{"id":"https://openalex.org/W7117251024","doi":"https://doi.org/10.48550/arxiv.2512.20082","title":"Adaptive Financial Sentiment Analysis for NIFTY 50 via Instruction-Tuned LLMs , RAG and Reinforcement Learning Approaches","display_name":"Adaptive Financial Sentiment Analysis for NIFTY 50 via Instruction-Tuned LLMs , RAG and Reinforcement Learning Approaches","publication_year":2025,"publication_date":"2025-12-23","ids":{"openalex":"https://openalex.org/W7117251024","doi":"https://doi.org/10.48550/arxiv.2512.20082"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2512.20082","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.20082","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2512.20082","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121287080","display_name":"Chaithra","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chaithra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121244953","display_name":"Kamesh Kadimisetty","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kadimisetty, Kamesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032581304","display_name":"Biju R. Mohan","orcid":"https://orcid.org/0000-0002-3928-8924"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohan, Biju R","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5121287080"],"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.9803000092506409,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9803000092506409,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.005400000140070915,"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/T11052","display_name":"Energy Load and Power Forecasting","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8519999980926514},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.6050000190734863},{"id":"https://openalex.org/keywords/stock-market","display_name":"Stock market","score":0.5960000157356262},{"id":"https://openalex.org/keywords/financial-market","display_name":"Financial market","score":0.525600016117096},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.47699999809265137},{"id":"https://openalex.org/keywords/stock","display_name":"Stock (firearms)","score":0.4763999879360199},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4632999897003174},{"id":"https://openalex.org/keywords/stock-exchange","display_name":"Stock exchange","score":0.3910999894142151}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8519999980926514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6320000290870667},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.6050000190734863},{"id":"https://openalex.org/C2780299701","wikidata":"https://www.wikidata.org/wiki/Q475000","display_name":"Stock market","level":3,"score":0.5960000157356262},{"id":"https://openalex.org/C19244329","wikidata":"https://www.wikidata.org/wiki/Q208697","display_name":"Financial market","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5020999908447266},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C204036174","wikidata":"https://www.wikidata.org/wiki/Q909380","display_name":"Stock (firearms)","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4221999943256378},{"id":"https://openalex.org/C200870193","wikidata":"https://www.wikidata.org/wiki/Q11691","display_name":"Stock exchange","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.3869999945163727},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.3059000074863434},{"id":"https://openalex.org/C103144560","wikidata":"https://www.wikidata.org/wiki/Q2670999","display_name":"Investment strategy","level":3,"score":0.305400013923645},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C2778865806","wikidata":"https://www.wikidata.org/wiki/Q6060850","display_name":"Investment decisions","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C88389905","wikidata":"https://www.wikidata.org/wiki/Q223371","display_name":"Stock market index","level":4,"score":0.26809999346733093},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C163068380","wikidata":"https://www.wikidata.org/wiki/Q3409313","display_name":"Economic forecasting","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2512.20082","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.20082","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2512.20082","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.20082","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Financial":[0],"sentiment":[1,23,37,60,88,128,231],"analysis":[2,24],"plays":[3],"a":[4,90,113,151],"crucial":[5],"role":[6],"in":[7,21,62],"informing":[8],"investment":[9],"decisions,":[10],"assessing":[11],"market":[12,34,56,141,203],"risk,":[13],"and":[14,202,208,224],"predicting":[15],"stock":[16,31,55,68,132],"price":[17],"trends.":[18],"Existing":[19],"works":[20],"financial":[22,230],"have":[25],"not":[26],"considered":[27],"the":[28,63,66,74,83,105,109,120,123,135,194,215],"impact":[29],"of":[30,65,108,122,217],"prices":[32],"or":[33],"feedback":[35,57,223],"on":[36,82,104,173,182],"analysis.":[38],"In":[39],"this":[40,145],"paper,":[41],"we":[42],"propose":[43],"an":[44],"adaptive":[45,146],"framework":[46],"that":[47,97,118,193],"integrates":[48],"large":[49],"language":[50],"models":[51,207],"(LLMs)":[52],"with":[53,129,221],"real-world":[54],"to":[58,137,140,167,190],"improve":[59],"classification":[61,199],"context":[64],"Indian":[67],"market.":[69],"The":[70,163,212],"proposed":[71,195],"methodology":[72],"fine-tunes":[73],"LLaMA":[75],"3.2":[76],"3B":[77],"model":[78],"using":[79,156],"instruction-based":[80],"learning":[81,153,226],"SentiFin":[84],"dataset.":[85],"To":[86,143],"enhance":[87],"predictions,":[89],"retrieval-augmented":[91],"generation":[92],"(RAG)":[93],"pipeline":[94],"is":[95,116,161],"employed":[96],"dynamically":[98],"selects":[99],"multi-source":[100],"contextual":[101],"information":[102],"based":[103,172],"cosine":[106],"similarity":[107],"sentence":[110],"embeddings.":[111],"Furthermore,":[112],"feedback-driven":[114],"module":[115],"introduced":[117],"adjusts":[119],"reliability":[121],"source":[124,169],"by":[125],"comparing":[126],"predicted":[127],"actual":[130],"next-day":[131],"returns,":[133],"allowing":[134],"system":[136,196],"iteratively":[138],"adapt":[139],"behavior.":[142],"generalize":[144],"mechanism":[147],"across":[148],"temporal":[149],"data,":[150],"reinforcement":[152,225],"agent":[154,165],"trained":[155],"proximal":[157],"policy":[158],"optimization":[159],"(PPO)":[160],"incorporated.":[162],"PPO":[164],"learns":[166],"optimize":[168],"weighting":[170],"policies":[171],"cumulative":[174],"reward":[175],"signals":[176],"from":[177,188],"sentiment-return":[178],"alignment.":[179],"Experimental":[180],"results":[181,213],"NIFTY":[183],"50":[184],"news":[185],"headlines":[186],"collected":[187],"2024":[189],"2025":[191],"demonstrate":[192],"significantly":[197],"improves":[198],"accuracy,":[200],"F1-score,":[201],"alignment":[204],"over":[205],"baseline":[206],"static":[209],"retrieval":[210],"methods.":[211],"validate":[214],"potential":[216],"combining":[218],"instruction-tuned":[219],"LLMs":[220],"dynamic":[222],"for":[227],"robust,":[228],"market-aware":[229],"modeling.":[232]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-12-25T00:00:00"}