Graph-Guided Textual Explanation Generation Framework Article Swipe
Shuzhou Yuan
,
Jingyi Sun
,
Ran Zhang
,
Michael Färber
,
Steffen Eger
,
Pepa Atanasova
,
Isabelle Augenstein
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2412.12318
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2412.12318
Natural language explanations (NLEs) are commonly used to provide plausible free-text explanations of a model's reasoning about its predictions. However, recent work has questioned their faithfulness, as they may not accurately reflect the model's internal reasoning process regarding its predicted answer. In contrast, highlight explanations--input fragments critical for the model's predicted answers--exhibit measurable faithfulness. Building on this foundation, we propose G-Tex, a Graph-Guided Textual Explanation Generation framework designed to enhance the faithfulness of NLEs. Specifically, highlight explanations are first extracted as faithful cues reflecting the model's reasoning logic toward answer prediction. They are subsequently encoded through a graph neural network layer to guide the NLE generation, which aligns the generated explanations with the model's underlying reasoning toward the predicted answer. Experiments on T5 and BART using three reasoning datasets show that G-Tex improves NLE faithfulness by up to 12.18% compared to baseline methods. Additionally, G-Tex generates NLEs with greater semantic and lexical similarity to human-written ones. Human evaluations show that G-Tex can decrease redundant content and enhance the overall quality of NLEs. Our work presents a novel method for explicitly guiding NLE generation to enhance faithfulness, serving as a foundation for addressing broader criteria in NLE and generated text.
Related Topics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2412.12318
- https://arxiv.org/pdf/2412.12318
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4405562047
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4405562047Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2412.12318Digital Object Identifier
- Title
-
Graph-Guided Textual Explanation Generation FrameworkWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-12-16Full publication date if available
- Authors
-
Shuzhou Yuan, Jingyi Sun, Ran Zhang, Michael Färber, Steffen Eger, Pepa Atanasova, Isabelle AugensteinList of authors in order
- Landing page
-
https://arxiv.org/abs/2412.12318Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2412.12318Direct 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/2412.12318Direct OA link when available
- Concepts
-
Graph, Computer science, Theoretical computer scienceTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4405562047 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2412.12318 |
| ids.doi | https://doi.org/10.48550/arxiv.2412.12318 |
| ids.openalex | https://openalex.org/W4405562047 |
| fwci | |
| type | preprint |
| title | Graph-Guided Textual Explanation Generation Framework |
| 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 | 0.9818999767303467 |
| 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/T11986 |
| topics[1].field.id | https://openalex.org/fields/18 |
| topics[1].field.display_name | Decision Sciences |
| topics[1].score | 0.9596999883651733 |
| topics[1].domain.id | https://openalex.org/domains/2 |
| topics[1].domain.display_name | Social Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1802 |
| topics[1].subfield.display_name | Information Systems and Management |
| topics[1].display_name | Scientific Computing and Data Management |
| topics[2].id | https://openalex.org/T10215 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9506999850273132 |
| 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 | Semantic Web and Ontologies |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C132525143 |
| concepts[0].level | 2 |
| concepts[0].score | 0.523175060749054 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q141488 |
| concepts[0].display_name | Graph |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.4837243854999542 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C80444323 |
| concepts[2].level | 1 |
| concepts[2].score | 0.2735408544540405 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[2].display_name | Theoretical computer science |
| keywords[0].id | https://openalex.org/keywords/graph |
| keywords[0].score | 0.523175060749054 |
| keywords[0].display_name | Graph |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.4837243854999542 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[2].score | 0.2735408544540405 |
| keywords[2].display_name | Theoretical computer science |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2412.12318 |
| 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/2412.12318 |
| 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/2412.12318 |
| locations[1].id | doi:10.48550/arxiv.2412.12318 |
| 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 | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| 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.2412.12318 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5008824325 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Shuzhou Yuan |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yuan, Shuzhou |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5048158777 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-5335-0985 |
| authorships[1].author.display_name | Jingyi Sun |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Sun, Jingyi |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5114500347 |
| authorships[2].author.orcid | https://orcid.org/0009-0000-0708-5287 |
| authorships[2].author.display_name | Ran Zhang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhang, Ran |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5031600582 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-5458-8645 |
| authorships[3].author.display_name | Michael Färber |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Färber, Michael |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5053947568 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-4663-8336 |
| authorships[4].author.display_name | Steffen Eger |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Eger, Steffen |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5001646936 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-0023-2616 |
| authorships[5].author.display_name | Pepa Atanasova |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Atanasova, Pepa |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5018976680 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-1562-7909 |
| authorships[6].author.display_name | Isabelle Augenstein |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Augenstein, Isabelle |
| authorships[6].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/2412.12318 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Graph-Guided Textual Explanation Generation Framework |
| 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 | 0.9818999767303467 |
| 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/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2412.12318 |
| 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/2412.12318 |
| 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/2412.12318 |
| primary_location.id | pmh:oai:arXiv.org:2412.12318 |
| 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/2412.12318 |
| 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/2412.12318 |
| publication_date | 2024-12-16 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 13, 61, 96, 175, 188 |
| abstract_inverted_index.In | 41 |
| abstract_inverted_index.T5 | 122 |
| abstract_inverted_index.as | 26, 80, 187 |
| abstract_inverted_index.by | 135 |
| abstract_inverted_index.in | 194 |
| abstract_inverted_index.of | 12, 72, 170 |
| abstract_inverted_index.on | 55, 121 |
| abstract_inverted_index.to | 7, 68, 101, 137, 140, 153, 183 |
| abstract_inverted_index.up | 136 |
| abstract_inverted_index.we | 58 |
| abstract_inverted_index.NLE | 104, 133, 181, 195 |
| abstract_inverted_index.Our | 172 |
| abstract_inverted_index.and | 123, 150, 165, 196 |
| abstract_inverted_index.are | 4, 77, 92 |
| abstract_inverted_index.can | 161 |
| abstract_inverted_index.for | 47, 178, 190 |
| abstract_inverted_index.has | 22 |
| abstract_inverted_index.its | 17, 38 |
| abstract_inverted_index.may | 28 |
| abstract_inverted_index.not | 29 |
| abstract_inverted_index.the | 32, 48, 70, 84, 103, 108, 112, 117, 167 |
| abstract_inverted_index.BART | 124 |
| abstract_inverted_index.NLEs | 146 |
| abstract_inverted_index.They | 91 |
| abstract_inverted_index.cues | 82 |
| abstract_inverted_index.show | 129, 158 |
| abstract_inverted_index.that | 130, 159 |
| abstract_inverted_index.they | 27 |
| abstract_inverted_index.this | 56 |
| abstract_inverted_index.used | 6 |
| abstract_inverted_index.with | 111, 147 |
| abstract_inverted_index.work | 21, 173 |
| abstract_inverted_index.G-Tex | 131, 144, 160 |
| abstract_inverted_index.Human | 156 |
| abstract_inverted_index.NLEs. | 73, 171 |
| abstract_inverted_index.about | 16 |
| abstract_inverted_index.first | 78 |
| abstract_inverted_index.graph | 97 |
| abstract_inverted_index.guide | 102 |
| abstract_inverted_index.layer | 100 |
| abstract_inverted_index.logic | 87 |
| abstract_inverted_index.novel | 176 |
| abstract_inverted_index.ones. | 155 |
| abstract_inverted_index.text. | 198 |
| abstract_inverted_index.their | 24 |
| abstract_inverted_index.three | 126 |
| abstract_inverted_index.using | 125 |
| abstract_inverted_index.which | 106 |
| abstract_inverted_index.(NLEs) | 3 |
| abstract_inverted_index.12.18% | 138 |
| abstract_inverted_index.G-Tex, | 60 |
| abstract_inverted_index.aligns | 107 |
| abstract_inverted_index.answer | 89 |
| abstract_inverted_index.method | 177 |
| abstract_inverted_index.neural | 98 |
| abstract_inverted_index.recent | 20 |
| abstract_inverted_index.toward | 88, 116 |
| abstract_inverted_index.Natural | 0 |
| abstract_inverted_index.Textual | 63 |
| abstract_inverted_index.answer. | 40, 119 |
| abstract_inverted_index.broader | 192 |
| abstract_inverted_index.content | 164 |
| abstract_inverted_index.encoded | 94 |
| abstract_inverted_index.enhance | 69, 166, 184 |
| abstract_inverted_index.greater | 148 |
| abstract_inverted_index.guiding | 180 |
| abstract_inverted_index.lexical | 151 |
| abstract_inverted_index.model's | 14, 33, 49, 85, 113 |
| abstract_inverted_index.network | 99 |
| abstract_inverted_index.overall | 168 |
| abstract_inverted_index.process | 36 |
| abstract_inverted_index.propose | 59 |
| abstract_inverted_index.provide | 8 |
| abstract_inverted_index.quality | 169 |
| abstract_inverted_index.reflect | 31 |
| abstract_inverted_index.serving | 186 |
| abstract_inverted_index.through | 95 |
| abstract_inverted_index.Building | 54 |
| abstract_inverted_index.However, | 19 |
| abstract_inverted_index.baseline | 141 |
| abstract_inverted_index.commonly | 5 |
| abstract_inverted_index.compared | 139 |
| abstract_inverted_index.criteria | 193 |
| abstract_inverted_index.critical | 46 |
| abstract_inverted_index.datasets | 128 |
| abstract_inverted_index.decrease | 162 |
| abstract_inverted_index.designed | 67 |
| abstract_inverted_index.faithful | 81 |
| abstract_inverted_index.improves | 132 |
| abstract_inverted_index.internal | 34 |
| abstract_inverted_index.language | 1 |
| abstract_inverted_index.methods. | 142 |
| abstract_inverted_index.presents | 174 |
| abstract_inverted_index.semantic | 149 |
| abstract_inverted_index.contrast, | 42 |
| abstract_inverted_index.extracted | 79 |
| abstract_inverted_index.fragments | 45 |
| abstract_inverted_index.framework | 66 |
| abstract_inverted_index.free-text | 10 |
| abstract_inverted_index.generated | 109, 197 |
| abstract_inverted_index.generates | 145 |
| abstract_inverted_index.highlight | 43, 75 |
| abstract_inverted_index.plausible | 9 |
| abstract_inverted_index.predicted | 39, 50, 118 |
| abstract_inverted_index.reasoning | 15, 35, 86, 115, 127 |
| abstract_inverted_index.redundant | 163 |
| abstract_inverted_index.regarding | 37 |
| abstract_inverted_index.Generation | 65 |
| abstract_inverted_index.accurately | 30 |
| abstract_inverted_index.addressing | 191 |
| abstract_inverted_index.explicitly | 179 |
| abstract_inverted_index.foundation | 189 |
| abstract_inverted_index.generation | 182 |
| abstract_inverted_index.measurable | 52 |
| abstract_inverted_index.questioned | 23 |
| abstract_inverted_index.reflecting | 83 |
| abstract_inverted_index.similarity | 152 |
| abstract_inverted_index.underlying | 114 |
| abstract_inverted_index.Experiments | 120 |
| abstract_inverted_index.Explanation | 64 |
| abstract_inverted_index.evaluations | 157 |
| abstract_inverted_index.foundation, | 57 |
| abstract_inverted_index.generation, | 105 |
| abstract_inverted_index.prediction. | 90 |
| abstract_inverted_index.Graph-Guided | 62 |
| abstract_inverted_index.explanations | 2, 11, 76, 110 |
| abstract_inverted_index.faithfulness | 71, 134 |
| abstract_inverted_index.predictions. | 18 |
| abstract_inverted_index.subsequently | 93 |
| abstract_inverted_index.Additionally, | 143 |
| abstract_inverted_index.Specifically, | 74 |
| abstract_inverted_index.faithfulness, | 25, 185 |
| abstract_inverted_index.faithfulness. | 53 |
| abstract_inverted_index.human-written | 154 |
| abstract_inverted_index.answers--exhibit | 51 |
| abstract_inverted_index.explanations--input | 44 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile |