{"id":"https://openalex.org/W4407219009","doi":"https://doi.org/10.9781/ijimai.2025.02.001","title":"Improved Fine-Tuned Reinforcement Learning From Human Feedback Using Prompting Methods for News Summarization.","display_name":"Improved Fine-Tuned Reinforcement Learning From Human Feedback Using Prompting Methods for News Summarization.","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407219009","doi":"https://doi.org/10.9781/ijimai.2025.02.001"},"language":"en","primary_location":{"id":"doi:10.9781/ijimai.2025.02.001","doi":"https://doi.org/10.9781/ijimai.2025.02.001","is_oa":true,"landing_page_url":"https://doi.org/10.9781/ijimai.2025.02.001","pdf_url":"https://www.ijimai.org/index.php/ijimai/article/download/259/105","source":{"id":"https://openalex.org/S2738898797","display_name":"International Journal of Interactive Multimedia and Artificial Intelligence","issn_l":"1989-1660","issn":["1989-1660"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","dongbi-c","fecyt-seal","latindex","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310321767","host_organization_name":"International University of La Rioja","host_organization_lineage":["https://openalex.org/P4310321767"],"host_organization_lineage_names":["International University of La Rioja"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Interactive Multimedia and Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.ijimai.org/index.php/ijimai/article/download/259/105","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031398742","display_name":"Sini Raj Pulari","orcid":"https://orcid.org/0000-0001-6591-1655","observed_orcids":["https://orcid.org/0000-0001-6591-1655"]},"institutions":[{"id":"https://openalex.org/I149313025","display_name":"Vignan's Foundation for Science, Technology & Research","ror":"https://ror.org/03bzf1g85","country_code":"IN","type":"education","lineage":["https://openalex.org/I149313025"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sini Raj Pulari","raw_affiliation_strings":["Vignan's Foundation for Science, Technology & Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vignan's Foundation for Science, Technology & Research","institution_ids":["https://openalex.org/I149313025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022447097","display_name":"M. Umadevi","orcid":"https://orcid.org/0000-0002-4242-5547","observed_orcids":["https://orcid.org/0000-0002-4242-5547"]},"institutions":[{"id":"https://openalex.org/I149313025","display_name":"Vignan's Foundation for Science, Technology & Research","ror":"https://ror.org/03bzf1g85","country_code":"IN","type":"education","lineage":["https://openalex.org/I149313025"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Maramreddy Umadevi","raw_affiliation_strings":["Vignan's Foundation for Science, Technology & Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vignan's Foundation for Science, Technology & Research","institution_ids":["https://openalex.org/I149313025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088256645","display_name":"Shriram K. Vasudevan","orcid":"https://orcid.org/0000-0002-4619-0079","observed_orcids":["https://orcid.org/0000-0002-4619-0079"]},"institutions":[{"id":"https://openalex.org/I4210146682","display_name":"Intel (India)","ror":"https://ror.org/04f2n1245","country_code":"IN","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210146682"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shriram K. Vasudevan","raw_affiliation_strings":["Intel (India)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel (India)","institution_ids":["https://openalex.org/I4210146682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7723,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71580767,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"9","issue":"2","first_page":"59","last_page":"67"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8974999785423279,"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/T10028","display_name":"Topic Modeling","score":0.8974999785423279,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.03480000048875809,"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":0.024399999529123306,"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/reinforcement-learning-from-human-feedback","display_name":"reinforcement learning from human feedback","score":0.9660000205039978},{"id":"https://openalex.org/keywords/news-summarization","display_name":"news summarization","score":0.8009999990463257},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.9200000166893005},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"multi-objective optimization","score":0.8740000128746033},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8769999742507935},{"id":"https://openalex.org/keywords/chatgpt","display_name":"ChatGPT","score":0.8870000243186951},{"id":"https://openalex.org/keywords/summarization-evaluation-metrics","display_name":"summarization evaluation metrics","score":0.6119999885559082}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9498711228370667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8898993730545044},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.811417818069458},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5187606811523438},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41245919466018677},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4041055142879486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36220240592956543},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0560472309589386},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.9781/ijimai.2025.02.001","doi":"https://doi.org/10.9781/ijimai.2025.02.001","is_oa":true,"landing_page_url":"https://doi.org/10.9781/ijimai.2025.02.001","pdf_url":"https://www.ijimai.org/index.php/ijimai/article/download/259/105","source":{"id":"https://openalex.org/S2738898797","display_name":"International Journal of Interactive Multimedia and Artificial Intelligence","issn_l":"1989-1660","issn":["1989-1660"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","dongbi-c","fecyt-seal","latindex","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310321767","host_organization_name":"International University of La Rioja","host_organization_lineage":["https://openalex.org/P4310321767"],"host_organization_lineage_names":["International University of La Rioja"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Interactive Multimedia and Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:reunir.unir.net:123456789/19232","doi":null,"is_oa":true,"landing_page_url":"https://reunir.unir.net/handle/123456789/19232","pdf_url":"https://reunir.unir.net/bitstream/123456789/19232/1/Improved%20Fine-Tuned%20Reinforcement%20Learning%20From%20Human%20Feedback%20Using%20Prompting%20Methods%20for%20News%20Summarization.pdf","source":{"id":"https://openalex.org/S4306400329","display_name":"Re-Unir (International University of La Rioja)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:4e4281a363ad4912bb1a876607e0dcff","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/4e4281a363ad4912bb1a876607e0dcff","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Interactive Multimedia and Artificial Intelligence, Vol 9, Iss 2 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.9781/ijimai.2025.02.001","doi":"https://doi.org/10.9781/ijimai.2025.02.001","is_oa":true,"landing_page_url":"https://doi.org/10.9781/ijimai.2025.02.001","pdf_url":"https://www.ijimai.org/index.php/ijimai/article/download/259/105","source":{"id":"https://openalex.org/S2738898797","display_name":"International Journal of Interactive Multimedia and Artificial Intelligence","issn_l":"1989-1660","issn":["1989-1660"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","dongbi-c","fecyt-seal","latindex","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310321767","host_organization_name":"International University of La Rioja","host_organization_lineage":["https://openalex.org/P4310321767"],"host_organization_lineage_names":["International University of La Rioja"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Interactive Multimedia and Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407219009.pdf","grobid_xml":"https://content.openalex.org/works/W4407219009.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2980282514","https://openalex.org/W2982399380","https://openalex.org/W4223908421","https://openalex.org/W4225934689","https://openalex.org/W4285141065","https://openalex.org/W4285191678","https://openalex.org/W4297435087","https://openalex.org/W4308244910","https://openalex.org/W4309444617","https://openalex.org/W4319453300","https://openalex.org/W4377121527","https://openalex.org/W4386215278","https://openalex.org/W4387428151","https://openalex.org/W4390023570","https://openalex.org/W4416542771","https://openalex.org/W7133200384"],"related_works":["https://openalex.org/W4403076929","https://openalex.org/W3082115681","https://openalex.org/W4402489471","https://openalex.org/W4388584595","https://openalex.org/W4393247779","https://openalex.org/W4417298827","https://openalex.org/W2971996420","https://openalex.org/W4414547772","https://openalex.org/W4404783718","https://openalex.org/W4402595822"],"abstract_inverted_index":{"ChatGPT":[0,22,36,45],"uses":[1],"a":[2,81,107,138],"generative":[3,16],"pretrained":[4],"transformer":[5],"neural":[6],"network":[7],"model,":[8],"which":[9,29,146],"is":[10,23,30,86,106],"under":[11],"the":[12,24,31,47,52,71,89,97,131,156,169,180,191],"larger":[13],"umbrella":[14],"of":[15,26,35,56,96,100,118,130,143,171,194],"models.":[17,77],"One":[18],"major":[19,72],"boom":[20],"after":[21],"advent":[25],"prompt":[27,177],"engineering,":[28],"most":[32],"critical":[33],"part":[34,129],"that":[37,85],"utilizes":[38],"Large":[39],"Language":[40],"Models":[41],"(LLM)":[42],"and":[43,54,122,183],"helps":[44],"provide":[46],"desired":[48],"outputs":[49],"based":[50],"on":[51],"style":[53],"tone":[55],"interactions":[57],"carried":[58],"out":[59],"with":[60,158,176],"it.":[61],"Reinforcement":[62],"learning":[63],"from":[64],"human":[65,82,101,141],"feedback":[66],"(RLHF)":[67],"was":[68],"used":[69],"as":[70,128],"aspect":[73],"for":[74,103,111,140],"fine-tuning":[75],"LLM-based":[76],"This":[78,160],"work":[79,185],"proposes":[80],"selection":[83,142],"strategy":[84,139],"incorporated":[87],"in":[88,168,179,190],"RLHF":[90,144],"process":[91,157],"to":[92,150,174],"prevent":[93],"undesirable":[94],"consequences":[95],"rightful":[98],"choice":[99],"reviewers":[102],"feedback.":[104],"H-Rouge":[105],"new":[108],"metric":[109],"proposed":[110,134],"humanized":[112],"AI":[113],"systems.":[114],"A":[115],"detailed":[116],"evaluation":[117],"State-of-the-art":[119],"summarization":[120,173,181],"algorithms":[121],"prompt-based":[123],"methods":[124,135],"have":[125,136],"been":[126],"provided":[127],"article.":[132],"The":[133],"introduced":[137],"models":[145],"employs":[147],"multi-objective":[148],"optimization":[149],"balance":[151],"various":[152],"goals":[153],"encountered":[154],"during":[155],"H-Rouge.":[159],"article":[161],"will":[162,186],"help":[163,187],"nuance":[164],"readers":[165],"conduct":[166],"research":[167],"field":[170],"text":[172],"start":[175],"engineering":[178],"field,":[182],"future":[184],"them":[188],"proceed":[189],"right":[192],"direction":[193],"research.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-02-07T00:00:00"}