Dual Instruction Tuning with Large Language Models for Mathematical Reasoning Article Swipe
Yongwei Zhou
,
Tiejun Zhao
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2403.18295
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2403.18295
Recent advancements highlight the success of instruction tuning with large language models (LLMs) utilizing Chain-of-Thought (CoT) data for mathematical reasoning tasks. Despite the fine-tuned LLMs, challenges persist, such as incorrect, missing, and redundant steps in CoT generation leading to inaccuracies in answer predictions. To alleviate this problem, we propose a dual instruction tuning strategy to meticulously model mathematical reasoning from both forward and reverse directions. This involves introducing the Intermediate Reasoning State Prediction task (forward reasoning) and the Instruction Reconstruction task (reverse reasoning) to enhance the LLMs' understanding and execution of instructions. Training instances for these tasks are constructed based on existing mathematical instruction tuning datasets. Subsequently, LLMs undergo multi-task fine-tuning using both existing mathematical instructions and the newly created data. Comprehensive experiments validate the effectiveness and domain generalization of the dual instruction tuning strategy across various mathematical reasoning tasks.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2403.18295
- https://arxiv.org/pdf/2403.18295
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4393300084
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4393300084Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2403.18295Digital Object Identifier
- Title
-
Dual Instruction Tuning with Large Language Models for Mathematical ReasoningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-03-27Full publication date if available
- Authors
-
Yongwei Zhou, Tiejun ZhaoList of authors in order
- Landing page
-
https://arxiv.org/abs/2403.18295Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2403.18295Direct 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/2403.18295Direct OA link when available
- Concepts
-
Dual language, Computer science, Dual (grammatical number), Language model, Cognitive science, Natural language processing, Linguistics, Mathematics education, Psychology, PhilosophyTop 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/W4393300084 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2403.18295 |
| ids.doi | https://doi.org/10.48550/arxiv.2403.18295 |
| ids.openalex | https://openalex.org/W4393300084 |
| fwci | |
| type | preprint |
| title | Dual Instruction Tuning with Large Language Models for Mathematical Reasoning |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11902 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.8561000227928162 |
| 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 | Intelligent Tutoring Systems and Adaptive Learning |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2992540719 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7452183961868286 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q5310213 |
| concepts[0].display_name | Dual language |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6390169858932495 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2780980858 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6060367822647095 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q110022 |
| concepts[2].display_name | Dual (grammatical number) |
| concepts[3].id | https://openalex.org/C137293760 |
| concepts[3].level | 2 |
| concepts[3].score | 0.4334193170070648 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q3621696 |
| concepts[3].display_name | Language model |
| concepts[4].id | https://openalex.org/C188147891 |
| concepts[4].level | 1 |
| concepts[4].score | 0.33535236120224 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q147638 |
| concepts[4].display_name | Cognitive science |
| concepts[5].id | https://openalex.org/C204321447 |
| concepts[5].level | 1 |
| concepts[5].score | 0.3128809332847595 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[5].display_name | Natural language processing |
| concepts[6].id | https://openalex.org/C41895202 |
| concepts[6].level | 1 |
| concepts[6].score | 0.3100670874118805 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[6].display_name | Linguistics |
| concepts[7].id | https://openalex.org/C145420912 |
| concepts[7].level | 1 |
| concepts[7].score | 0.3048100471496582 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q853077 |
| concepts[7].display_name | Mathematics education |
| concepts[8].id | https://openalex.org/C15744967 |
| concepts[8].level | 0 |
| concepts[8].score | 0.21332550048828125 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[8].display_name | Psychology |
| concepts[9].id | https://openalex.org/C138885662 |
| concepts[9].level | 0 |
| concepts[9].score | 0.08900758624076843 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[9].display_name | Philosophy |
| keywords[0].id | https://openalex.org/keywords/dual-language |
| keywords[0].score | 0.7452183961868286 |
| keywords[0].display_name | Dual language |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6390169858932495 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/dual |
| keywords[2].score | 0.6060367822647095 |
| keywords[2].display_name | Dual (grammatical number) |
| keywords[3].id | https://openalex.org/keywords/language-model |
| keywords[3].score | 0.4334193170070648 |
| keywords[3].display_name | Language model |
| keywords[4].id | https://openalex.org/keywords/cognitive-science |
| keywords[4].score | 0.33535236120224 |
| keywords[4].display_name | Cognitive science |
| keywords[5].id | https://openalex.org/keywords/natural-language-processing |
| keywords[5].score | 0.3128809332847595 |
| keywords[5].display_name | Natural language processing |
| keywords[6].id | https://openalex.org/keywords/linguistics |
| keywords[6].score | 0.3100670874118805 |
| keywords[6].display_name | Linguistics |
| keywords[7].id | https://openalex.org/keywords/mathematics-education |
| keywords[7].score | 0.3048100471496582 |
| keywords[7].display_name | Mathematics education |
| keywords[8].id | https://openalex.org/keywords/psychology |
| keywords[8].score | 0.21332550048828125 |
| keywords[8].display_name | Psychology |
| keywords[9].id | https://openalex.org/keywords/philosophy |
| keywords[9].score | 0.08900758624076843 |
| keywords[9].display_name | Philosophy |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2403.18295 |
| 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/2403.18295 |
| 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/2403.18295 |
| locations[1].id | doi:10.48550/arxiv.2403.18295 |
| 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.2403.18295 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5102195851 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Yongwei Zhou |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhou, Yongwei |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5101661008 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-4659-4935 |
| authorships[1].author.display_name | Tiejun Zhao |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Zhao, Tiejun |
| authorships[1].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/2403.18295 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Dual Instruction Tuning with Large Language Models for Mathematical Reasoning |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11902 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.8561000227928162 |
| 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 | Intelligent Tutoring Systems and Adaptive Learning |
| related_works | https://openalex.org/W2742579949, https://openalex.org/W4385978307, https://openalex.org/W2339968826, https://openalex.org/W2981284406, https://openalex.org/W4200412772, https://openalex.org/W2975760732, https://openalex.org/W1707019247, https://openalex.org/W2221456461, https://openalex.org/W4307244554, https://openalex.org/W2323798523 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2403.18295 |
| 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/2403.18295 |
| 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/2403.18295 |
| primary_location.id | pmh:oai:arXiv.org:2403.18295 |
| 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/2403.18295 |
| 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/2403.18295 |
| publication_date | 2024-03-27 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 49 |
| abstract_inverted_index.To | 43 |
| abstract_inverted_index.as | 28 |
| abstract_inverted_index.in | 34, 40 |
| abstract_inverted_index.of | 5, 90, 129 |
| abstract_inverted_index.on | 100 |
| abstract_inverted_index.to | 38, 54, 83 |
| abstract_inverted_index.we | 47 |
| abstract_inverted_index.CoT | 35 |
| abstract_inverted_index.and | 31, 62, 76, 88, 116, 126 |
| abstract_inverted_index.are | 97 |
| abstract_inverted_index.for | 17, 94 |
| abstract_inverted_index.the | 3, 22, 68, 77, 85, 117, 124, 130 |
| abstract_inverted_index.LLMs | 107 |
| abstract_inverted_index.This | 65 |
| abstract_inverted_index.both | 60, 112 |
| abstract_inverted_index.data | 16 |
| abstract_inverted_index.dual | 50, 131 |
| abstract_inverted_index.from | 59 |
| abstract_inverted_index.such | 27 |
| abstract_inverted_index.task | 73, 80 |
| abstract_inverted_index.this | 45 |
| abstract_inverted_index.with | 8 |
| abstract_inverted_index.(CoT) | 15 |
| abstract_inverted_index.LLMs' | 86 |
| abstract_inverted_index.LLMs, | 24 |
| abstract_inverted_index.State | 71 |
| abstract_inverted_index.based | 99 |
| abstract_inverted_index.data. | 120 |
| abstract_inverted_index.large | 9 |
| abstract_inverted_index.model | 56 |
| abstract_inverted_index.newly | 118 |
| abstract_inverted_index.steps | 33 |
| abstract_inverted_index.tasks | 96 |
| abstract_inverted_index.these | 95 |
| abstract_inverted_index.using | 111 |
| abstract_inverted_index.(LLMs) | 12 |
| abstract_inverted_index.Recent | 0 |
| abstract_inverted_index.across | 135 |
| abstract_inverted_index.answer | 41 |
| abstract_inverted_index.domain | 127 |
| abstract_inverted_index.models | 11 |
| abstract_inverted_index.tasks. | 20, 139 |
| abstract_inverted_index.tuning | 7, 52, 104, 133 |
| abstract_inverted_index.Despite | 21 |
| abstract_inverted_index.created | 119 |
| abstract_inverted_index.enhance | 84 |
| abstract_inverted_index.forward | 61 |
| abstract_inverted_index.leading | 37 |
| abstract_inverted_index.propose | 48 |
| abstract_inverted_index.reverse | 63 |
| abstract_inverted_index.success | 4 |
| abstract_inverted_index.undergo | 108 |
| abstract_inverted_index.various | 136 |
| abstract_inverted_index.(forward | 74 |
| abstract_inverted_index.(reverse | 81 |
| abstract_inverted_index.Training | 92 |
| abstract_inverted_index.existing | 101, 113 |
| abstract_inverted_index.involves | 66 |
| abstract_inverted_index.language | 10 |
| abstract_inverted_index.missing, | 30 |
| abstract_inverted_index.persist, | 26 |
| abstract_inverted_index.problem, | 46 |
| abstract_inverted_index.strategy | 53, 134 |
| abstract_inverted_index.validate | 123 |
| abstract_inverted_index.Reasoning | 70 |
| abstract_inverted_index.alleviate | 44 |
| abstract_inverted_index.datasets. | 105 |
| abstract_inverted_index.execution | 89 |
| abstract_inverted_index.highlight | 2 |
| abstract_inverted_index.instances | 93 |
| abstract_inverted_index.reasoning | 19, 58, 138 |
| abstract_inverted_index.redundant | 32 |
| abstract_inverted_index.utilizing | 13 |
| abstract_inverted_index.Prediction | 72 |
| abstract_inverted_index.challenges | 25 |
| abstract_inverted_index.fine-tuned | 23 |
| abstract_inverted_index.generation | 36 |
| abstract_inverted_index.incorrect, | 29 |
| abstract_inverted_index.multi-task | 109 |
| abstract_inverted_index.reasoning) | 75, 82 |
| abstract_inverted_index.Instruction | 78 |
| abstract_inverted_index.constructed | 98 |
| abstract_inverted_index.directions. | 64 |
| abstract_inverted_index.experiments | 122 |
| abstract_inverted_index.fine-tuning | 110 |
| abstract_inverted_index.instruction | 6, 51, 103, 132 |
| abstract_inverted_index.introducing | 67 |
| abstract_inverted_index.Intermediate | 69 |
| abstract_inverted_index.advancements | 1 |
| abstract_inverted_index.inaccuracies | 39 |
| abstract_inverted_index.instructions | 115 |
| abstract_inverted_index.mathematical | 18, 57, 102, 114, 137 |
| abstract_inverted_index.meticulously | 55 |
| abstract_inverted_index.predictions. | 42 |
| abstract_inverted_index.Comprehensive | 121 |
| abstract_inverted_index.Subsequently, | 106 |
| abstract_inverted_index.effectiveness | 125 |
| abstract_inverted_index.instructions. | 91 |
| abstract_inverted_index.understanding | 87 |
| abstract_inverted_index.Reconstruction | 79 |
| abstract_inverted_index.generalization | 128 |
| abstract_inverted_index.Chain-of-Thought | 14 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 2 |
| citation_normalized_percentile |