@inproceedings{ebert-etal-2026-reading,
title = "Reading Between the Lines: The One-Sided Conversation Problem",
author = "Ebert, Victoria and
Singh, Rishabh and
Chen, Tuochao and
Smith, Noah A. and
Gollakota, Shyamnath",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1757/",
doi = "10.18653/v1/2026.findings-acl.1757",
pages = "35227--35260",
ISBN = "979-8-89176-395-1",
abstract = "Conversational AI is constrained in many real-world settings where only one side of a dialogue can be recorded. We formalize the one-sided conversation problem (1SC): inferring and learning from only one side of a conversation. We study two tasks: (1) reconstructing the missing speaker{'}s turns and (2) generating summaries from one-sided transcripts. Evaluating models on MultiWOZ, DailyDialog, SpokenWOZ and Candor with both human A/B testing and LLM-as-a-judge metrics, we find that additional context improves reconstruction, and while large models generate promising reconstructions with prompting, smaller models require finetuning. Further, high-quality summaries can be generated without reconstructing missing turns. We present 1SC as a novel challenge and report promising results that mark a step toward privacy-aware conversational AI."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ebert-etal-2026-reading">
<titleInfo>
<title>Reading Between the Lines: The One-Sided Conversation Problem</title>
</titleInfo>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Ebert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rishabh</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tuochao</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyamnath</namePart>
<namePart type="family">Gollakota</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>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</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, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Conversational AI is constrained in many real-world settings where only one side of a dialogue can be recorded. We formalize the one-sided conversation problem (1SC): inferring and learning from only one side of a conversation. We study two tasks: (1) reconstructing the missing speaker’s turns and (2) generating summaries from one-sided transcripts. Evaluating models on MultiWOZ, DailyDialog, SpokenWOZ and Candor with both human A/B testing and LLM-as-a-judge metrics, we find that additional context improves reconstruction, and while large models generate promising reconstructions with prompting, smaller models require finetuning. Further, high-quality summaries can be generated without reconstructing missing turns. We present 1SC as a novel challenge and report promising results that mark a step toward privacy-aware conversational AI.</abstract>
<identifier type="citekey">ebert-etal-2026-reading</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1757</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1757/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>35227</start>
<end>35260</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reading Between the Lines: The One-Sided Conversation Problem
%A Ebert, Victoria
%A Singh, Rishabh
%A Chen, Tuochao
%A Smith, Noah A.
%A Gollakota, Shyamnath
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F ebert-etal-2026-reading
%X Conversational AI is constrained in many real-world settings where only one side of a dialogue can be recorded. We formalize the one-sided conversation problem (1SC): inferring and learning from only one side of a conversation. We study two tasks: (1) reconstructing the missing speaker’s turns and (2) generating summaries from one-sided transcripts. Evaluating models on MultiWOZ, DailyDialog, SpokenWOZ and Candor with both human A/B testing and LLM-as-a-judge metrics, we find that additional context improves reconstruction, and while large models generate promising reconstructions with prompting, smaller models require finetuning. Further, high-quality summaries can be generated without reconstructing missing turns. We present 1SC as a novel challenge and report promising results that mark a step toward privacy-aware conversational AI.
%R 10.18653/v1/2026.findings-acl.1757
%U https://aclanthology.org/2026.findings-acl.1757/
%U https://doi.org/10.18653/v1/2026.findings-acl.1757
%P 35227-35260
Markdown (Informal)
[Reading Between the Lines: The One-Sided Conversation Problem](https://aclanthology.org/2026.findings-acl.1757/) (Ebert et al., Findings 2026)
ACL
- Victoria Ebert, Rishabh Singh, Tuochao Chen, Noah A. Smith, and Shyamnath Gollakota. 2026. Reading Between the Lines: The One-Sided Conversation Problem. In Findings of the Association for Computational Linguistics: ACL 2026, pages 35227–35260, San Diego, California, United States. Association for Computational Linguistics.