llome_ehrlich_benchmark_data_package Article Swipe
Angelica Chen
,
Samuel C. Stanton
,
Robert G. Alberstein
,
Andrew M. Watkins
,
Richard Bonneau
,
Vladimir Gligorijevi
,
Kyunghyun Cho
,
Nathan C. Frey
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.5281/zenodo.14926734
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.5281/zenodo.14926734
Although large language models (LLMs) have shown promise in biomolecule optimization problems, they incur heavy computational costs and struggle to satisfy precise constraints. On the other hand, specialized solvers like LaMBO-2 offer efficiency and fine-grained control but require more domain expertise. Comparing these approaches is challenging due to expensive laboratory validation and inadequate synthetic benchmarks. We address this by introducing Ehrlich functions, a synthetic test suite that captures the geometric structure of biophysical sequence optimization problems. With prompting alone, off-the-shelf LLMs struggle to optimize Ehrlich functions. In response, we propose LLOME (Language Model Optimization with Margin Expectation), a bilevel optimization routine for online black-box optimization. When combined with a novel preference learning loss, we find LLOME can not only learn to solve some Ehrlich functions, but can even perform as well as or better than LaMBO-2 on moderately difficult Ehrlich variants. However, LLMs also exhibit some likelihood-reward miscalibration and struggle without explicit rewards. Our results indicate LLMs can occasionally provide significant benefits, but specialized solvers are still competitive and incur less overhead.
Related Topics
Metadata
- Type
- preprint
- Language
- pt
- Landing Page
- http://arxiv.org/abs/2410.22296
- https://arxiv.org/pdf/2410.22296
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4404344192
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4404344192Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.5281/zenodo.14926734Digital Object Identifier
- Title
-
llome_ehrlich_benchmark_data_packageWork title
- Type
-
preprintOpenAlex work type
- Language
-
ptPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-02-26Full publication date if available
- Authors
-
Angelica Chen, Samuel C. Stanton, Robert G. Alberstein, Andrew M. Watkins, Richard Bonneau, Vladimir Gligorijevi, Kyunghyun Cho, Nathan C. FreyList of authors in order
- Landing page
-
https://arxiv.org/abs/2410.22296Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2410.22296Direct 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/2410.22296Direct OA link when available
- Concepts
-
Sequence (biology), Computational biology, Biology, Computer science, BiochemistryTop 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/W4404344192 |
|---|---|
| doi | https://doi.org/10.5281/zenodo.14926734 |
| ids.doi | https://doi.org/10.5281/zenodo.14926734 |
| ids.openalex | https://openalex.org/W4404344192 |
| fwci | |
| type | preprint |
| title | llome_ehrlich_benchmark_data_package |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10015 |
| topics[0].field.id | https://openalex.org/fields/13 |
| topics[0].field.display_name | Biochemistry, Genetics and Molecular Biology |
| topics[0].score | 0.9466000199317932 |
| topics[0].domain.id | https://openalex.org/domains/1 |
| topics[0].domain.display_name | Life Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1312 |
| topics[0].subfield.display_name | Molecular Biology |
| topics[0].display_name | Genomics and Phylogenetic Studies |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2778112365 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6910009384155273 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q3511065 |
| concepts[0].display_name | Sequence (biology) |
| concepts[1].id | https://openalex.org/C70721500 |
| concepts[1].level | 1 |
| concepts[1].score | 0.40705326199531555 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q177005 |
| concepts[1].display_name | Computational biology |
| concepts[2].id | https://openalex.org/C86803240 |
| concepts[2].level | 0 |
| concepts[2].score | 0.35047242045402527 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[2].display_name | Biology |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.32194966077804565 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C55493867 |
| concepts[4].level | 1 |
| concepts[4].score | 0.14280807971954346 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[4].display_name | Biochemistry |
| keywords[0].id | https://openalex.org/keywords/sequence |
| keywords[0].score | 0.6910009384155273 |
| keywords[0].display_name | Sequence (biology) |
| keywords[1].id | https://openalex.org/keywords/computational-biology |
| keywords[1].score | 0.40705326199531555 |
| keywords[1].display_name | Computational biology |
| keywords[2].id | https://openalex.org/keywords/biology |
| keywords[2].score | 0.35047242045402527 |
| keywords[2].display_name | Biology |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.32194966077804565 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/biochemistry |
| keywords[4].score | 0.14280807971954346 |
| keywords[4].display_name | Biochemistry |
| language | pt |
| locations[0].id | pmh:oai:arXiv.org:2410.22296 |
| 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/2410.22296 |
| 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/2410.22296 |
| locations[1].id | doi:10.48550/arxiv.2410.22296 |
| 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.2410.22296 |
| locations[2].id | doi:10.5281/zenodo.14926733 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306400562 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | True |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | Zenodo (CERN European Organization for Nuclear Research) |
| locations[2].source.host_organization | https://openalex.org/I67311998 |
| locations[2].source.host_organization_name | European Organization for Nuclear Research |
| locations[2].source.host_organization_lineage | https://openalex.org/I67311998 |
| locations[2].license | cc-by |
| locations[2].pdf_url | |
| locations[2].version | |
| locations[2].raw_type | dataset |
| locations[2].license_id | https://openalex.org/licenses/cc-by |
| locations[2].is_accepted | False |
| locations[2].is_published | |
| locations[2].raw_source_name | |
| locations[2].landing_page_url | https://doi.org/10.5281/zenodo.14926733 |
| locations[3].id | doi:10.5281/zenodo.14926734 |
| locations[3].is_oa | True |
| locations[3].source.id | https://openalex.org/S4306400562 |
| locations[3].source.issn | |
| locations[3].source.type | repository |
| locations[3].source.is_oa | True |
| locations[3].source.issn_l | |
| locations[3].source.is_core | False |
| locations[3].source.is_in_doaj | False |
| locations[3].source.display_name | Zenodo (CERN European Organization for Nuclear Research) |
| locations[3].source.host_organization | https://openalex.org/I67311998 |
| locations[3].source.host_organization_name | European Organization for Nuclear Research |
| locations[3].source.host_organization_lineage | https://openalex.org/I67311998 |
| locations[3].license | cc-by |
| locations[3].pdf_url | |
| locations[3].version | |
| locations[3].raw_type | dataset |
| locations[3].license_id | https://openalex.org/licenses/cc-by |
| locations[3].is_accepted | False |
| locations[3].is_published | |
| locations[3].raw_source_name | |
| locations[3].landing_page_url | https://doi.org/10.5281/zenodo.14926734 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5101278232 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-1744-3209 |
| authorships[0].author.display_name | Angelica Chen |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Chen, Angelica |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5102736359 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-1664-2465 |
| authorships[1].author.display_name | Samuel C. Stanton |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Stanton, Samuel D. |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5049530706 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-6655-8811 |
| authorships[2].author.display_name | Robert G. Alberstein |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Alberstein, Robert G. |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5001503348 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-1617-1720 |
| authorships[3].author.display_name | Andrew M. Watkins |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Watkins, Andrew M. |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5055203249 |
| authorships[4].author.orcid | https://orcid.org/0000-0003-4354-7906 |
| authorships[4].author.display_name | Richard Bonneau |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Bonneau, Richard |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5114634580 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Vladimir Gligorijevi |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Gligorijevi, Vladimir |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5091175785 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-1669-3211 |
| authorships[6].author.display_name | Kyunghyun Cho |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Cho, Kyunghyun |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5090160831 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-5291-6131 |
| authorships[7].author.display_name | Nathan C. Frey |
| authorships[7].author_position | last |
| authorships[7].raw_author_name | Frey, Nathan C. |
| authorships[7].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/2410.22296 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-11-14T00:00:00 |
| display_name | llome_ehrlich_benchmark_data_package |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10015 |
| primary_topic.field.id | https://openalex.org/fields/13 |
| primary_topic.field.display_name | Biochemistry, Genetics and Molecular Biology |
| primary_topic.score | 0.9466000199317932 |
| primary_topic.domain.id | https://openalex.org/domains/1 |
| primary_topic.domain.display_name | Life Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1312 |
| primary_topic.subfield.display_name | Molecular Biology |
| primary_topic.display_name | Genomics and Phylogenetic Studies |
| related_works | https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W4391375266, https://openalex.org/W2082860237, https://openalex.org/W2119695867, https://openalex.org/W2130076355, https://openalex.org/W1990804418, https://openalex.org/W1993764875, https://openalex.org/W2046158694, https://openalex.org/W2788277189 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 4 |
| best_oa_location.id | pmh:oai:arXiv.org:2410.22296 |
| 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/2410.22296 |
| 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/2410.22296 |
| primary_location.id | pmh:oai:arXiv.org:2410.22296 |
| 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/2410.22296 |
| 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/2410.22296 |
| publication_date | 2025-02-26 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 62, 97, 108 |
| abstract_inverted_index.In | 86 |
| abstract_inverted_index.On | 23 |
| abstract_inverted_index.We | 55 |
| abstract_inverted_index.as | 129, 131 |
| abstract_inverted_index.by | 58 |
| abstract_inverted_index.in | 8 |
| abstract_inverted_index.is | 44 |
| abstract_inverted_index.of | 71 |
| abstract_inverted_index.on | 136 |
| abstract_inverted_index.or | 132 |
| abstract_inverted_index.to | 19, 47, 82, 120 |
| abstract_inverted_index.we | 88, 113 |
| abstract_inverted_index.Our | 153 |
| abstract_inverted_index.and | 17, 33, 51, 148, 168 |
| abstract_inverted_index.are | 165 |
| abstract_inverted_index.but | 36, 125, 162 |
| abstract_inverted_index.can | 116, 126, 157 |
| abstract_inverted_index.due | 46 |
| abstract_inverted_index.for | 101 |
| abstract_inverted_index.not | 117 |
| abstract_inverted_index.the | 24, 68 |
| abstract_inverted_index.LLMs | 80, 142, 156 |
| abstract_inverted_index.When | 105 |
| abstract_inverted_index.With | 76 |
| abstract_inverted_index.also | 143 |
| abstract_inverted_index.even | 127 |
| abstract_inverted_index.find | 114 |
| abstract_inverted_index.have | 5 |
| abstract_inverted_index.less | 170 |
| abstract_inverted_index.like | 29 |
| abstract_inverted_index.more | 38 |
| abstract_inverted_index.only | 118 |
| abstract_inverted_index.some | 122, 145 |
| abstract_inverted_index.test | 64 |
| abstract_inverted_index.than | 134 |
| abstract_inverted_index.that | 66 |
| abstract_inverted_index.they | 12 |
| abstract_inverted_index.this | 57 |
| abstract_inverted_index.well | 130 |
| abstract_inverted_index.with | 94, 107 |
| abstract_inverted_index.LLOME | 90, 115 |
| abstract_inverted_index.Model | 92 |
| abstract_inverted_index.costs | 16 |
| abstract_inverted_index.hand, | 26 |
| abstract_inverted_index.heavy | 14 |
| abstract_inverted_index.incur | 13, 169 |
| abstract_inverted_index.large | 1 |
| abstract_inverted_index.learn | 119 |
| abstract_inverted_index.loss, | 112 |
| abstract_inverted_index.novel | 109 |
| abstract_inverted_index.offer | 31 |
| abstract_inverted_index.other | 25 |
| abstract_inverted_index.shown | 6 |
| abstract_inverted_index.solve | 121 |
| abstract_inverted_index.still | 166 |
| abstract_inverted_index.suite | 65 |
| abstract_inverted_index.these | 42 |
| abstract_inverted_index.(LLMs) | 4 |
| abstract_inverted_index.Margin | 95 |
| abstract_inverted_index.alone, | 78 |
| abstract_inverted_index.better | 133 |
| abstract_inverted_index.domain | 39 |
| abstract_inverted_index.models | 3 |
| abstract_inverted_index.online | 102 |
| abstract_inverted_index.Ehrlich | 60, 84, 123, 139 |
| abstract_inverted_index.LaMBO-2 | 30, 135 |
| abstract_inverted_index.address | 56 |
| abstract_inverted_index.bilevel | 98 |
| abstract_inverted_index.control | 35 |
| abstract_inverted_index.exhibit | 144 |
| abstract_inverted_index.perform | 128 |
| abstract_inverted_index.precise | 21 |
| abstract_inverted_index.promise | 7 |
| abstract_inverted_index.propose | 89 |
| abstract_inverted_index.provide | 159 |
| abstract_inverted_index.require | 37 |
| abstract_inverted_index.results | 154 |
| abstract_inverted_index.routine | 100 |
| abstract_inverted_index.satisfy | 20 |
| abstract_inverted_index.solvers | 28, 164 |
| abstract_inverted_index.without | 150 |
| abstract_inverted_index.Although | 0 |
| abstract_inverted_index.However, | 141 |
| abstract_inverted_index.captures | 67 |
| abstract_inverted_index.combined | 106 |
| abstract_inverted_index.explicit | 151 |
| abstract_inverted_index.indicate | 155 |
| abstract_inverted_index.language | 2 |
| abstract_inverted_index.learning | 111 |
| abstract_inverted_index.optimize | 83 |
| abstract_inverted_index.rewards. | 152 |
| abstract_inverted_index.sequence | 73 |
| abstract_inverted_index.struggle | 18, 81, 149 |
| abstract_inverted_index.(Language | 91 |
| abstract_inverted_index.Comparing | 41 |
| abstract_inverted_index.benefits, | 161 |
| abstract_inverted_index.black-box | 103 |
| abstract_inverted_index.difficult | 138 |
| abstract_inverted_index.expensive | 48 |
| abstract_inverted_index.geometric | 69 |
| abstract_inverted_index.overhead. | 171 |
| abstract_inverted_index.problems, | 11 |
| abstract_inverted_index.problems. | 75 |
| abstract_inverted_index.prompting | 77 |
| abstract_inverted_index.response, | 87 |
| abstract_inverted_index.structure | 70 |
| abstract_inverted_index.synthetic | 53, 63 |
| abstract_inverted_index.variants. | 140 |
| abstract_inverted_index.approaches | 43 |
| abstract_inverted_index.efficiency | 32 |
| abstract_inverted_index.expertise. | 40 |
| abstract_inverted_index.functions, | 61, 124 |
| abstract_inverted_index.functions. | 85 |
| abstract_inverted_index.inadequate | 52 |
| abstract_inverted_index.laboratory | 49 |
| abstract_inverted_index.moderately | 137 |
| abstract_inverted_index.preference | 110 |
| abstract_inverted_index.validation | 50 |
| abstract_inverted_index.benchmarks. | 54 |
| abstract_inverted_index.biomolecule | 9 |
| abstract_inverted_index.biophysical | 72 |
| abstract_inverted_index.challenging | 45 |
| abstract_inverted_index.competitive | 167 |
| abstract_inverted_index.introducing | 59 |
| abstract_inverted_index.significant | 160 |
| abstract_inverted_index.specialized | 27, 163 |
| abstract_inverted_index.Optimization | 93 |
| abstract_inverted_index.constraints. | 22 |
| abstract_inverted_index.fine-grained | 34 |
| abstract_inverted_index.occasionally | 158 |
| abstract_inverted_index.optimization | 10, 74, 99 |
| abstract_inverted_index.Expectation), | 96 |
| abstract_inverted_index.computational | 15 |
| abstract_inverted_index.off-the-shelf | 79 |
| abstract_inverted_index.optimization. | 104 |
| abstract_inverted_index.miscalibration | 147 |
| abstract_inverted_index.likelihood-reward | 146 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 8 |
| citation_normalized_percentile |