@inproceedings{huber-etal-2026-cosy,
title = "{C}o{S}y: Conversational Synthesis for Grounded Question Answering",
author = "Huber, Patrick and
Einolghozati, Arash and
Conway, Rylan and
Narang, Kanika and
Smith, Matt and
Nayyar, Waqar and
Sagar, Adithya and
Aly, Ahmed A and
Shrivastava, Akshat",
editor = "Mille, Simon and
Gehrmann, Sebastian and
Schmidtov{\'a}, Patr{\'i}cia and
Du{\v{s}}ek, Ond{\v{r}}ej and
Fadaee, Marzieh and
Lo, Kyle and
Santus, Enrico and
Stanovsky, Gabriel",
booktitle = "Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics ({GEM})",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.gem-main.2/",
pages = "1--10",
ISBN = "979-8-89176-423-1",
abstract = "High-quality, large-scale conversational datasets are scarce, making it difficult to train on-device language models ({\textasciitilde}1B parameters) as effective assistants. We introduce CoSy (Conversational Synthesis), a novel framework for generating diverse, steerable, multi-turn conversations at scale. CoSY combines three key mechanisms: (1) conversational graphs that ensure natural dialogue flow, (2) turn-based prompt augmentations for diversity, and (3) explicit linguistic phenomena for coherence. We evaluate CoSy on conversational grounded reasoning tasks (i.e. answering questions based on contextual information), a core on-device use case.Our on-device sized models trained on CoSy-synthesized data achieve competitive performance with human-annotated baselines and outperform instruction-tuned models of up to 70B parameters in zero-shot settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huber-etal-2026-cosy">
<titleInfo>
<title>CoSy: Conversational Synthesis for Grounded Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Huber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arash</namePart>
<namePart type="family">Einolghozati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rylan</namePart>
<namePart type="family">Conway</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kanika</namePart>
<namePart type="family">Narang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Waqar</namePart>
<namePart type="family">Nayyar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adithya</namePart>
<namePart type="family">Sagar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Aly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akshat</namePart>
<namePart type="family">Shrivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Mille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrícia</namePart>
<namePart type="family">Schmidtová</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Dušek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marzieh</namePart>
<namePart type="family">Fadaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-423-1</identifier>
</relatedItem>
<abstract>High-quality, large-scale conversational datasets are scarce, making it difficult to train on-device language models (~1B parameters) as effective assistants. We introduce CoSy (Conversational Synthesis), a novel framework for generating diverse, steerable, multi-turn conversations at scale. CoSY combines three key mechanisms: (1) conversational graphs that ensure natural dialogue flow, (2) turn-based prompt augmentations for diversity, and (3) explicit linguistic phenomena for coherence. We evaluate CoSy on conversational grounded reasoning tasks (i.e. answering questions based on contextual information), a core on-device use case.Our on-device sized models trained on CoSy-synthesized data achieve competitive performance with human-annotated baselines and outperform instruction-tuned models of up to 70B parameters in zero-shot settings.</abstract>
<identifier type="citekey">huber-etal-2026-cosy</identifier>
<location>
<url>https://aclanthology.org/2026.gem-main.2/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoSy: Conversational Synthesis for Grounded Question Answering
%A Huber, Patrick
%A Einolghozati, Arash
%A Conway, Rylan
%A Narang, Kanika
%A Smith, Matt
%A Nayyar, Waqar
%A Sagar, Adithya
%A Aly, Ahmed A.
%A Shrivastava, Akshat
%Y Mille, Simon
%Y Gehrmann, Sebastian
%Y Schmidtová, Patrícia
%Y Dušek, Ondřej
%Y Fadaee, Marzieh
%Y Lo, Kyle
%Y Santus, Enrico
%Y Stanovsky, Gabriel
%S Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-423-1
%F huber-etal-2026-cosy
%X High-quality, large-scale conversational datasets are scarce, making it difficult to train on-device language models (~1B parameters) as effective assistants. We introduce CoSy (Conversational Synthesis), a novel framework for generating diverse, steerable, multi-turn conversations at scale. CoSY combines three key mechanisms: (1) conversational graphs that ensure natural dialogue flow, (2) turn-based prompt augmentations for diversity, and (3) explicit linguistic phenomena for coherence. We evaluate CoSy on conversational grounded reasoning tasks (i.e. answering questions based on contextual information), a core on-device use case.Our on-device sized models trained on CoSy-synthesized data achieve competitive performance with human-annotated baselines and outperform instruction-tuned models of up to 70B parameters in zero-shot settings.
%U https://aclanthology.org/2026.gem-main.2/
%P 1-10
Markdown (Informal)
[CoSy: Conversational Synthesis for Grounded Question Answering](https://aclanthology.org/2026.gem-main.2/) (Huber et al., GEM 2026)
ACL
- Patrick Huber, Arash Einolghozati, Rylan Conway, Kanika Narang, Matt Smith, Waqar Nayyar, Adithya Sagar, Ahmed A Aly, and Akshat Shrivastava. 2026. CoSy: Conversational Synthesis for Grounded Question Answering. In Proceedings of the Fifth Workshop on Generation, Evaluation and Metrics (GEM), pages 1–10, San Diego, California, USA. Association for Computational Linguistics.