstract_inverted_index.suite | 126 |
| abstract_inverted_index.these | 25 |
| abstract_inverted_index.while | 60 |
| abstract_inverted_index.Toward | 73 |
| abstract_inverted_index.design | 77, 115 |
| abstract_inverted_index.ensure | 57 |
| abstract_inverted_index.parole | 14 |
| abstract_inverted_index.types, | 143 |
| abstract_inverted_index.weight | 107 |
| abstract_inverted_index.account | 66 |
| abstract_inverted_index.compare | 122 |
| abstract_inverted_index.feature | 63 |
| abstract_inverted_index.intense | 19 |
| abstract_inverted_index.propose | 48 |
| abstract_inverted_index.tabular | 144 |
| abstract_inverted_index.through | 102 |
| abstract_inverted_index.However, | 27 |
| abstract_inverted_index.approach | 135 |
| abstract_inverted_index.audited, | 43 |
| abstract_inverted_index.decision | 39, 70 |
| abstract_inverted_index.distinct | 141 |
| abstract_inverted_index.domains, | 9 |
| abstract_inverted_index.ensuring | 28 |
| abstract_inverted_index.fairness | 23, 29, 98 |
| abstract_inverted_index.features | 92 |
| abstract_inverted_index.identify | 91 |
| abstract_inverted_index.methods. | 26 |
| abstract_inverted_index.outcomes | 59 |
| abstract_inverted_index.scrutiny | 20 |
| abstract_inverted_index.strategy | 120 |
| abstract_inverted_index.systems, | 16 |
| abstract_inverted_index.textual. | 146 |
| abstract_inverted_index.attention | 51, 103, 106 |
| abstract_inverted_index.defended. | 46 |
| abstract_inverted_index.leveraged | 84 |
| abstract_inverted_index.mechanism | 52 |
| abstract_inverted_index.providing | 62 |
| abstract_inverted_index.rationale | 35 |
| abstract_inverted_index.Artificial | 4 |
| abstract_inverted_index.baselines. | 128 |
| abstract_inverted_index.conducting | 137 |
| abstract_inverted_index.framework, | 112 |
| abstract_inverted_index.framework. | 88 |
| abstract_inverted_index.mitigation | 119 |
| abstract_inverted_index.widespread | 1 |
| abstract_inverted_index.attribution | 87, 111 |
| abstract_inverted_index.contentious | 38 |
| abstract_inverted_index.demonstrate | 130 |
| abstract_inverted_index.experiments | 138 |
| abstract_inverted_index.health-care | 12 |
| abstract_inverted_index.performance | 96 |
| abstract_inverted_index.responsible | 93 |
| abstract_inverted_index.understood, | 44 |
| abstract_inverted_index.versatility | 132 |
| abstract_inverted_index.Intelligence | 5 |
| abstract_inverted_index.attributions | 64 |
| abstract_inverted_index.insufficient | 32 |
| abstract_inverted_index.consequential | 8 |
| abstract_inverted_index.interventions | 104 |
| abstract_inverted_index.manipulation. | 108 |
| abstract_inverted_index.simultaneously | 61 |
| abstract_inverted_index.attention-based | 79 |
| abstract_inverted_index.decision-making | 15 |
| abstract_inverted_index.post-processing | 117 |
| cited_by_percentile_year.max | 99 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 5 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/16 |
| sustainable_development_goals[0].score | 0.8199999928474426 |
| sustainable_development_goals[0].display_name | Peace, Justice and strong institutions |
| citation_normalized_percentile.value | 0.93906414 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |