@inproceedings{rode-etal-2026-rethinking,
title = "Rethinking Clustering as a Conversational Supervision Problem",
author = "Rode, Theo and
Co, Aimee and
Zeng, Qingyang and
Gandhi, Sanaya and
Purwar, Ananya and
Chang, Jonathan P. and
Hashemi, Masoud and
Mahajan, Khyati and
Deryckere, Filip and
Casati, Fabio",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1924/",
pages = "43823--43840",
ISBN = "979-8-89176-459-0",
abstract = "Clustering is often a process of trial and error: we apply different algorithms (such as k-means or hdbscan), apply different embeddings, try a dimensionality reduction, explore different values of K, inspect the result with the product manager, and repeat. When the data is large, even communicating and analyzing a single clustering becomes difficult.\par We argue that the nature of clustering requires a fundamentally different approach. We posit that clustering is fundamentally a subjective and iterative process, and its central challenges are how to elicit the dimensions and nuances a user cares about, how to communicate a clustering effectively, and how to converge to an output of interest through efficient conversation. We reframe clustering as a conversational supervision problem. We formalize conversational clustering as a new task, derive evaluation metrics suited to it, and release an evaluation framework and reference implementation to seed further work."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rode-etal-2026-rethinking">
<titleInfo>
<title>Rethinking Clustering as a Conversational Supervision Problem</title>
</titleInfo>
<name type="personal">
<namePart type="given">Theo</namePart>
<namePart type="family">Rode</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aimee</namePart>
<namePart type="family">Co</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingyang</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanaya</namePart>
<namePart type="family">Gandhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ananya</namePart>
<namePart type="family">Purwar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masoud</namePart>
<namePart type="family">Hashemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyati</namePart>
<namePart type="family">Mahajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Deryckere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Casati</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</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Clustering is often a process of trial and error: we apply different algorithms (such as k-means or hdbscan), apply different embeddings, try a dimensionality reduction, explore different values of K, inspect the result with the product manager, and repeat. When the data is large, even communicating and analyzing a single clustering becomes difficult.\par We argue that the nature of clustering requires a fundamentally different approach. We posit that clustering is fundamentally a subjective and iterative process, and its central challenges are how to elicit the dimensions and nuances a user cares about, how to communicate a clustering effectively, and how to converge to an output of interest through efficient conversation. We reframe clustering as a conversational supervision problem. We formalize conversational clustering as a new task, derive evaluation metrics suited to it, and release an evaluation framework and reference implementation to seed further work.</abstract>
<identifier type="citekey">rode-etal-2026-rethinking</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1924/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>43823</start>
<end>43840</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rethinking Clustering as a Conversational Supervision Problem
%A Rode, Theo
%A Co, Aimee
%A Zeng, Qingyang
%A Gandhi, Sanaya
%A Purwar, Ananya
%A Chang, Jonathan P.
%A Hashemi, Masoud
%A Mahajan, Khyati
%A Deryckere, Filip
%A Casati, Fabio
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F rode-etal-2026-rethinking
%X Clustering is often a process of trial and error: we apply different algorithms (such as k-means or hdbscan), apply different embeddings, try a dimensionality reduction, explore different values of K, inspect the result with the product manager, and repeat. When the data is large, even communicating and analyzing a single clustering becomes difficult.\par We argue that the nature of clustering requires a fundamentally different approach. We posit that clustering is fundamentally a subjective and iterative process, and its central challenges are how to elicit the dimensions and nuances a user cares about, how to communicate a clustering effectively, and how to converge to an output of interest through efficient conversation. We reframe clustering as a conversational supervision problem. We formalize conversational clustering as a new task, derive evaluation metrics suited to it, and release an evaluation framework and reference implementation to seed further work.
%U https://aclanthology.org/2026.emnlp-main.1924/
%P 43823-43840
Markdown (Informal)
[Rethinking Clustering as a Conversational Supervision Problem](https://aclanthology.org/2026.emnlp-main.1924/) (Rode et al., EMNLP 2026)
ACL
- Theo Rode, Aimee Co, Qingyang Zeng, Sanaya Gandhi, Ananya Purwar, Jonathan P. Chang, Masoud Hashemi, Khyati Mahajan, Filip Deryckere, and Fabio Casati. 2026. Rethinking Clustering as a Conversational Supervision Problem. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 43823–43840, Budapest, Hungary. Association for Computational Linguistics.