SELF: Self-Evolution with Language Feedback Article Swipe
Jianqiao Lu
,
Wanjun Zhong
,
Wenyong Huang
,
Yufei Wang
,
Fei Mi
,
Baojun Wang
,
Weichao Wang
,
Lifeng Shang
,
Qun Liu
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.00533
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.00533
Large Language Models (LLMs) have demonstrated remarkable versatility across various domains. To further advance LLMs, we propose 'SELF' (Self-Evolution with Language Feedback), a novel approach that enables LLMs to self-improve through self-reflection, akin to human learning processes. SELF initiates with a meta-skill learning process that equips the LLMs with capabilities for self-feedback and self-refinement. Subsequently, the model undergoes an iterative process of self-evolution. In each iteration, it utilizes an unlabeled dataset of instructions to generate initial responses. These responses are enhanced through self-feedback and self-refinement. The model is then fine-tuned using this enhanced data. The model undergoes progressive improvement through this iterative self-evolution process. Moreover, the SELF framework enables the model to apply self-refinement during inference, which further improves response quality. Our experiments in mathematics and general tasks demonstrate that SELF can enhance the capabilities of LLMs without human intervention. The SELF framework indicates a promising direction for the autonomous evolution of LLMs, transitioning them from passive information receivers to active participants in their development.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2310.00533
- https://arxiv.org/pdf/2310.00533
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4387323597
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4387323597Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2310.00533Digital Object Identifier
- Title
-
SELF: Self-Evolution with Language FeedbackWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-10-01Full publication date if available
- Authors
-
Jianqiao Lu, Wanjun Zhong, Wenyong Huang, Yufei Wang, Fei Mi, Baojun Wang, Weichao Wang, Lifeng Shang, Qun LiuList of authors in order
- Landing page
-
https://arxiv.org/abs/2310.00533Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2310.00533Direct 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/2310.00533Direct OA link when available
- Concepts
-
Process (computing), Computer science, Inference, Iterative and incremental development, Artificial intelligence, Cognitive psychology, Psychology, Software engineering, Programming languageTop 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/W4387323597 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2310.00533 |
| ids.doi | https://doi.org/10.48550/arxiv.2310.00533 |
| ids.openalex | https://openalex.org/W4387323597 |
| fwci | |
| type | preprint |
| title | SELF: Self-Evolution with Language Feedback |
| 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 | 0.9990000128746033 |
| 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/T10181 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9865999817848206 |
| 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 | Natural Language Processing Techniques |
| topics[2].id | https://openalex.org/T13910 |
| topics[2].field.id | https://openalex.org/fields/33 |
| topics[2].field.display_name | Social Sciences |
| topics[2].score | 0.9136000275611877 |
| topics[2].domain.id | https://openalex.org/domains/2 |
| topics[2].domain.display_name | Social Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/3300 |
| topics[2].subfield.display_name | General Social Sciences |
| topics[2].display_name | Computational and Text Analysis Methods |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C98045186 |
| concepts[0].level | 2 |
| concepts[0].score | 0.5813694596290588 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q205663 |
| concepts[0].display_name | Process (computing) |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.555382251739502 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2776214188 |
| concepts[2].level | 2 |
| concepts[2].score | 0.49851250648498535 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[2].display_name | Inference |
| concepts[3].id | https://openalex.org/C143587482 |
| concepts[3].level | 2 |
| concepts[3].score | 0.4600726068019867 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1543216 |
| concepts[3].display_name | Iterative and incremental development |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.3305532932281494 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C180747234 |
| concepts[5].level | 1 |
| concepts[5].score | 0.3292316496372223 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q23373 |
| concepts[5].display_name | Cognitive psychology |
| concepts[6].id | https://openalex.org/C15744967 |
| concepts[6].level | 0 |
| concepts[6].score | 0.26180189847946167 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[6].display_name | Psychology |
| concepts[7].id | https://openalex.org/C115903868 |
| concepts[7].level | 1 |
| concepts[7].score | 0.10340666770935059 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q80993 |
| concepts[7].display_name | Software engineering |
| concepts[8].id | https://openalex.org/C199360897 |
| concepts[8].level | 1 |
| concepts[8].score | 0.08295604586601257 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[8].display_name | Programming language |
| keywords[0].id | https://openalex.org/keywords/process |
| keywords[0].score | 0.5813694596290588 |
| keywords[0].display_name | Process (computing) |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.555382251739502 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/inference |
| keywords[2].score | 0.49851250648498535 |
| keywords[2].display_name | Inference |
| keywords[3].id | https://openalex.org/keywords/iterative-and-incremental-development |
| keywords[3].score | 0.4600726068019867 |
| keywords[3].display_name | Iterative and incremental development |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.3305532932281494 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/cognitive-psychology |
| keywords[5].score | 0.3292316496372223 |
| keywords[5].display_name | Cognitive psychology |
| keywords[6].id | https://openalex.org/keywords/psychology |
| keywords[6].score | 0.26180189847946167 |
| keywords[6].display_name | Psychology |
| keywords[7].id | https://openalex.org/keywords/software-engineering |
| keywords[7].score | 0.10340666770935059 |
| keywords[7].display_name | Software engineering |
| keywords[8].id | https://openalex.org/keywords/programming-language |
| keywords[8].score | 0.08295604586601257 |
| keywords[8].display_name | Programming language |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2310.00533 |
| 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/2310.00533 |
| 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/2310.00533 |
| locations[1].id | doi:10.48550/arxiv.2310.00533 |
| 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.2310.00533 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5113021849 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Jianqiao Lu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Lu, Jianqiao |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5019101763 |
| authorships[1].author.orcid | https://orcid.org/0009-0007-2236-228X |
| authorships[1].author.display_name | Wanjun Zhong |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Zhong, Wanjun |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5002206405 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-3167-0851 |
| authorships[2].author.display_name | Wenyong Huang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Huang, Wenyong |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100374831 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-8108-3818 |
| authorships[3].author.display_name | Yufei Wang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Wang, Yufei |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5012014905 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-6358-9922 |
| authorships[4].author.display_name | Fei Mi |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Mi, Fei |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5038563026 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-4858-8937 |
| authorships[5].author.display_name | Baojun Wang |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Wang, Baojun |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5110551419 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Weichao Wang |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Wang, Weichao |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5046228314 |
| authorships[7].author.orcid | |
| authorships[7].author.display_name | Lifeng Shang |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Shang, Lifeng |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5100426170 |
| authorships[8].author.orcid | https://orcid.org/0000-0002-7000-1792 |
| authorships[8].author.display_name | Qun Liu |
| authorships[8].author_position | last |
| authorships[8].raw_author_name | Liu, Qun |
| authorships[8].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/2310.00533 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2023-10-04T00:00:00 |
| display_name | SELF: Self-Evolution with Language Feedback |
| 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 | 0.9990000128746033 |
| 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/W2055243143, https://openalex.org/W4321636575, https://openalex.org/W1986418932, https://openalex.org/W2357796999, https://openalex.org/W2045526782, https://openalex.org/W2741131631, https://openalex.org/W2156919374, https://openalex.org/W1984019423, https://openalex.org/W4280588203, https://openalex.org/W1483472507 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2310.00533 |
| 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/2310.00533 |
| 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/2310.00533 |
| primary_location.id | pmh:oai:arXiv.org:2310.00533 |
| 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/2310.00533 |
| 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/2310.00533 |
| publication_date | 2023-10-01 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 22, 40, 144 |
| abstract_inverted_index.In | 63 |
| abstract_inverted_index.To | 11 |
| abstract_inverted_index.an | 58, 68 |
| abstract_inverted_index.in | 123, 162 |
| abstract_inverted_index.is | 87 |
| abstract_inverted_index.it | 66 |
| abstract_inverted_index.of | 61, 71, 135, 151 |
| abstract_inverted_index.to | 28, 33, 73, 111, 159 |
| abstract_inverted_index.we | 15 |
| abstract_inverted_index.Our | 121 |
| abstract_inverted_index.The | 85, 94, 140 |
| abstract_inverted_index.and | 52, 83, 125 |
| abstract_inverted_index.are | 79 |
| abstract_inverted_index.can | 131 |
| abstract_inverted_index.for | 50, 147 |
| abstract_inverted_index.the | 46, 55, 105, 109, 133, 148 |
| abstract_inverted_index.LLMs | 27, 47, 136 |
| abstract_inverted_index.SELF | 37, 106, 130, 141 |
| abstract_inverted_index.akin | 32 |
| abstract_inverted_index.each | 64 |
| abstract_inverted_index.from | 155 |
| abstract_inverted_index.have | 4 |
| abstract_inverted_index.that | 25, 44, 129 |
| abstract_inverted_index.them | 154 |
| abstract_inverted_index.then | 88 |
| abstract_inverted_index.this | 91, 100 |
| abstract_inverted_index.with | 19, 39, 48 |
| abstract_inverted_index.LLMs, | 14, 152 |
| abstract_inverted_index.Large | 0 |
| abstract_inverted_index.These | 77 |
| abstract_inverted_index.apply | 112 |
| abstract_inverted_index.data. | 93 |
| abstract_inverted_index.human | 34, 138 |
| abstract_inverted_index.model | 56, 86, 95, 110 |
| abstract_inverted_index.novel | 23 |
| abstract_inverted_index.tasks | 127 |
| abstract_inverted_index.their | 163 |
| abstract_inverted_index.using | 90 |
| abstract_inverted_index.which | 116 |
| abstract_inverted_index.'SELF' | 17 |
| abstract_inverted_index.(LLMs) | 3 |
| abstract_inverted_index.Models | 2 |
| abstract_inverted_index.across | 8 |
| abstract_inverted_index.active | 160 |
| abstract_inverted_index.during | 114 |
| abstract_inverted_index.equips | 45 |
| abstract_inverted_index.advance | 13 |
| abstract_inverted_index.dataset | 70 |
| abstract_inverted_index.enables | 26, 108 |
| abstract_inverted_index.enhance | 132 |
| abstract_inverted_index.further | 12, 117 |
| abstract_inverted_index.general | 126 |
| abstract_inverted_index.initial | 75 |
| abstract_inverted_index.passive | 156 |
| abstract_inverted_index.process | 43, 60 |
| abstract_inverted_index.propose | 16 |
| abstract_inverted_index.through | 30, 81, 99 |
| abstract_inverted_index.various | 9 |
| abstract_inverted_index.without | 137 |
| abstract_inverted_index.Language | 1, 20 |
| abstract_inverted_index.approach | 24 |
| abstract_inverted_index.domains. | 10 |
| abstract_inverted_index.enhanced | 80, 92 |
| abstract_inverted_index.generate | 74 |
| abstract_inverted_index.improves | 118 |
| abstract_inverted_index.learning | 35, 42 |
| abstract_inverted_index.process. | 103 |
| abstract_inverted_index.quality. | 120 |
| abstract_inverted_index.response | 119 |
| abstract_inverted_index.utilizes | 67 |
| abstract_inverted_index.Moreover, | 104 |
| abstract_inverted_index.direction | 146 |
| abstract_inverted_index.evolution | 150 |
| abstract_inverted_index.framework | 107, 142 |
| abstract_inverted_index.indicates | 143 |
| abstract_inverted_index.initiates | 38 |
| abstract_inverted_index.iterative | 59, 101 |
| abstract_inverted_index.promising | 145 |
| abstract_inverted_index.receivers | 158 |
| abstract_inverted_index.responses | 78 |
| abstract_inverted_index.undergoes | 57, 96 |
| abstract_inverted_index.unlabeled | 69 |
| abstract_inverted_index.Feedback), | 21 |
| abstract_inverted_index.autonomous | 149 |
| abstract_inverted_index.fine-tuned | 89 |
| abstract_inverted_index.inference, | 115 |
| abstract_inverted_index.iteration, | 65 |
| abstract_inverted_index.meta-skill | 41 |
| abstract_inverted_index.processes. | 36 |
| abstract_inverted_index.remarkable | 6 |
| abstract_inverted_index.responses. | 76 |
| abstract_inverted_index.demonstrate | 128 |
| abstract_inverted_index.experiments | 122 |
| abstract_inverted_index.improvement | 98 |
| abstract_inverted_index.information | 157 |
| abstract_inverted_index.mathematics | 124 |
| abstract_inverted_index.progressive | 97 |
| abstract_inverted_index.versatility | 7 |
| abstract_inverted_index.capabilities | 49, 134 |
| abstract_inverted_index.demonstrated | 5 |
| abstract_inverted_index.development. | 164 |
| abstract_inverted_index.instructions | 72 |
| abstract_inverted_index.participants | 161 |
| abstract_inverted_index.self-improve | 29 |
| abstract_inverted_index.Subsequently, | 54 |
| abstract_inverted_index.intervention. | 139 |
| abstract_inverted_index.self-feedback | 51, 82 |
| abstract_inverted_index.transitioning | 153 |
| abstract_inverted_index.self-evolution | 102 |
| abstract_inverted_index.(Self-Evolution | 18 |
| abstract_inverted_index.self-evolution. | 62 |
| abstract_inverted_index.self-refinement | 113 |
| abstract_inverted_index.self-refinement. | 53, 84 |
| abstract_inverted_index.self-reflection, | 31 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 9 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.800000011920929 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |