{"id":"https://openalex.org/W7156778249","doi":"https://doi.org/10.48550/arxiv.2604.23430","title":"Automating Categorization of Scientific Texts with In-Context Learning and Prompt-Chaining in Large Language Models","display_name":"Automating Categorization of Scientific Texts with In-Context Learning and Prompt-Chaining in Large Language Models","publication_year":2026,"publication_date":"2026-04-25","ids":{"openalex":"https://openalex.org/W7156778249","doi":"https://doi.org/10.48550/arxiv.2604.23430"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.23430","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23430","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.23430","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061017602","display_name":"Gautam Kishore Shahi","orcid":"https://orcid.org/0000-0001-6168-0132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shahi, Gautam Kishore","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075502491","display_name":"Oliver Hummel","orcid":"https://orcid.org/0009-0007-3826-9477"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hummel, Oliver","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.2485000044107437,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.2485000044107437,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.1890999972820282,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.16030000150203705,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7479000091552734},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.5953999757766724},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.5892000198364258},{"id":"https://openalex.org/keywords/chaining","display_name":"Chaining","score":0.5383999943733215},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.47440001368522644},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46219998598098755},{"id":"https://openalex.org/keywords/subject-matter-expert","display_name":"Subject-matter expert","score":0.41999998688697815},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.3353999853134155}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7479000091552734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7372000217437744},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5953999757766724},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.5892000198364258},{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.5383999943733215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4975999891757965},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.44920000433921814},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.41999998688697815},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4171000123023987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3919999897480011},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38530001044273376},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.28459998965263367},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C148863701","wikidata":"https://www.wikidata.org/wiki/Q5292","display_name":"Encyclopedia","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C92548554","wikidata":"https://www.wikidata.org/wiki/Q2262868","display_name":"Domain model","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.23430","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23430","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.23430","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.23430","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.48032745718955994,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"relentless":[1],"expansion":[2],"of":[3,85,122,139,168,216],"scientific":[4,93],"literature":[5],"presents":[6],"significant":[7],"challenges":[8],"for":[9,28,68,180,190],"navigation":[10],"and":[11,24,31,77,131,134,185],"knowledge":[12],"discovery.":[13],"Within":[14],"Research":[15],"Information":[16],"Retrieval,":[17],"established":[18],"tasks":[19],"such":[20],"as":[21,107,115,225],"text":[22],"summarization":[23],"classification":[25,99,109,145,155],"remain":[26],"crucial":[27],"enabling":[29],"researchers":[30],"practitioners":[32],"to":[33,57,65,96,158,164,196,207],"effectively":[34],"navigate":[35],"this":[36,221],"vast":[37],"landscape,":[38],"so":[39],"that":[40,150],"efforts":[41],"have":[42],"increasingly":[43],"been":[44],"focused":[45],"on":[46,144,220],"developing":[47],"advanced":[48,123],"research":[49,217],"information":[50],"systems.":[51],"These":[52],"systems":[53],"aim":[54],"not":[55,204],"only":[56,227],"provide":[58],"standard":[59],"keyword-based":[60],"search":[61],"functionalities":[62],"but":[63],"also":[64],"incorporate":[66],"capabilities":[67],"automatic":[69],"content":[70],"categorization":[71],"within":[72],"knowledge-intensive":[73],"organizations":[74],"across":[75],"academia":[76],"industry.":[78],"This":[79],"study":[80],"systematically":[81],"evaluates":[82],"the":[83,103,112,120,137,140,165,169,177,197,212],"performance":[84,189],"off-the-shelf":[86],"Large":[87],"Language":[88],"Models":[89],"(LLMs)":[90],"in":[91,210],"analyzing":[92],"texts":[94],"according":[95],"a":[97,108],"given":[98],"scheme.":[100],"We":[101,118],"utilized":[102],"hierarchical":[104,223],"ORKG":[105,170],"taxonomy":[106],"framework,":[110],"employing":[111],"FORC":[113],"dataset":[114],"ground":[116],"truth.":[117],"investigated":[119],"effectiveness":[121],"prompt":[124,174,234],"engineering":[125],"strategies,":[126],"namely":[127],"In-Context":[128],"Learning":[129],"(ICL)":[130],"Prompt":[132,151],"Chaining,":[133],"experimentally":[135],"explored":[136],"influence":[138],"LLMs'":[141],"temperature":[142],"hyperparameter":[143],"accuracy.":[146],"Our":[147],"experiments":[148],"demonstrate":[149],"Chaining":[152],"yields":[153],"superior":[154],"accuracy":[156,231],"compared":[157,195],"pure":[159],"ICL,":[160],"particularly":[161],"when":[162],"applied":[163],"nested":[166],"structure":[167],"taxonomy.":[171],"LLMs":[172,202],"with":[173,233],"chaining":[175],"outperform":[176],"state-of-the-art":[178],"models":[179],"domain":[181],"(1st":[182],"level)":[183,193,215],"prediction":[184,194],"show":[186],"even":[187,232],"better":[188],"subject":[191],"(2nd":[192],"older":[198],"BERT":[199],"model.":[200],"However,":[201],"are":[203],"yet":[205],"able":[206],"perform":[208],"well":[209],"classifying":[211],"topic":[213],"(3rd":[214],"areas":[218],"based":[219],"specific":[222],"taxonomy,":[224],"they":[226],"reach":[228],"about":[229],"50%":[230],"chaining.":[235]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-29T00:00:00"}