@inproceedings{aluguvelly-2026-latentdemandbench,
title = "{L}atent{D}emand{B}ench: A Contamination-Resistant Diagnostic for Pre-Recognition Product{--}Need Ranking in Synthetic Economies",
author = "Aluguvelly, Avinash Goutham",
editor = "Huang, Jimin and
Lee, Yongjae and
Ananiadou, Sophia and
Chen, Hsin-Hsi and
Takamura, Hiroya and
Chen, Chung-Chi",
booktitle = "Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.finnlp-1.29/",
pages = "351--372",
ISBN = "979-8-89176-466-8",
abstract = "An existing product may meet an unmet need before the market recognises the connection. Testing whether a language model can identify such opportunities is difficult when historical outcomes may already be in its training data. We introduce LatentDemandBench, a contamination-resistant benchmark that generates fictional economies with known realisation probabilities and noisy documentary evidence. Solvers rank product{--}need pairings by their chance of realisation within a fixed horizon. Market commentary is generated separately from realisation, allowing us to evaluate ranking both among discussed pairings and where market attention supplies no ordering. On 30 matched economies, two frontier models beat a mention-count control but trail a supervised logistic ranker using fourteen features recovered from the same dossiers by a template-aware parser. The stronger model, GPT-5.6-TERRA, scores 0.669 in top-K-imputed AUC, with a paired reference-minus-model gap of +0.047 [+0.025, +0.074]. Aggregating three completions under the same final top-K budget yields 0.659, leaving a reference gap of +0.058 [+0.031, +0.095]. The deficit is not uniform: an exploratory analysis finds it smaller on unmentioned pairings than on those already discussed. We release the generator, harness and artifacts to support evaluation on fresh economies"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aluguvelly-2026-latentdemandbench">
<titleInfo>
<title>LatentDemandBench: A Contamination-Resistant Diagnostic for Pre-Recognition Product–Need Ranking in Synthetic Economies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Avinash</namePart>
<namePart type="given">Goutham</namePart>
<namePart type="family">Aluguvelly</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 11th Workshop on Financial Technology and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjae</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</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">979-8-89176-466-8</identifier>
</relatedItem>
<abstract>An existing product may meet an unmet need before the market recognises the connection. Testing whether a language model can identify such opportunities is difficult when historical outcomes may already be in its training data. We introduce LatentDemandBench, a contamination-resistant benchmark that generates fictional economies with known realisation probabilities and noisy documentary evidence. Solvers rank product–need pairings by their chance of realisation within a fixed horizon. Market commentary is generated separately from realisation, allowing us to evaluate ranking both among discussed pairings and where market attention supplies no ordering. On 30 matched economies, two frontier models beat a mention-count control but trail a supervised logistic ranker using fourteen features recovered from the same dossiers by a template-aware parser. The stronger model, GPT-5.6-TERRA, scores 0.669 in top-K-imputed AUC, with a paired reference-minus-model gap of +0.047 [+0.025, +0.074]. Aggregating three completions under the same final top-K budget yields 0.659, leaving a reference gap of +0.058 [+0.031, +0.095]. The deficit is not uniform: an exploratory analysis finds it smaller on unmentioned pairings than on those already discussed. We release the generator, harness and artifacts to support evaluation on fresh economies</abstract>
<identifier type="citekey">aluguvelly-2026-latentdemandbench</identifier>
<location>
<url>https://aclanthology.org/2026.finnlp-1.29/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>351</start>
<end>372</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LatentDemandBench: A Contamination-Resistant Diagnostic for Pre-Recognition Product–Need Ranking in Synthetic Economies
%A Aluguvelly, Avinash Goutham
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F aluguvelly-2026-latentdemandbench
%X An existing product may meet an unmet need before the market recognises the connection. Testing whether a language model can identify such opportunities is difficult when historical outcomes may already be in its training data. We introduce LatentDemandBench, a contamination-resistant benchmark that generates fictional economies with known realisation probabilities and noisy documentary evidence. Solvers rank product–need pairings by their chance of realisation within a fixed horizon. Market commentary is generated separately from realisation, allowing us to evaluate ranking both among discussed pairings and where market attention supplies no ordering. On 30 matched economies, two frontier models beat a mention-count control but trail a supervised logistic ranker using fourteen features recovered from the same dossiers by a template-aware parser. The stronger model, GPT-5.6-TERRA, scores 0.669 in top-K-imputed AUC, with a paired reference-minus-model gap of +0.047 [+0.025, +0.074]. Aggregating three completions under the same final top-K budget yields 0.659, leaving a reference gap of +0.058 [+0.031, +0.095]. The deficit is not uniform: an exploratory analysis finds it smaller on unmentioned pairings than on those already discussed. We release the generator, harness and artifacts to support evaluation on fresh economies
%U https://aclanthology.org/2026.finnlp-1.29/
%P 351-372
Markdown (Informal)
[LatentDemandBench: A Contamination-Resistant Diagnostic for Pre-Recognition Product–Need Ranking in Synthetic Economies](https://aclanthology.org/2026.finnlp-1.29/) (Aluguvelly, FinNLP 2026)
ACL