Best of Both Worlds: A Hybrid Approach for Multi-Hop Explanation with Declarative Facts Article Swipe
Shane Storks
,
Qiaozi Gao
,
Aishwarya Reganti
,
Govind Thattai
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2201.02740
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2201.02740
Language-enabled AI systems can answer complex, multi-hop questions to high accuracy, but supporting answers with evidence is a more challenging task which is important for the transparency and trustworthiness to users. Prior work in this area typically makes a trade-off between efficiency and accuracy; state-of-the-art deep neural network systems are too cumbersome to be useful in large-scale applications, while the fastest systems lack reliability. In this work, we integrate fast syntactic methods with powerful semantic methods for multi-hop explanation generation based on declarative facts. Our best system, which learns a lightweight operation to simulate multi-hop reasoning over pieces of evidence and fine-tunes language models to re-rank generated explanation chains, outperforms a purely syntactic baseline from prior work by up to 7% in gold explanation retrieval rate.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2201.02740
- https://arxiv.org/pdf/2201.02740
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4226361228
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4226361228Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2201.02740Digital Object Identifier
- Title
-
Best of Both Worlds: A Hybrid Approach for Multi-Hop Explanation with Declarative FactsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-12-17Full publication date if available
- Authors
-
Shane Storks, Qiaozi Gao, Aishwarya Reganti, Govind ThattaiList of authors in order
- Landing page
-
https://arxiv.org/abs/2201.02740Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2201.02740Direct 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/2201.02740Direct OA link when available
- Concepts
-
Computer science, Baseline (sea), Artificial intelligence, Transparency (behavior), Hop (telecommunications), Trustworthiness, Reliability (semiconductor), Machine learning, Natural language processing, Power (physics), Geology, Quantum mechanics, Oceanography, Computer security, Computer network, PhysicsTop 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)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4226361228 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2201.02740 |
| ids.doi | https://doi.org/10.48550/arxiv.2201.02740 |
| ids.openalex | https://openalex.org/W4226361228 |
| fwci | |
| type | preprint |
| title | Best of Both Worlds: A Hybrid Approach for Multi-Hop Explanation with Declarative Facts |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10028 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9966999888420105 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Topic Modeling |
| topics[1].id | https://openalex.org/T12026 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9918000102043152 |
| 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/T10181 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9300000071525574 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Natural Language Processing Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8534116744995117 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C12725497 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5103294253349304 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q810247 |
| concepts[1].display_name | Baseline (sea) |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.49956369400024414 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C2780233690 |
| concepts[3].level | 2 |
| concepts[3].score | 0.4992363452911377 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q535347 |
| concepts[3].display_name | Transparency (behavior) |
| concepts[4].id | https://openalex.org/C25906391 |
| concepts[4].level | 2 |
| concepts[4].score | 0.4488542079925537 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1432381 |
| concepts[4].display_name | Hop (telecommunications) |
| concepts[5].id | https://openalex.org/C153701036 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4338507652282715 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q659974 |
| concepts[5].display_name | Trustworthiness |
| concepts[6].id | https://openalex.org/C43214815 |
| concepts[6].level | 3 |
| concepts[6].score | 0.41483357548713684 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q7310987 |
| concepts[6].display_name | Reliability (semiconductor) |
| concepts[7].id | https://openalex.org/C119857082 |
| concepts[7].level | 1 |
| concepts[7].score | 0.4120427966117859 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[7].display_name | Machine learning |
| concepts[8].id | https://openalex.org/C204321447 |
| concepts[8].level | 1 |
| concepts[8].score | 0.396605521440506 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[8].display_name | Natural language processing |
| concepts[9].id | https://openalex.org/C163258240 |
| concepts[9].level | 2 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q25342 |
| concepts[9].display_name | Power (physics) |
| concepts[10].id | https://openalex.org/C127313418 |
| concepts[10].level | 0 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q1069 |
| concepts[10].display_name | Geology |
| concepts[11].id | https://openalex.org/C62520636 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[11].display_name | Quantum mechanics |
| concepts[12].id | https://openalex.org/C111368507 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q43518 |
| concepts[12].display_name | Oceanography |
| concepts[13].id | https://openalex.org/C38652104 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q3510521 |
| concepts[13].display_name | Computer security |
| concepts[14].id | https://openalex.org/C31258907 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q1301371 |
| concepts[14].display_name | Computer network |
| concepts[15].id | https://openalex.org/C121332964 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[15].display_name | Physics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8534116744995117 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/baseline |
| keywords[1].score | 0.5103294253349304 |
| keywords[1].display_name | Baseline (sea) |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.49956369400024414 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/transparency |
| keywords[3].score | 0.4992363452911377 |
| keywords[3].display_name | Transparency (behavior) |
| keywords[4].id | https://openalex.org/keywords/hop |
| keywords[4].score | 0.4488542079925537 |
| keywords[4].display_name | Hop (telecommunications) |
| keywords[5].id | https://openalex.org/keywords/trustworthiness |
| keywords[5].score | 0.4338507652282715 |
| keywords[5].display_name | Trustworthiness |
| keywords[6].id | https://openalex.org/keywords/reliability |
| keywords[6].score | 0.41483357548713684 |
| keywords[6].display_name | Reliability (semiconductor) |
| keywords[7].id | https://openalex.org/keywords/machine-learning |
| keywords[7].score | 0.4120427966117859 |
| keywords[7].display_name | Machine learning |
| keywords[8].id | https://openalex.org/keywords/natural-language-processing |
| keywords[8].score | 0.396605521440506 |
| keywords[8].display_name | Natural language processing |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2201.02740 |
| 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/2201.02740 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| 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/2201.02740 |
| locations[1].id | doi:10.48550/arxiv.2201.02740 |
| 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.2201.02740 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5001093904 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-5826-4426 |
| authorships[0].author.display_name | Shane Storks |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Storks, Shane |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5077622605 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-5403-0796 |
| authorships[1].author.display_name | Qiaozi Gao |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Gao, Qiaozi |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5057785836 |
| authorships[2].author.orcid | https://orcid.org/0009-0005-0989-1406 |
| authorships[2].author.display_name | Aishwarya Reganti |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Reganti, Aishwarya |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5088771920 |
| authorships[3].author.orcid | https://orcid.org/0009-0005-1010-8896 |
| authorships[3].author.display_name | Govind Thattai |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Thattai, Govind |
| 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/2201.02740 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2022-05-05T00:00:00 |
| display_name | Best of Both Worlds: A Hybrid Approach for Multi-Hop Explanation with Declarative Facts |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10028 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9966999888420105 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Topic Modeling |
| related_works | https://openalex.org/W2383111961, https://openalex.org/W2365952365, https://openalex.org/W2352448290, https://openalex.org/W2380820513, https://openalex.org/W2913146933, https://openalex.org/W2372385138, https://openalex.org/W4296359239, https://openalex.org/W2101155126, https://openalex.org/W2043093291, https://openalex.org/W2363545964 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2201.02740 |
| 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/2201.02740 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| 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/2201.02740 |
| primary_location.id | pmh:oai:arXiv.org:2201.02740 |
| 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/2201.02740 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| 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/2201.02740 |
| publication_date | 2021-12-17 |
| publication_year | 2021 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 17, 38, 89, 110 |
| abstract_inverted_index.7% | 120 |
| abstract_inverted_index.AI | 1 |
| abstract_inverted_index.In | 64 |
| abstract_inverted_index.be | 53 |
| abstract_inverted_index.by | 117 |
| abstract_inverted_index.in | 33, 55, 121 |
| abstract_inverted_index.is | 16, 22 |
| abstract_inverted_index.of | 98 |
| abstract_inverted_index.on | 81 |
| abstract_inverted_index.to | 8, 29, 52, 92, 104, 119 |
| abstract_inverted_index.up | 118 |
| abstract_inverted_index.we | 67 |
| abstract_inverted_index.Our | 84 |
| abstract_inverted_index.and | 27, 42, 100 |
| abstract_inverted_index.are | 49 |
| abstract_inverted_index.but | 11 |
| abstract_inverted_index.can | 3 |
| abstract_inverted_index.for | 24, 76 |
| abstract_inverted_index.the | 25, 59 |
| abstract_inverted_index.too | 50 |
| abstract_inverted_index.area | 35 |
| abstract_inverted_index.best | 85 |
| abstract_inverted_index.deep | 45 |
| abstract_inverted_index.fast | 69 |
| abstract_inverted_index.from | 114 |
| abstract_inverted_index.gold | 122 |
| abstract_inverted_index.high | 9 |
| abstract_inverted_index.lack | 62 |
| abstract_inverted_index.more | 18 |
| abstract_inverted_index.over | 96 |
| abstract_inverted_index.task | 20 |
| abstract_inverted_index.this | 34, 65 |
| abstract_inverted_index.with | 14, 72 |
| abstract_inverted_index.work | 32, 116 |
| abstract_inverted_index.Prior | 31 |
| abstract_inverted_index.based | 80 |
| abstract_inverted_index.makes | 37 |
| abstract_inverted_index.prior | 115 |
| abstract_inverted_index.rate. | 125 |
| abstract_inverted_index.which | 21, 87 |
| abstract_inverted_index.while | 58 |
| abstract_inverted_index.work, | 66 |
| abstract_inverted_index.answer | 4 |
| abstract_inverted_index.facts. | 83 |
| abstract_inverted_index.learns | 88 |
| abstract_inverted_index.models | 103 |
| abstract_inverted_index.neural | 46 |
| abstract_inverted_index.pieces | 97 |
| abstract_inverted_index.purely | 111 |
| abstract_inverted_index.useful | 54 |
| abstract_inverted_index.users. | 30 |
| abstract_inverted_index.answers | 13 |
| abstract_inverted_index.between | 40 |
| abstract_inverted_index.chains, | 108 |
| abstract_inverted_index.fastest | 60 |
| abstract_inverted_index.methods | 71, 75 |
| abstract_inverted_index.network | 47 |
| abstract_inverted_index.re-rank | 105 |
| abstract_inverted_index.system, | 86 |
| abstract_inverted_index.systems | 2, 48, 61 |
| abstract_inverted_index.baseline | 113 |
| abstract_inverted_index.complex, | 5 |
| abstract_inverted_index.evidence | 15, 99 |
| abstract_inverted_index.language | 102 |
| abstract_inverted_index.powerful | 73 |
| abstract_inverted_index.semantic | 74 |
| abstract_inverted_index.simulate | 93 |
| abstract_inverted_index.accuracy, | 10 |
| abstract_inverted_index.accuracy; | 43 |
| abstract_inverted_index.generated | 106 |
| abstract_inverted_index.important | 23 |
| abstract_inverted_index.integrate | 68 |
| abstract_inverted_index.multi-hop | 6, 77, 94 |
| abstract_inverted_index.operation | 91 |
| abstract_inverted_index.questions | 7 |
| abstract_inverted_index.reasoning | 95 |
| abstract_inverted_index.retrieval | 124 |
| abstract_inverted_index.syntactic | 70, 112 |
| abstract_inverted_index.trade-off | 39 |
| abstract_inverted_index.typically | 36 |
| abstract_inverted_index.cumbersome | 51 |
| abstract_inverted_index.efficiency | 41 |
| abstract_inverted_index.fine-tunes | 101 |
| abstract_inverted_index.generation | 79 |
| abstract_inverted_index.supporting | 12 |
| abstract_inverted_index.challenging | 19 |
| abstract_inverted_index.declarative | 82 |
| abstract_inverted_index.explanation | 78, 107, 123 |
| abstract_inverted_index.large-scale | 56 |
| abstract_inverted_index.lightweight | 90 |
| abstract_inverted_index.outperforms | 109 |
| abstract_inverted_index.reliability. | 63 |
| abstract_inverted_index.transparency | 26 |
| abstract_inverted_index.applications, | 57 |
| abstract_inverted_index.trustworthiness | 28 |
| abstract_inverted_index.Language-enabled | 0 |
| abstract_inverted_index.state-of-the-art | 44 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |