@inproceedings{oncevay-etal-2026-multi,
title = "Multi-Stage Proxy Retrieval for Illiquid Bond Pricing",
author = "Oncevay, Arturo and
Sain, Joy Prakash and
Ling, Chen and
Kaur, Simerjot and
Smiley, Charese and
Liu, Xiaomo",
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.23/",
pages = "352--364",
ISBN = "979-8-89176-460-6",
abstract = "Identifying proxy issuers and bonds is a critical but largely manual step in illiquid corporate bond pricing, requiring analysts to navigate sparse public information and inconsistent industry signals. We present a modular pipeline for proxy retrieval that integrates issuer profiling with hierarchical industry classification and multi-stage retrieval over issuers. We evaluate alternative design choices across hierarchical classification and reranking stages to understand how structured representations and industry-aware signals influence performance. Experiments on a large internal dataset show that domain-adapted embeddings and explicit industry hierarchy signals are primary drivers of quality across stages. The evaluated system produces issuer-level proxy shortlists rather than final bond prices. Pilot deployment experience highlights the value of modular, cost-aware designs for robust proxy retrieval in enterprise settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oncevay-etal-2026-multi">
<titleInfo>
<title>Multi-Stage Proxy Retrieval for Illiquid Bond Pricing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Oncevay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joy</namePart>
<namePart type="given">Prakash</namePart>
<namePart type="family">Sain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Ling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simerjot</namePart>
<namePart type="family">Kaur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charese</namePart>
<namePart type="family">Smiley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaomo</namePart>
<namePart type="family">Liu</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>Identifying proxy issuers and bonds is a critical but largely manual step in illiquid corporate bond pricing, requiring analysts to navigate sparse public information and inconsistent industry signals. We present a modular pipeline for proxy retrieval that integrates issuer profiling with hierarchical industry classification and multi-stage retrieval over issuers. We evaluate alternative design choices across hierarchical classification and reranking stages to understand how structured representations and industry-aware signals influence performance. Experiments on a large internal dataset show that domain-adapted embeddings and explicit industry hierarchy signals are primary drivers of quality across stages. The evaluated system produces issuer-level proxy shortlists rather than final bond prices. Pilot deployment experience highlights the value of modular, cost-aware designs for robust proxy retrieval in enterprise settings.</abstract>
<identifier type="citekey">oncevay-etal-2026-multi</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.23/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>352</start>
<end>364</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Stage Proxy Retrieval for Illiquid Bond Pricing
%A Oncevay, Arturo
%A Sain, Joy Prakash
%A Ling, Chen
%A Kaur, Simerjot
%A Smiley, Charese
%A Liu, Xiaomo
%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 oncevay-etal-2026-multi
%X Identifying proxy issuers and bonds is a critical but largely manual step in illiquid corporate bond pricing, requiring analysts to navigate sparse public information and inconsistent industry signals. We present a modular pipeline for proxy retrieval that integrates issuer profiling with hierarchical industry classification and multi-stage retrieval over issuers. We evaluate alternative design choices across hierarchical classification and reranking stages to understand how structured representations and industry-aware signals influence performance. Experiments on a large internal dataset show that domain-adapted embeddings and explicit industry hierarchy signals are primary drivers of quality across stages. The evaluated system produces issuer-level proxy shortlists rather than final bond prices. Pilot deployment experience highlights the value of modular, cost-aware designs for robust proxy retrieval in enterprise settings.
%U https://aclanthology.org/2026.emnlp-industry.23/
%P 352-364
Markdown (Informal)
[Multi-Stage Proxy Retrieval for Illiquid Bond Pricing](https://aclanthology.org/2026.emnlp-industry.23/) (Oncevay et al., EMNLP 2026)
ACL
- Arturo Oncevay, Joy Prakash Sain, Chen Ling, Simerjot Kaur, Charese Smiley, and Xiaomo Liu. 2026. Multi-Stage Proxy Retrieval for Illiquid Bond Pricing. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 352–364, Budapest, Hungary. Association for Computational Linguistics.