{"id":"https://openalex.org/W7155416622","doi":"https://doi.org/10.48550/arxiv.2604.19779","title":"ESGLens: An LLM-Based RAG Framework for Interactive ESG Report Analysis and Score Prediction","display_name":"ESGLens: An LLM-Based RAG Framework for Interactive ESG Report Analysis and Score Prediction","publication_year":2026,"publication_date":"2026-03-29","ids":{"openalex":"https://openalex.org/W7155416622","doi":"https://doi.org/10.48550/arxiv.2604.19779"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.19779","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19779","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":null,"license_id":null,"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.2604.19779","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134430143","display_name":"Tsung-Yu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang, Tsung-Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134369609","display_name":"Meng-Chi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Meng-Chi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5134430143"],"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.27970001101493835,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.27970001101493835,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.05900000035762787,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.04839999973773956,"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/traceability","display_name":"Traceability","score":0.5343999862670898},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.5034999847412109},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47440001368522644},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4668000042438507},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.46219998598098755},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.42260000109672546},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4056999981403351},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.39469999074935913},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.3898000121116638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676800012588501},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5521000027656555},{"id":"https://openalex.org/C153876917","wikidata":"https://www.wikidata.org/wiki/Q899704","display_name":"Traceability","level":2,"score":0.5343999862670898},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4668000042438507},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41929998993873596},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3718000054359436},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C20256973","wikidata":"https://www.wikidata.org/wiki/Q1050272","display_name":"Standard score","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.19779","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19779","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.19779","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19779","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Environmental,":[0],"Social,":[1],"and":[2,16,25,59,92,99,106,136,149,186,221,226],"Governance":[3],"(ESG)":[4],"reports":[5,129],"are":[6],"central":[7],"to":[8,40,109,188,211,223,230],"investment":[9],"decision-making,":[10],"yet":[11],"their":[12],"length,":[13],"heterogeneous":[14,78],"content,":[15],"lack":[17],"of":[18,165,198],"standardized":[19],"structure":[20],"make":[21],"manual":[22],"analysis":[23],"costly":[24],"inconsistent.":[26],"We":[27,122,215],"present":[28],"ESGLens,":[29],"a":[30,74,87,100,110,158,162,175],"proof-of-concept":[31],"framework":[32,125],"combining":[33],"retrieval-augmented":[34],"generation":[35],"(RAG)":[36],"with":[37,56,96,157,207],"prompt-engineered":[38],"extraction":[39,46,89],"automate":[41],"three":[42,143],"tasks:":[43],"(1)~structured":[44],"information":[45,94],"guided":[47],"by":[48],"Global":[49],"Reporting":[50],"Initiative":[51],"(GRI)":[52],"standards,":[53],"(2)~interactive":[54],"question-answering":[55],"source":[57,205],"traceability,":[58],"(3)~ESG":[60],"score":[61],"prediction":[62],"via":[63],"regression":[64,111],"on":[65,126],"LLM-generated":[66],"embeddings.":[67],"ESGLens":[68],"is":[69],"purpose-built":[70],"for":[71],"the":[72,124,133,182,189,204,228],"domain:":[73],"report-processing":[75],"module":[76,90,102],"segments":[77],"PDF":[79],"content":[80],"into":[81],"typed":[82],"chunks":[83],"(text,":[84],"tables,":[85],"charts);":[86],"GRI-guided":[88],"retrieves":[91],"synthesizes":[93],"aligned":[95],"specific":[97],"standards;":[98],"scoring":[101],"embeds":[103],"extracted":[104,200],"summaries":[105],"feeds":[107],"them":[108],"model":[112],"trained":[113],"against":[114,170,203],"London":[115],"Stock":[116],"Exchange":[117],"Group":[118],"(LSEG)":[119],"reference":[120],"scores.":[121],"evaluate":[123],"approximately":[127],"300":[128],"from":[130],"companies":[131],"in":[132],"QQQ,":[134],"S\\&P~500,":[135],"Russell~1000":[137],"indices":[138],"(fiscal":[139],"year":[140],"2022).":[141],"Among":[142],"embedding":[144],"methods":[145],"(ChatGPT,":[146],"BERT,":[147],"RoBERTa)":[148],"two":[150,208],"regressors":[151],"(Neural":[152],"Network,":[153],"LightGBM),":[154],"ChatGPT":[155],"embeddings":[156],"Neural":[159],"Network":[160],"achieve":[161],"Pearson":[163],"correlation":[164],"0.48":[166],"($R^{2}":[167],"\\approx":[168],"0.23$)":[169],"LSEG":[171],"ground-truth":[172],"scores":[173],"--":[174],"modest":[176],"but":[177],"statistically":[178],"meaningful":[179],"signal":[180],"given":[181],"${\\sim}300$-report":[183],"training":[184],"set":[185],"restriction":[187,222],"environmental":[190,224],"pillar.":[191],"A":[192],"traceability":[193],"audit":[194],"shows":[195],"that":[196],"8":[197],"10":[199],"claims":[201],"verify":[202],"document,":[206],"failures":[209],"attributable":[210],"few-shot":[212],"example":[213],"leakage.":[214],"discuss":[216],"limitations":[217],"including":[218],"dataset":[219],"size":[220],"indicators,":[225],"release":[227],"code":[229],"support":[231],"reproducibility.":[232]},"counts_by_year":[],"updated_date":"2026-04-24T06:07:52.864757","created_date":"2026-04-24T00:00:00"}