@inproceedings{choi-etal-2026-text,
title = "From Text to Alpha: Can {LLM}s Track Evolving Signals in Corporate Disclosures?",
author = "Choi, Chanyeol and
Kim, Yoon and
Yu, Yu and
Cha, Young and
Golkhou, Zach and
Halperin, Igor and
Papaioannou, Georgios and
Kim, Minkyu and
Wang, Zhangyang and
Kwon, Jihoon and
Kim, Minjae and
Lopez-Lira, Alejandro and
Lee, Yongjae",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.174/",
pages = "2952--2961",
ISBN = "979-8-89176-460-6",
abstract = "Natural language processing (NLP) has been widely used in quantitative finance, but traditional methods often struggle to capture rich narratives in textual data, leaving potentially informative signals under-explored. Large language models (LLMs) offer a promising alternative as they are able to extract nuanced semantics. In this paper, we ask whether semantic signals extracted by LLMs from corporate disclosures predict abnormal returns (alpha) beyond broad market movements and common risk factors. We introduce a simple framework, *LLM as extractor, embedding as ruler*, which extracts context-aware, metric-focused textual spans and quantifies semantic changes across consecutive disclosure periods using embedding similarity. This allows us to measure the degree of metric shifting - how much firms move away from previously emphasized metrics, referred to as moving targets. In portfolio and cross-sectional regression tests against a recent traditional baseline, our method yields a moving-targets signal that delivers significant risk-adjusted alpha. Qualitative analysis suggests that these gains stem from preserving contextual qualifiers and filtering out non-metric terms that traditional approaches often miss."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choi-etal-2026-text">
<titleInfo>
<title>From Text to Alpha: Can LLMs Track Evolving Signals in Corporate Disclosures?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chanyeol</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Young</namePart>
<namePart type="family">Cha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zach</namePart>
<namePart type="family">Golkhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Igor</namePart>
<namePart type="family">Halperin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgios</namePart>
<namePart type="family">Papaioannou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minkyu</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhangyang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jihoon</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjae</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alejandro</namePart>
<namePart type="family">Lopez-Lira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjae</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Natural language processing (NLP) has been widely used in quantitative finance, but traditional methods often struggle to capture rich narratives in textual data, leaving potentially informative signals under-explored. Large language models (LLMs) offer a promising alternative as they are able to extract nuanced semantics. In this paper, we ask whether semantic signals extracted by LLMs from corporate disclosures predict abnormal returns (alpha) beyond broad market movements and common risk factors. We introduce a simple framework, *LLM as extractor, embedding as ruler*, which extracts context-aware, metric-focused textual spans and quantifies semantic changes across consecutive disclosure periods using embedding similarity. This allows us to measure the degree of metric shifting - how much firms move away from previously emphasized metrics, referred to as moving targets. In portfolio and cross-sectional regression tests against a recent traditional baseline, our method yields a moving-targets signal that delivers significant risk-adjusted alpha. Qualitative analysis suggests that these gains stem from preserving contextual qualifiers and filtering out non-metric terms that traditional approaches often miss.</abstract>
<identifier type="citekey">choi-etal-2026-text</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.174/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2952</start>
<end>2961</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Text to Alpha: Can LLMs Track Evolving Signals in Corporate Disclosures?
%A Choi, Chanyeol
%A Kim, Yoon
%A Yu, Yu
%A Cha, Young
%A Golkhou, Zach
%A Halperin, Igor
%A Papaioannou, Georgios
%A Kim, Minkyu
%A Wang, Zhangyang
%A Kwon, Jihoon
%A Kim, Minjae
%A Lopez-Lira, Alejandro
%A Lee, Yongjae
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F choi-etal-2026-text
%X Natural language processing (NLP) has been widely used in quantitative finance, but traditional methods often struggle to capture rich narratives in textual data, leaving potentially informative signals under-explored. Large language models (LLMs) offer a promising alternative as they are able to extract nuanced semantics. In this paper, we ask whether semantic signals extracted by LLMs from corporate disclosures predict abnormal returns (alpha) beyond broad market movements and common risk factors. We introduce a simple framework, *LLM as extractor, embedding as ruler*, which extracts context-aware, metric-focused textual spans and quantifies semantic changes across consecutive disclosure periods using embedding similarity. This allows us to measure the degree of metric shifting - how much firms move away from previously emphasized metrics, referred to as moving targets. In portfolio and cross-sectional regression tests against a recent traditional baseline, our method yields a moving-targets signal that delivers significant risk-adjusted alpha. Qualitative analysis suggests that these gains stem from preserving contextual qualifiers and filtering out non-metric terms that traditional approaches often miss.
%U https://aclanthology.org/2026.emnlp-industry.174/
%P 2952-2961
Markdown (Informal)
[From Text to Alpha: Can LLMs Track Evolving Signals in Corporate Disclosures?](https://aclanthology.org/2026.emnlp-industry.174/) (Choi et al., EMNLP 2026)
ACL
- Chanyeol Choi, Yoon Kim, Yu Yu, Young Cha, Zach Golkhou, Igor Halperin, Georgios Papaioannou, Minkyu Kim, Zhangyang Wang, Jihoon Kwon, Minjae Kim, Alejandro Lopez-Lira, and Yongjae Lee. 2026. From Text to Alpha: Can LLMs Track Evolving Signals in Corporate Disclosures?. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 2952–2961, Budapest, Hungary. Association for Computational Linguistics.