This study extends prior research on using large language models (LLMs) to uncover return-predictive sentiment in Japanese 10-K reports by focusing on highly liquid stocks. Building on a dataset of Tokyo Stock Exchange-listed firms (2014–2023) and previously established methodologies, we narrow our scope to the TOPIX 100 and TOPIX 500—indices composed of the largest Japanese companies by market capitalization. Despite expectations that these well-followed and actively traded stocks should incorporate public information more efficiently, LLM-derived sentiment still predicts future returns, with larger abnormal returns (alpha) than when all listed stocks are included. These findings highlight the robustness of LLM-based approaches in detecting subtle signals within corporate disclosures and challenge the notion that highly liquid markets fully reflect available information. By highlighting the predictive power of LLM-extracted sentiment in large-cap portfolios, this study offers practical insights into how advanced natural language processing can enhance investment strategies, even in supposedly efficient segments of the equity market.
"},{"@language":"ja","@value":"本稿は、有価証券報告書におけるリターン予測可能なセンチメントを大規模言語モデル（LLM）によって抽出する先行研究を発展させ、時価総額が大きい企業で構成されるTOPIX 100およびTOPIX 500に分析対象を絞っている。これらの銘柄は、投資家による注目度が高く、取引も活発であるため公開情報が効率的に価格に反映されていると考えられる。しかしながら、LLMによって抽出されたセンチメントは依然として将来リターンの予測力を持ち、センチメントに基づく投資戦略は東証一部上場全銘柄を対象とした場合よりも大きな異常リターンをもたらしている。これらの発見は、企業の開示情報に含まれる微細なシグナルを検出するうえでのLLMベースのアプローチの頑健性を示すとともに、高流動性銘柄においても利用可能な情報が完全には価格に反映されていない可能性を示している。自然言語処理技術の高度化が、効率的とされる株式市場のセグメントにおいても投資戦略の高度化に寄与し得ることが示唆されている。
"}],"abstractLicenseFlag":"disallow"}],"creator":[{"@id":"https://cir.nii.ac.jp/crid/1410304704716980867","@type":"Researcher","foaf:name":[{"@language":"ja","@value":"中筋 萌"},{"@language":"en","@value":"NAKASUJI Moe"}],"jpcoar:affiliationName":[{"@language":"en","@value":"Kwansei Gakuin University"},{"@language":"ja","@value":"関西学院大学"}]},{"@id":"https://cir.nii.ac.jp/crid/1410304704716980865","@type":"Researcher","foaf:name":[{"@language":"ja","@value":"岡田 克彦"},{"@language":"en","@value":"OKADA Katsuhiko"}],"jpcoar:affiliationName":[{"@language":"en","@value":"Kwansei Gakuin University"},{"@language":"ja","@value":"関西学院大学"}]},{"@id":"https://cir.nii.ac.jp/crid/1410304704716980866","@type":"Researcher","foaf:name":[{"@language":"ja","@value":"月岡 靖智"},{"@language":"en","@value":"TSUKIOKA Yasutomo"}],"jpcoar:affiliationName":[{"@language":"en","@value":"Kwansei Gakuin University"},{"@language":"ja","@value":"関西学院大学"}]},{"@id":"https://cir.nii.ac.jp/crid/1410304704716980864","@type":"Researcher","foaf:name":[{"@language":"ja","@value":"山崎 高弘"},{"@language":"en","@value":"YAMASAKI Takahiro"}],"jpcoar:affiliationName":[{"@language":"en","@value":"Osaka Sangyo University"},{"@language":"ja","@value":"大阪産業大学"}]}],"publication":{"publicationIdentifier":[{"@type":"EISSN","@value":"27587347"}],"prism:publicationName":[{"@language":"en","@value":"Proceedings of the Annual Conference of JSAI"},{"@language":"ja","@value":"人工知能学会全国大会論文集"},{"@language":"en","@value":"Proc. of JSAI"},{"@language":"ja","@value":"JSAI大会論文集"}],"dc:publisher":[{"@language":"en","@value":"The Japanese Society for Artificial Intelligence"},{"@language":"ja","@value":"一般社団法人 人工知能学会"}],"prism:publicationDate":"2025","prism:volume":"JSAI2025","prism:number":"0","prism:startingPage":"1H3OS8a05","prism:endingPage":"1H3OS8a05"},"jpcoar:conferenceName":"2025年度人工知能学会全国大会（第39回）","jpcoar:conferencePlace":"大阪国際会議場＋オンライン","availableAt":"2025","foaf:topic":[{"@id":"https://cir.nii.ac.jp/all?q=%E5%A4%A7%E8%A6%8F%E6%A8%A1%E8%A8%80%E8%AA%9E%E3%83%A2%E3%83%87%E3%83%AB","dc:title":"大規模言語モデル"},{"@id":"https://cir.nii.ac.jp/all?q=%E3%83%AA%E3%82%BF%E3%83%BC%E3%83%B3%E3%81%AE%E4%BA%88%E6%B8%AC%E5%8F%AF%E8%83%BD%E6%80%A7","dc:title":"リターンの予測可能性"},{"@id":"https://cir.nii.ac.jp/all?q=%E6%9C%89%E4%BE%A1%E8%A8%BC%E5%88%B8%E5%A0%B1%E5%91%8A%E6%9B%B8","dc:title":"有価証券報告書"},{"@id":"https://cir.nii.ac.jp/all?q=%E7%B5%8C%E5%96%B6%E8%80%85%E3%81%AB%E3%82%88%E3%82%8B%E8%B2%A1%E6%94%BF%E7%8A%B6%E6%85%8B","dc:title":"経営者による財政状態"},{"@id":"https://cir.nii.ac.jp/all?q=%E7%B5%8C%E5%96%B6%E6%88%90%E7%B8%BE%E5%8F%8A%E3%81%B3%E3%82%AD%E3%83%A3%E3%83%83%E3%82%B7%E3%83%A5%E3%83%95%E3%83%AD%E3%83%BC%E3%81%AE%E7%8A%B6%E6%B3%81%E3%81%AE%E5%88%86%E6%9E%90","dc:title":"経営成績及びキャッシュフローの状況の分析"},{"@id":"https://cir.nii.ac.jp/all?q=LLM","dc:title":"LLM"},{"@id":"https://cir.nii.ac.jp/all?q=return%20predictability","dc:title":"return predictability"},{"@id":"https://cir.nii.ac.jp/all?q=10-K%20report","dc:title":"10-K report"},{"@id":"https://cir.nii.ac.jp/all?q=MD%26A","dc:title":"MD&A"}],"dataSourceIdentifier":[{"@type":"JALC","@value":"oai:japanlinkcenter.org:2014130938"}]}