@inproceedings{rajbahadur-etal-2026-llm,
title = "{LLM} Post-Training as Brownfield Maintenance: An Industrial Perspective on Dataware Engineering",
author = "Rajbahadur, Gopi Krishnan and
Ebrahimi, Amir and
Chen, Boyuan and
Hassan, Ahmed E.",
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.212/",
pages = "3555--3569",
ISBN = "979-8-89176-460-6",
abstract = "Industrial post-training is a brownfield regime. Teams inherit a deployed checkpoint and must land targeted improvements under fixed compute and mixture budgets without regressing the rest. The maintained artifact is increasingly **dataware**: behavior governed by a curated post-training mixture, updated via bounded mixture patches rather than clean-slate retraining. From an industrial code-generation improvement effort, we offer a maintainer{'}s perspective on why this work is hard in practice, distilling three recurring challenges, **zero-sum mixture design**, **yield as the binding metric**, and **end-to-end integration under uncertainty**, and arguing that progress depends less on one-off recipes than on an engineering discipline for programming dataware. In our case study, interventions that raised the conversion of teacher distillation into usable training data increased accepted supervision by **2.84$\times$** while using the same solution teacher and four solution attempts per candidate problem. In our primary evaluation, the yield-engineered patch improved CodeForces pass@1 by **+2.59** points (+3.11 pass@3) and held-out LiveCodeBench v6 pass@1 by **+6.11** (+8.05 pass@3), all statistically significant across 16 stochastic evaluations of each benchmark from one fixed checkpoint per condition, with internal AIME and MATH regression suites within tolerance"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rajbahadur-etal-2026-llm">
<titleInfo>
<title>LLM Post-Training as Brownfield Maintenance: An Industrial Perspective on Dataware Engineering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gopi</namePart>
<namePart type="given">Krishnan</namePart>
<namePart type="family">Rajbahadur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boyuan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Hassan</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>Industrial post-training is a brownfield regime. Teams inherit a deployed checkpoint and must land targeted improvements under fixed compute and mixture budgets without regressing the rest. The maintained artifact is increasingly **dataware**: behavior governed by a curated post-training mixture, updated via bounded mixture patches rather than clean-slate retraining. From an industrial code-generation improvement effort, we offer a maintainer’s perspective on why this work is hard in practice, distilling three recurring challenges, **zero-sum mixture design**, **yield as the binding metric**, and **end-to-end integration under uncertainty**, and arguing that progress depends less on one-off recipes than on an engineering discipline for programming dataware. In our case study, interventions that raised the conversion of teacher distillation into usable training data increased accepted supervision by **2.84\times** while using the same solution teacher and four solution attempts per candidate problem. In our primary evaluation, the yield-engineered patch improved CodeForces pass@1 by **+2.59** points (+3.11 pass@3) and held-out LiveCodeBench v6 pass@1 by **+6.11** (+8.05 pass@3), all statistically significant across 16 stochastic evaluations of each benchmark from one fixed checkpoint per condition, with internal AIME and MATH regression suites within tolerance</abstract>
<identifier type="citekey">rajbahadur-etal-2026-llm</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.212/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3555</start>
<end>3569</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLM Post-Training as Brownfield Maintenance: An Industrial Perspective on Dataware Engineering
%A Rajbahadur, Gopi Krishnan
%A Ebrahimi, Amir
%A Chen, Boyuan
%A Hassan, Ahmed E.
%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 rajbahadur-etal-2026-llm
%X Industrial post-training is a brownfield regime. Teams inherit a deployed checkpoint and must land targeted improvements under fixed compute and mixture budgets without regressing the rest. The maintained artifact is increasingly **dataware**: behavior governed by a curated post-training mixture, updated via bounded mixture patches rather than clean-slate retraining. From an industrial code-generation improvement effort, we offer a maintainer’s perspective on why this work is hard in practice, distilling three recurring challenges, **zero-sum mixture design**, **yield as the binding metric**, and **end-to-end integration under uncertainty**, and arguing that progress depends less on one-off recipes than on an engineering discipline for programming dataware. In our case study, interventions that raised the conversion of teacher distillation into usable training data increased accepted supervision by **2.84\times** while using the same solution teacher and four solution attempts per candidate problem. In our primary evaluation, the yield-engineered patch improved CodeForces pass@1 by **+2.59** points (+3.11 pass@3) and held-out LiveCodeBench v6 pass@1 by **+6.11** (+8.05 pass@3), all statistically significant across 16 stochastic evaluations of each benchmark from one fixed checkpoint per condition, with internal AIME and MATH regression suites within tolerance
%U https://aclanthology.org/2026.emnlp-industry.212/
%P 3555-3569
Markdown (Informal)
[LLM Post-Training as Brownfield Maintenance: An Industrial Perspective on Dataware Engineering](https://aclanthology.org/2026.emnlp-industry.212/) (Rajbahadur et al., EMNLP 2026)
ACL