@inproceedings{chai-etal-2026-techmatch,
title = "{T}ech{M}atch: Matching Enterprise Technology Demands to Academic Resources with Graph-Augmented Retrieval",
author = "Chai, Rui and
Huang, Shiyun and
Su, Yubing and
Zhen, Yuhan and
Sun, Yi and
Zhao, Maozhe and
Liu, Shengzhong and
Shen, Rui and
Wang, Ruijie and
Li, Jianxin",
editor = "Agrawal, Sweta and
Abad, Alberto",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-demos.59/",
pages = "614--624",
ISBN = "979-8-89176-461-3",
abstract = "Matching enterprise technology demands with academic resources is critical for technology transfer, yet difficult because enterprise requests are often vague, constraint-sensitive, and expressed differently from scholarly outputs. Existing search and retrieval-augmented generation (RAG) systems may retrieve topically relevant results but often provide unsupported recommendations or insufficient evidence. We present TechMatch, an interactive system for evidence-constrained matching of enterprise demands to papers, scholars, patents, and projects. Its key novelty is a trustworthy workflow that combines demand clarification, structured constraint extraction, graph-augmented retrieval, evidence-aware reranking, and traceable report generation. Each recommendation is grounded in retrieved source evidence, reducing hallucinated rationales and exposing unresolved constraints and feasibility risks. To support efficient interaction, TechMatch uses hierarchical scholar representations, lightweight profile indexing, parallel reranking, and context-budgeted evidence selection. We construct a large-scale academic corpus covering four million research resources. On a public-source benchmark, TechMatch outperforms standard RAG by 9.9{\%} on P@5, 10.1{\%} on NDCG@5, and 9.3{\%} on evidence support, while enabling users to inspect evidence and generate actionable technology-transfer reports."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chai-etal-2026-techmatch">
<titleInfo>
<title>TechMatch: Matching Enterprise Technology Demands to Academic Resources with Graph-Augmented Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiyun</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubing</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuhan</namePart>
<namePart type="family">Zhen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maozhe</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shengzhong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruijie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianxin</namePart>
<namePart type="family">Li</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: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sweta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Abad</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">979-8-89176-461-3</identifier>
</relatedItem>
<abstract>Matching enterprise technology demands with academic resources is critical for technology transfer, yet difficult because enterprise requests are often vague, constraint-sensitive, and expressed differently from scholarly outputs. Existing search and retrieval-augmented generation (RAG) systems may retrieve topically relevant results but often provide unsupported recommendations or insufficient evidence. We present TechMatch, an interactive system for evidence-constrained matching of enterprise demands to papers, scholars, patents, and projects. Its key novelty is a trustworthy workflow that combines demand clarification, structured constraint extraction, graph-augmented retrieval, evidence-aware reranking, and traceable report generation. Each recommendation is grounded in retrieved source evidence, reducing hallucinated rationales and exposing unresolved constraints and feasibility risks. To support efficient interaction, TechMatch uses hierarchical scholar representations, lightweight profile indexing, parallel reranking, and context-budgeted evidence selection. We construct a large-scale academic corpus covering four million research resources. On a public-source benchmark, TechMatch outperforms standard RAG by 9.9% on P@5, 10.1% on NDCG@5, and 9.3% on evidence support, while enabling users to inspect evidence and generate actionable technology-transfer reports.</abstract>
<identifier type="citekey">chai-etal-2026-techmatch</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-demos.59/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>614</start>
<end>624</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TechMatch: Matching Enterprise Technology Demands to Academic Resources with Graph-Augmented Retrieval
%A Chai, Rui
%A Huang, Shiyun
%A Su, Yubing
%A Zhen, Yuhan
%A Sun, Yi
%A Zhao, Maozhe
%A Liu, Shengzhong
%A Shen, Rui
%A Wang, Ruijie
%A Li, Jianxin
%Y Agrawal, Sweta
%Y Abad, Alberto
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-461-3
%F chai-etal-2026-techmatch
%X Matching enterprise technology demands with academic resources is critical for technology transfer, yet difficult because enterprise requests are often vague, constraint-sensitive, and expressed differently from scholarly outputs. Existing search and retrieval-augmented generation (RAG) systems may retrieve topically relevant results but often provide unsupported recommendations or insufficient evidence. We present TechMatch, an interactive system for evidence-constrained matching of enterprise demands to papers, scholars, patents, and projects. Its key novelty is a trustworthy workflow that combines demand clarification, structured constraint extraction, graph-augmented retrieval, evidence-aware reranking, and traceable report generation. Each recommendation is grounded in retrieved source evidence, reducing hallucinated rationales and exposing unresolved constraints and feasibility risks. To support efficient interaction, TechMatch uses hierarchical scholar representations, lightweight profile indexing, parallel reranking, and context-budgeted evidence selection. We construct a large-scale academic corpus covering four million research resources. On a public-source benchmark, TechMatch outperforms standard RAG by 9.9% on P@5, 10.1% on NDCG@5, and 9.3% on evidence support, while enabling users to inspect evidence and generate actionable technology-transfer reports.
%U https://aclanthology.org/2026.emnlp-demos.59/
%P 614-624
Markdown (Informal)
[TechMatch: Matching Enterprise Technology Demands to Academic Resources with Graph-Augmented Retrieval](https://aclanthology.org/2026.emnlp-demos.59/) (Chai et al., EMNLP 2026)
ACL
- Rui Chai, Shiyun Huang, Yubing Su, Yuhan Zhen, Yi Sun, Maozhe Zhao, Shengzhong Liu, Rui Shen, Ruijie Wang, and Jianxin Li. 2026. TechMatch: Matching Enterprise Technology Demands to Academic Resources with Graph-Augmented Retrieval. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 614–624, Budapest, Hungary. Association for Computational Linguistics.