Listwise Preference Optimization with Element-wise Confusions for Aspect Sentiment Quad Prediction Article Swipe
Aspect sentiment quad prediction (ASQP) is inherently challenging to predict a structured quadruple with four core sentiment elements, including aspect term (a), aspect category (c), opinion term (o), and sentiment polarity (s). Prior methods relying on marker-based prediction struggle with modeling the intricate relationships among elements and experience sharp performance declines when predicting higher-order elements (e.g., c and s) under standard supervised fine-tuning. To address these limitations, we employ reasoning-based generation to output both the quadruple and a natural language rationale under element prefixes within a unified template, encouraging explicit relational reasoning and interpretability. To further enhance element-wise alignment, we introduce a listwise preference optimization framework for improving structural validity and relational coherence. Specifically, we generate element-wise confusable candidates via syntactic and semantic proximity, then train the model with listwise objectives to prefer the gold candidates over closely competing alternatives. Extensive experiments on four benchmark datasets demonstrate that our framework effectively improves quadruple prediction accuracy and explanation consistency.
Related Topics
Concepts
Computer science
Sentiment analysis
Artificial intelligence
Benchmark (surveying)
Preference
Natural language processing
Semantics (computer science)
Core (optical fiber)
Prefix
Term (time)
Machine learning
Property (philosophy)
Natural language understanding
Element (criminal law)
Polarity (international relations)
Natural language
Data mining
Relational database
Quality (philosophy)
Domain (mathematical analysis)
Variety (cybernetics)
Scale (ratio)
Metadata
- Type
- article
- Landing Page
- http://arxiv.org/abs/2511.23184
- https://arxiv.org/pdf/2511.23184
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W7108248293
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W7108248293Canonical identifier for this work in OpenAlex
- Title
-
Listwise Preference Optimization with Element-wise Confusions for Aspect Sentiment Quad PredictionWork title
- Type
-
articleOpenAlex work type
- Publication year
-
2025Year of publication
- Publication date
-
2025-11-28Full publication date if available
- Authors
-
Lai, Wenna, Xie, Haoran, Xu Guandong, Li Qing, Qin S. JoeList of authors in order
- Landing page
-
https://arxiv.org/abs/2511.23184Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2511.23184Direct 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/2511.23184Direct OA link when available
- Concepts
-
Computer science, Sentiment analysis, Artificial intelligence, Benchmark (surveying), Preference, Natural language processing, Semantics (computer science), Core (optical fiber), Prefix, Term (time), Machine learning, Property (philosophy), Natural language understanding, Element (criminal law), Polarity (international relations), Natural language, Data mining, Relational database, Quality (philosophy), Domain (mathematical analysis), Variety (cybernetics), Scale (ratio)Top concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W7108248293 |
|---|---|
| doi | |
| ids.openalex | https://openalex.org/W7108248293 |
| fwci | 0.0 |
| type | article |
| title | Listwise Preference Optimization with Element-wise Confusions for Aspect Sentiment Quad Prediction |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10664 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9863393306732178 |
| 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 | Sentiment Analysis and Opinion Mining |
| topics[1].id | https://openalex.org/T10028 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.002222674433141947 |
| 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 | Topic Modeling |
| topics[2].id | https://openalex.org/T10203 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.0008726210799068213 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1710 |
| topics[2].subfield.display_name | Information Systems |
| topics[2].display_name | Recommender Systems and Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7551568746566772 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C66402592 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6433030366897583 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q2271421 |
| concepts[1].display_name | Sentiment analysis |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.620413064956665 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C185798385 |
| concepts[3].level | 2 |
| concepts[3].score | 0.582347571849823 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1161707 |
| concepts[3].display_name | Benchmark (surveying) |
| concepts[4].id | https://openalex.org/C2781249084 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5491766929626465 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q908656 |
| concepts[4].display_name | Preference |
| concepts[5].id | https://openalex.org/C204321447 |
| concepts[5].level | 1 |
| concepts[5].score | 0.5263916850090027 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[5].display_name | Natural language processing |
| concepts[6].id | https://openalex.org/C184337299 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5132262110710144 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q1437428 |
| concepts[6].display_name | Semantics (computer science) |
| concepts[7].id | https://openalex.org/C2164484 |
| concepts[7].level | 2 |
| concepts[7].score | 0.49361151456832886 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q5170150 |
| concepts[7].display_name | Core (optical fiber) |
| concepts[8].id | https://openalex.org/C141603448 |
| concepts[8].level | 2 |
| concepts[8].score | 0.47561463713645935 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q134830 |
| concepts[8].display_name | Prefix |
| concepts[9].id | https://openalex.org/C61797465 |
| concepts[9].level | 2 |
| concepts[9].score | 0.4631218910217285 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q1188986 |
| concepts[9].display_name | Term (time) |
| concepts[10].id | https://openalex.org/C119857082 |
| concepts[10].level | 1 |
| concepts[10].score | 0.4222661256790161 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[10].display_name | Machine learning |
| concepts[11].id | https://openalex.org/C189950617 |
| concepts[11].level | 2 |
| concepts[11].score | 0.41911590099334717 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q937228 |
| concepts[11].display_name | Property (philosophy) |
| concepts[12].id | https://openalex.org/C2779439875 |
| concepts[12].level | 3 |
| concepts[12].score | 0.395481675863266 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q1078276 |
| concepts[12].display_name | Natural language understanding |
| concepts[13].id | https://openalex.org/C200288055 |
| concepts[13].level | 2 |
| concepts[13].score | 0.3719596862792969 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q2621792 |
| concepts[13].display_name | Element (criminal law) |
| concepts[14].id | https://openalex.org/C2777361361 |
| concepts[14].level | 3 |
| concepts[14].score | 0.335614413022995 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q1112585 |
| concepts[14].display_name | Polarity (international relations) |
| concepts[15].id | https://openalex.org/C195324797 |
| concepts[15].level | 2 |
| concepts[15].score | 0.3213890492916107 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q33742 |
| concepts[15].display_name | Natural language |
| concepts[16].id | https://openalex.org/C124101348 |
| concepts[16].level | 1 |
| concepts[16].score | 0.3119385540485382 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q172491 |
| concepts[16].display_name | Data mining |
| concepts[17].id | https://openalex.org/C5655090 |
| concepts[17].level | 2 |
| concepts[17].score | 0.3052559196949005 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q192588 |
| concepts[17].display_name | Relational database |
| concepts[18].id | https://openalex.org/C2779530757 |
| concepts[18].level | 2 |
| concepts[18].score | 0.2921667993068695 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q1207505 |
| concepts[18].display_name | Quality (philosophy) |
| concepts[19].id | https://openalex.org/C36503486 |
| concepts[19].level | 2 |
| concepts[19].score | 0.277853399515152 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q11235244 |
| concepts[19].display_name | Domain (mathematical analysis) |
| concepts[20].id | https://openalex.org/C136197465 |
| concepts[20].level | 2 |
| concepts[20].score | 0.26292315125465393 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q1729295 |
| concepts[20].display_name | Variety (cybernetics) |
| concepts[21].id | https://openalex.org/C2778755073 |
| concepts[21].level | 2 |
| concepts[21].score | 0.2592497169971466 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q10858537 |
| concepts[21].display_name | Scale (ratio) |
| keywords[0].id | https://openalex.org/keywords/sentiment-analysis |
| keywords[0].score | 0.6433030366897583 |
| keywords[0].display_name | Sentiment analysis |
| keywords[1].id | https://openalex.org/keywords/benchmark |
| keywords[1].score | 0.582347571849823 |
| keywords[1].display_name | Benchmark (surveying) |
| keywords[2].id | https://openalex.org/keywords/preference |
| keywords[2].score | 0.5491766929626465 |
| keywords[2].display_name | Preference |
| keywords[3].id | https://openalex.org/keywords/semantics |
| keywords[3].score | 0.5132262110710144 |
| keywords[3].display_name | Semantics (computer science) |
| keywords[4].id | https://openalex.org/keywords/core |
| keywords[4].score | 0.49361151456832886 |
| keywords[4].display_name | Core (optical fiber) |
| keywords[5].id | https://openalex.org/keywords/prefix |
| keywords[5].score | 0.47561463713645935 |
| keywords[5].display_name | Prefix |
| keywords[6].id | https://openalex.org/keywords/term |
| keywords[6].score | 0.4631218910217285 |
| keywords[6].display_name | Term (time) |
| keywords[7].id | https://openalex.org/keywords/property |
| keywords[7].score | 0.41911590099334717 |
| keywords[7].display_name | Property (philosophy) |
| language | |
| locations[0].id | pmh:oai:arXiv.org:2511.23184 |
| 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/2511.23184 |
| 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/2511.23184 |
| indexed_in | arxiv |
| authorships[0].author.id | |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Lai, Wenna |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Lai, Wenna |
| authorships[0].is_corresponding | True |
| authorships[1].author.id | https://openalex.org/A2373043497 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Xie, Haoran |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Xie, Haoran |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A2331390008 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Xu Guandong |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Xu, Guandong |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A1935408072 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-6593-8380 |
| authorships[3].author.display_name | Li Qing |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Li, Qing |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A2744464116 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Qin S. Joe |
| authorships[4].author_position | last |
| authorships[4].raw_author_name | Qin, S. Joe |
| authorships[4].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/2511.23184 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-12-03T00:00:00 |
| display_name | Listwise Preference Optimization with Element-wise Confusions for Aspect Sentiment Quad Prediction |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-12-03T00:07:38.036990 |
| primary_topic.id | https://openalex.org/T10664 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9863393306732178 |
| 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 | Sentiment Analysis and Opinion Mining |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | pmh:oai:arXiv.org:2511.23184 |
| 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/2511.23184 |
| 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/2511.23184 |
| primary_location.id | pmh:oai:arXiv.org:2511.23184 |
| 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/2511.23184 |
| 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/2511.23184 |
| publication_date | 2025-11-28 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 10, 77, 85, 101 |
| abstract_inverted_index.c | 56 |
| abstract_inverted_index.To | 63, 94 |
| abstract_inverted_index.is | 5 |
| abstract_inverted_index.on | 35, 142 |
| abstract_inverted_index.s) | 58 |
| abstract_inverted_index.to | 8, 71, 131 |
| abstract_inverted_index.we | 67, 99, 114 |
| abstract_inverted_index.and | 28, 46, 57, 76, 92, 110, 121, 155 |
| abstract_inverted_index.for | 106 |
| abstract_inverted_index.our | 148 |
| abstract_inverted_index.the | 41, 74, 126, 133 |
| abstract_inverted_index.via | 119 |
| abstract_inverted_index.(a), | 21 |
| abstract_inverted_index.(c), | 24 |
| abstract_inverted_index.(o), | 27 |
| abstract_inverted_index.(s). | 31 |
| abstract_inverted_index.both | 73 |
| abstract_inverted_index.core | 15 |
| abstract_inverted_index.four | 14, 143 |
| abstract_inverted_index.gold | 134 |
| abstract_inverted_index.over | 136 |
| abstract_inverted_index.quad | 2 |
| abstract_inverted_index.term | 20, 26 |
| abstract_inverted_index.that | 147 |
| abstract_inverted_index.then | 124 |
| abstract_inverted_index.when | 51 |
| abstract_inverted_index.with | 13, 39, 128 |
| abstract_inverted_index.Prior | 32 |
| abstract_inverted_index.among | 44 |
| abstract_inverted_index.model | 127 |
| abstract_inverted_index.sharp | 48 |
| abstract_inverted_index.these | 65 |
| abstract_inverted_index.train | 125 |
| abstract_inverted_index.under | 59, 81 |
| abstract_inverted_index.(ASQP) | 4 |
| abstract_inverted_index.(e.g., | 55 |
| abstract_inverted_index.Aspect | 0 |
| abstract_inverted_index.aspect | 19, 22 |
| abstract_inverted_index.employ | 68 |
| abstract_inverted_index.output | 72 |
| abstract_inverted_index.prefer | 132 |
| abstract_inverted_index.within | 84 |
| abstract_inverted_index.address | 64 |
| abstract_inverted_index.closely | 137 |
| abstract_inverted_index.element | 82 |
| abstract_inverted_index.enhance | 96 |
| abstract_inverted_index.further | 95 |
| abstract_inverted_index.methods | 33 |
| abstract_inverted_index.natural | 78 |
| abstract_inverted_index.opinion | 25 |
| abstract_inverted_index.predict | 9 |
| abstract_inverted_index.relying | 34 |
| abstract_inverted_index.unified | 86 |
| abstract_inverted_index.accuracy | 154 |
| abstract_inverted_index.category | 23 |
| abstract_inverted_index.datasets | 145 |
| abstract_inverted_index.declines | 50 |
| abstract_inverted_index.elements | 45, 54 |
| abstract_inverted_index.explicit | 89 |
| abstract_inverted_index.generate | 115 |
| abstract_inverted_index.improves | 151 |
| abstract_inverted_index.language | 79 |
| abstract_inverted_index.listwise | 102, 129 |
| abstract_inverted_index.modeling | 40 |
| abstract_inverted_index.polarity | 30 |
| abstract_inverted_index.prefixes | 83 |
| abstract_inverted_index.semantic | 122 |
| abstract_inverted_index.standard | 60 |
| abstract_inverted_index.struggle | 38 |
| abstract_inverted_index.validity | 109 |
| abstract_inverted_index.Extensive | 140 |
| abstract_inverted_index.benchmark | 144 |
| abstract_inverted_index.competing | 138 |
| abstract_inverted_index.elements, | 17 |
| abstract_inverted_index.framework | 105, 149 |
| abstract_inverted_index.improving | 107 |
| abstract_inverted_index.including | 18 |
| abstract_inverted_index.intricate | 42 |
| abstract_inverted_index.introduce | 100 |
| abstract_inverted_index.quadruple | 12, 75, 152 |
| abstract_inverted_index.rationale | 80 |
| abstract_inverted_index.reasoning | 91 |
| abstract_inverted_index.sentiment | 1, 16, 29 |
| abstract_inverted_index.syntactic | 120 |
| abstract_inverted_index.template, | 87 |
| abstract_inverted_index.alignment, | 98 |
| abstract_inverted_index.candidates | 118, 135 |
| abstract_inverted_index.coherence. | 112 |
| abstract_inverted_index.confusable | 117 |
| abstract_inverted_index.experience | 47 |
| abstract_inverted_index.generation | 70 |
| abstract_inverted_index.inherently | 6 |
| abstract_inverted_index.objectives | 130 |
| abstract_inverted_index.predicting | 52 |
| abstract_inverted_index.prediction | 3, 37, 153 |
| abstract_inverted_index.preference | 103 |
| abstract_inverted_index.proximity, | 123 |
| abstract_inverted_index.relational | 90, 111 |
| abstract_inverted_index.structural | 108 |
| abstract_inverted_index.structured | 11 |
| abstract_inverted_index.supervised | 61 |
| abstract_inverted_index.challenging | 7 |
| abstract_inverted_index.demonstrate | 146 |
| abstract_inverted_index.effectively | 150 |
| abstract_inverted_index.encouraging | 88 |
| abstract_inverted_index.experiments | 141 |
| abstract_inverted_index.explanation | 156 |
| abstract_inverted_index.performance | 49 |
| abstract_inverted_index.consistency. | 157 |
| abstract_inverted_index.element-wise | 97, 116 |
| abstract_inverted_index.fine-tuning. | 62 |
| abstract_inverted_index.higher-order | 53 |
| abstract_inverted_index.limitations, | 66 |
| abstract_inverted_index.marker-based | 36 |
| abstract_inverted_index.optimization | 104 |
| abstract_inverted_index.Specifically, | 113 |
| abstract_inverted_index.alternatives. | 139 |
| abstract_inverted_index.relationships | 43 |
| abstract_inverted_index.reasoning-based | 69 |
| abstract_inverted_index.interpretability. | 93 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 5 |
| citation_normalized_percentile.value | 0.92207978 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |