LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation Article Swipe
Xi Ye
,
Fangcong Yin
,
Ying‐Hui He
,
J. Zhang
,
H. W. Yen
,
Tianyu Gao
,
Greg Durrett
,
Danqi Chen
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2501.05414
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2501.05414
Existing benchmarks for evaluating long-context language models (LCLMs) primarily focus on long-context recall, requiring models to produce short responses based on a few critical snippets while processing thousands of irrelevant tokens. We introduce LongProc (Long Procedural Generation), a new benchmark that requires both the integration of highly dispersed information and long-form generation. LongProc consists of six diverse procedural generation tasks, such as extracting structured information from HTML pages into a TSV format and executing complex search procedures to create travel plans. These tasks challenge LCLMs by testing their ability to follow detailed procedural instructions, synthesize and reason over dispersed information, and generate structured, long-form outputs (up to 8K tokens). Furthermore, as these tasks adhere to deterministic procedures and yield structured outputs, they enable reliable rule-based evaluation. We evaluated 23 LCLMs, including instruction-tuned models and recent reasoning models, on LongProc at three difficulty levels, with the maximum number of output tokens set at 500, 2K, and 8K. Notably, while all tested models claim a context window size above 32K tokens, open-weight models typically falter on 2K-token tasks, and closed-source models like GPT-4o show significant degradation on 8K-token tasks. Reasoning models achieve stronger overall performance in long-form generation, benefiting from long CoT training. Further analysis reveals that LCLMs struggle to maintain long-range coherence in long-form generations. These findings highlight critical limitations in current LCLMs and suggest substantial room for improvement. Data and code available at: https://princeton-pli.github.io/LongProc.
Related Topics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2501.05414
- https://arxiv.org/pdf/2501.05414
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4406273368
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4406273368Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2501.05414Digital Object Identifier
- Title
-
LongProc: Benchmarking Long-Context Language Models on Long Procedural GenerationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-01-09Full publication date if available
- Authors
-
Xi Ye, Fangcong Yin, Ying‐Hui He, J. Zhang, H. W. Yen, Tianyu Gao, Greg Durrett, Danqi ChenList of authors in order
- Landing page
-
https://arxiv.org/abs/2501.05414Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2501.05414Direct 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/2501.05414Direct OA link when available
- Concepts
-
Benchmarking, Context (archaeology), Computer science, Business, History, Marketing, ArchaeologyTop 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/W4406273368 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2501.05414 |
| ids.doi | https://doi.org/10.48550/arxiv.2501.05414 |
| ids.openalex | https://openalex.org/W4406273368 |
| fwci | 0.0 |
| type | preprint |
| title | LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10181 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9944999814033508 |
| 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 | Natural Language Processing Techniques |
| 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 | 0.9940000176429749 |
| 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/T12031 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.942799985408783 |
| 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 | Speech and dialogue systems |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C86251818 |
| concepts[0].level | 2 |
| concepts[0].score | 0.857162356376648 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q816754 |
| concepts[0].display_name | Benchmarking |
| concepts[1].id | https://openalex.org/C2779343474 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6242827773094177 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q3109175 |
| concepts[1].display_name | Context (archaeology) |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.5601645112037659 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C144133560 |
| concepts[3].level | 0 |
| concepts[3].score | 0.30203431844711304 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q4830453 |
| concepts[3].display_name | Business |
| concepts[4].id | https://openalex.org/C95457728 |
| concepts[4].level | 0 |
| concepts[4].score | 0.12270283699035645 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q309 |
| concepts[4].display_name | History |
| concepts[5].id | https://openalex.org/C162853370 |
| concepts[5].level | 1 |
| concepts[5].score | 0.0547221302986145 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q39809 |
| concepts[5].display_name | Marketing |
| concepts[6].id | https://openalex.org/C166957645 |
| concepts[6].level | 1 |
| concepts[6].score | 0.0 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q23498 |
| concepts[6].display_name | Archaeology |
| keywords[0].id | https://openalex.org/keywords/benchmarking |
| keywords[0].score | 0.857162356376648 |
| keywords[0].display_name | Benchmarking |
| keywords[1].id | https://openalex.org/keywords/context |
| keywords[1].score | 0.6242827773094177 |
| keywords[1].display_name | Context (archaeology) |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.5601645112037659 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/business |
| keywords[3].score | 0.30203431844711304 |
| keywords[3].display_name | Business |
| keywords[4].id | https://openalex.org/keywords/history |
| keywords[4].score | 0.12270283699035645 |
| keywords[4].display_name | History |
| keywords[5].id | https://openalex.org/keywords/marketing |
| keywords[5].score | 0.0547221302986145 |
| keywords[5].display_name | Marketing |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2501.05414 |
| 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/2501.05414 |
| 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/2501.05414 |
| locations[1].id | doi:10.48550/arxiv.2501.05414 |
| 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.2501.05414 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100579142 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Xi Ye |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Ye, Xi |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5099031453 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Fangcong Yin |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Yin, Fangcong |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5101114597 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-6857-0507 |
| authorships[2].author.display_name | Ying‐Hui He |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | He, Yinghui |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5029016146 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | J. Zhang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Zhang, Joie |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5111465448 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | H. W. Yen |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Yen, Howard |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5006863331 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-5178-0866 |
| authorships[5].author.display_name | Tianyu Gao |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Gao, Tianyu |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5015133105 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-7061-7298 |
| authorships[6].author.display_name | Greg Durrett |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Durrett, Greg |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5051064208 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-6226-6838 |
| authorships[7].author.display_name | Danqi Chen |
| authorships[7].author_position | last |
| authorships[7].raw_author_name | Chen, Danqi |
| 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/2501.05414 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10181 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9944999814033508 |
| 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 | Natural Language Processing Techniques |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W4238897586, https://openalex.org/W435179959, https://openalex.org/W2619091065, https://openalex.org/W2059640416, https://openalex.org/W1490753184, https://openalex.org/W2284465472, https://openalex.org/W2291782699 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2501.05414 |
| 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/2501.05414 |
| 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/2501.05414 |
| primary_location.id | pmh:oai:arXiv.org:2501.05414 |
| 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/2501.05414 |
| 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/2501.05414 |
| publication_date | 2025-01-09 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 21, 37, 69, 162 |
| abstract_inverted_index.23 | 128 |
| abstract_inverted_index.8K | 107 |
| abstract_inverted_index.We | 31, 126 |
| abstract_inverted_index.as | 61, 110 |
| abstract_inverted_index.at | 139, 151 |
| abstract_inverted_index.by | 85 |
| abstract_inverted_index.in | 193, 211, 219 |
| abstract_inverted_index.of | 28, 45, 54, 147 |
| abstract_inverted_index.on | 10, 20, 137, 173, 184 |
| abstract_inverted_index.to | 15, 77, 89, 106, 114, 207 |
| abstract_inverted_index.(up | 105 |
| abstract_inverted_index.2K, | 153 |
| abstract_inverted_index.32K | 167 |
| abstract_inverted_index.8K. | 155 |
| abstract_inverted_index.CoT | 199 |
| abstract_inverted_index.TSV | 70 |
| abstract_inverted_index.all | 158 |
| abstract_inverted_index.and | 49, 72, 95, 100, 117, 133, 154, 176, 222, 229 |
| abstract_inverted_index.at: | 232 |
| abstract_inverted_index.few | 22 |
| abstract_inverted_index.for | 2, 226 |
| abstract_inverted_index.new | 38 |
| abstract_inverted_index.set | 150 |
| abstract_inverted_index.six | 55 |
| abstract_inverted_index.the | 43, 144 |
| abstract_inverted_index.500, | 152 |
| abstract_inverted_index.Data | 228 |
| abstract_inverted_index.HTML | 66 |
| abstract_inverted_index.both | 42 |
| abstract_inverted_index.code | 230 |
| abstract_inverted_index.from | 65, 197 |
| abstract_inverted_index.into | 68 |
| abstract_inverted_index.like | 179 |
| abstract_inverted_index.long | 198 |
| abstract_inverted_index.over | 97 |
| abstract_inverted_index.room | 225 |
| abstract_inverted_index.show | 181 |
| abstract_inverted_index.size | 165 |
| abstract_inverted_index.such | 60 |
| abstract_inverted_index.that | 40, 204 |
| abstract_inverted_index.they | 121 |
| abstract_inverted_index.with | 143 |
| abstract_inverted_index.(Long | 34 |
| abstract_inverted_index.LCLMs | 84, 205, 221 |
| abstract_inverted_index.These | 81, 214 |
| abstract_inverted_index.above | 166 |
| abstract_inverted_index.based | 19 |
| abstract_inverted_index.claim | 161 |
| abstract_inverted_index.focus | 9 |
| abstract_inverted_index.pages | 67 |
| abstract_inverted_index.short | 17 |
| abstract_inverted_index.tasks | 82, 112 |
| abstract_inverted_index.their | 87 |
| abstract_inverted_index.these | 111 |
| abstract_inverted_index.three | 140 |
| abstract_inverted_index.while | 25, 157 |
| abstract_inverted_index.yield | 118 |
| abstract_inverted_index.GPT-4o | 180 |
| abstract_inverted_index.LCLMs, | 129 |
| abstract_inverted_index.adhere | 113 |
| abstract_inverted_index.create | 78 |
| abstract_inverted_index.enable | 122 |
| abstract_inverted_index.falter | 172 |
| abstract_inverted_index.follow | 90 |
| abstract_inverted_index.format | 71 |
| abstract_inverted_index.highly | 46 |
| abstract_inverted_index.models | 6, 14, 132, 160, 170, 178, 188 |
| abstract_inverted_index.number | 146 |
| abstract_inverted_index.output | 148 |
| abstract_inverted_index.plans. | 80 |
| abstract_inverted_index.reason | 96 |
| abstract_inverted_index.recent | 134 |
| abstract_inverted_index.search | 75 |
| abstract_inverted_index.tasks, | 59, 175 |
| abstract_inverted_index.tasks. | 186 |
| abstract_inverted_index.tested | 159 |
| abstract_inverted_index.tokens | 149 |
| abstract_inverted_index.travel | 79 |
| abstract_inverted_index.window | 164 |
| abstract_inverted_index.(LCLMs) | 7 |
| abstract_inverted_index.Further | 201 |
| abstract_inverted_index.ability | 88 |
| abstract_inverted_index.achieve | 189 |
| abstract_inverted_index.complex | 74 |
| abstract_inverted_index.context | 163 |
| abstract_inverted_index.current | 220 |
| abstract_inverted_index.diverse | 56 |
| abstract_inverted_index.levels, | 142 |
| abstract_inverted_index.maximum | 145 |
| abstract_inverted_index.models, | 136 |
| abstract_inverted_index.outputs | 104 |
| abstract_inverted_index.overall | 191 |
| abstract_inverted_index.produce | 16 |
| abstract_inverted_index.recall, | 12 |
| abstract_inverted_index.reveals | 203 |
| abstract_inverted_index.suggest | 223 |
| abstract_inverted_index.testing | 86 |
| abstract_inverted_index.tokens, | 168 |
| abstract_inverted_index.tokens. | 30 |
| abstract_inverted_index.2K-token | 174 |
| abstract_inverted_index.8K-token | 185 |
| abstract_inverted_index.Existing | 0 |
| abstract_inverted_index.LongProc | 33, 52, 138 |
| abstract_inverted_index.Notably, | 156 |
| abstract_inverted_index.analysis | 202 |
| abstract_inverted_index.consists | 53 |
| abstract_inverted_index.critical | 23, 217 |
| abstract_inverted_index.detailed | 91 |
| abstract_inverted_index.findings | 215 |
| abstract_inverted_index.generate | 101 |
| abstract_inverted_index.language | 5 |
| abstract_inverted_index.maintain | 208 |
| abstract_inverted_index.outputs, | 120 |
| abstract_inverted_index.reliable | 123 |
| abstract_inverted_index.requires | 41 |
| abstract_inverted_index.snippets | 24 |
| abstract_inverted_index.stronger | 190 |
| abstract_inverted_index.struggle | 206 |
| abstract_inverted_index.tokens). | 108 |
| abstract_inverted_index.Reasoning | 187 |
| abstract_inverted_index.available | 231 |
| abstract_inverted_index.benchmark | 39 |
| abstract_inverted_index.challenge | 83 |
| abstract_inverted_index.coherence | 210 |
| abstract_inverted_index.dispersed | 47, 98 |
| abstract_inverted_index.evaluated | 127 |
| abstract_inverted_index.executing | 73 |
| abstract_inverted_index.highlight | 216 |
| abstract_inverted_index.including | 130 |
| abstract_inverted_index.introduce | 32 |
| abstract_inverted_index.long-form | 50, 103, 194, 212 |
| abstract_inverted_index.primarily | 8 |
| abstract_inverted_index.reasoning | 135 |
| abstract_inverted_index.requiring | 13 |
| abstract_inverted_index.responses | 18 |
| abstract_inverted_index.thousands | 27 |
| abstract_inverted_index.training. | 200 |
| abstract_inverted_index.typically | 171 |
| abstract_inverted_index.Procedural | 35 |
| abstract_inverted_index.benchmarks | 1 |
| abstract_inverted_index.benefiting | 196 |
| abstract_inverted_index.difficulty | 141 |
| abstract_inverted_index.evaluating | 3 |
| abstract_inverted_index.extracting | 62 |
| abstract_inverted_index.generation | 58 |
| abstract_inverted_index.irrelevant | 29 |
| abstract_inverted_index.long-range | 209 |
| abstract_inverted_index.procedural | 57, 92 |
| abstract_inverted_index.procedures | 76, 116 |
| abstract_inverted_index.processing | 26 |
| abstract_inverted_index.rule-based | 124 |
| abstract_inverted_index.structured | 63, 119 |
| abstract_inverted_index.synthesize | 94 |
| abstract_inverted_index.degradation | 183 |
| abstract_inverted_index.evaluation. | 125 |
| abstract_inverted_index.generation, | 195 |
| abstract_inverted_index.generation. | 51 |
| abstract_inverted_index.information | 48, 64 |
| abstract_inverted_index.integration | 44 |
| abstract_inverted_index.limitations | 218 |
| abstract_inverted_index.open-weight | 169 |
| abstract_inverted_index.performance | 192 |
| abstract_inverted_index.significant | 182 |
| abstract_inverted_index.structured, | 102 |
| abstract_inverted_index.substantial | 224 |
| abstract_inverted_index.Furthermore, | 109 |
| abstract_inverted_index.Generation), | 36 |
| abstract_inverted_index.generations. | 213 |
| abstract_inverted_index.improvement. | 227 |
| abstract_inverted_index.information, | 99 |
| abstract_inverted_index.long-context | 4, 11 |
| abstract_inverted_index.closed-source | 177 |
| abstract_inverted_index.deterministic | 115 |
| abstract_inverted_index.instructions, | 93 |
| abstract_inverted_index.instruction-tuned | 131 |
| abstract_inverted_index.https://princeton-pli.github.io/LongProc. | 233 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 8 |
| citation_normalized_percentile |