@inproceedings{ojha-etal-2026-developers,
title = "What Do Developers Ask? A Taxonomy of Code Related Questions",
author = "Ojha, Ashutosh and
Saxena, Ashita and
Pateel, Varshini Reddy and
Kodeswaran, Palanivel and
Sen, Sayandeep and
Tamilselvam, Srikanth G.",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.2380/",
doi = "10.18653/2026.findings-emnlp.2380",
pages = "51122--51140",
ISBN = "979-8-89176-462-0",
abstract = "Progress in Code Question Answering (CodeQA) depends on benchmarks that reflect what developers actually ask. Yet most existing CodeQA datasets are built from docstring templates or GitHub issues, and rarely capture the diversity of real, repository-level developer queries. We address this gap by releasing a taxonomy of real-world code-assistance queries, grounded in 3,052 authentic user interactions from the RepoChat dataset. We construct the taxonomy via a semi-automated pipeline that combines clustering, LLM-based labeling, and an iterative refinement loop driven by inter-model disagreement, and we compare the result against three prior taxonomy-generation methods (TaxoGen, TaxoCom, TaxoAdapt). Our taxonomy achieves a favorable tradeoff between granularity and usability{---}86 nodes with 93.2{\%} node relevance, 99.4{\%} path validity, and 81.25{\%} sibling coherence{---}while remaining concise enough for downstream use. We then apply the taxonomy in two ways: (i) auditing existing Code related benchmarks to surface systematically underrepresented query types, and (ii) generating a synthetic CodeQA dataset whose categories are guided by the taxonomy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ojha-etal-2026-developers">
<titleInfo>
<title>What Do Developers Ask? A Taxonomy of Code Related Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashita</namePart>
<namePart type="family">Saxena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varshini</namePart>
<namePart type="given">Reddy</namePart>
<namePart type="family">Pateel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Palanivel</namePart>
<namePart type="family">Kodeswaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sayandeep</namePart>
<namePart type="family">Sen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srikanth</namePart>
<namePart type="given">G</namePart>
<namePart type="family">Tamilselvam</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Progress in Code Question Answering (CodeQA) depends on benchmarks that reflect what developers actually ask. Yet most existing CodeQA datasets are built from docstring templates or GitHub issues, and rarely capture the diversity of real, repository-level developer queries. We address this gap by releasing a taxonomy of real-world code-assistance queries, grounded in 3,052 authentic user interactions from the RepoChat dataset. We construct the taxonomy via a semi-automated pipeline that combines clustering, LLM-based labeling, and an iterative refinement loop driven by inter-model disagreement, and we compare the result against three prior taxonomy-generation methods (TaxoGen, TaxoCom, TaxoAdapt). Our taxonomy achieves a favorable tradeoff between granularity and usability—86 nodes with 93.2% node relevance, 99.4% path validity, and 81.25% sibling coherence—while remaining concise enough for downstream use. We then apply the taxonomy in two ways: (i) auditing existing Code related benchmarks to surface systematically underrepresented query types, and (ii) generating a synthetic CodeQA dataset whose categories are guided by the taxonomy.</abstract>
<identifier type="citekey">ojha-etal-2026-developers</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.2380</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2380/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>51122</start>
<end>51140</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What Do Developers Ask? A Taxonomy of Code Related Questions
%A Ojha, Ashutosh
%A Saxena, Ashita
%A Pateel, Varshini Reddy
%A Kodeswaran, Palanivel
%A Sen, Sayandeep
%A Tamilselvam, Srikanth G.
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F ojha-etal-2026-developers
%X Progress in Code Question Answering (CodeQA) depends on benchmarks that reflect what developers actually ask. Yet most existing CodeQA datasets are built from docstring templates or GitHub issues, and rarely capture the diversity of real, repository-level developer queries. We address this gap by releasing a taxonomy of real-world code-assistance queries, grounded in 3,052 authentic user interactions from the RepoChat dataset. We construct the taxonomy via a semi-automated pipeline that combines clustering, LLM-based labeling, and an iterative refinement loop driven by inter-model disagreement, and we compare the result against three prior taxonomy-generation methods (TaxoGen, TaxoCom, TaxoAdapt). Our taxonomy achieves a favorable tradeoff between granularity and usability—86 nodes with 93.2% node relevance, 99.4% path validity, and 81.25% sibling coherence—while remaining concise enough for downstream use. We then apply the taxonomy in two ways: (i) auditing existing Code related benchmarks to surface systematically underrepresented query types, and (ii) generating a synthetic CodeQA dataset whose categories are guided by the taxonomy.
%R 10.18653/2026.findings-emnlp.2380
%U https://aclanthology.org/2026.findings-emnlp.2380/
%U https://doi.org/10.18653/2026.findings-emnlp.2380
%P 51122-51140
Markdown (Informal)
[What Do Developers Ask? A Taxonomy of Code Related Questions](https://aclanthology.org/2026.findings-emnlp.2380/) (Ojha et al., Findings 2026)
ACL
- Ashutosh Ojha, Ashita Saxena, Varshini Reddy Pateel, Palanivel Kodeswaran, Sayandeep Sen, and Srikanth G. Tamilselvam. 2026. What Do Developers Ask? A Taxonomy of Code Related Questions. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 51122–51140, Budapest, Hungary. Association for Computational Linguistics.