@inproceedings{cimino-etal-2026-meta,
title = "Meta-Prompting Follow-Ups for Unsupervised Dialogue Evaluation Using Open-Source Large Language Models",
author = "Cimino, Gaetano and
Li, Chuyuan and
Carenini, Giuseppe and
Deufemia, Vincenzo",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.220/",
doi = "10.63317/4i8vxn9qi57r",
pages = "2812--2824",
abstract = "Automatically evaluating dialogue quality remains a major challenge due to the complexity and contextual variability of human interactions. This paper introduces DIET, a novel unsupervised, reference-free metric that uses follow-up utterances to assess dialogue quality. Unlike existing reference-free metrics, which rely on follow-ups derived from annotated data and apply a uniform set of utterances across all dialogues, DIET generates follow-ups using open-source Large Language Models (LLMs) and refines them through a selection process. Two strategies are explored: SELFMAP, where generation and evaluation are performed by the same model to ensure internal coherence, and CRAFT, where multiple models collaborate to generate diverse and complementary follow-ups, enhancing robustness and reducing model bias. Dialogue quality is measured via the likelihood of an LLM continuing the dialogue from selected follow-ups. Experiments show DIET better correlates with human judgments than existing reference-free metrics across multiple meta-evaluation datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cimino-etal-2026-meta">
<titleInfo>
<title>Meta-Prompting Follow-Ups for Unsupervised Dialogue Evaluation Using Open-Source Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gaetano</namePart>
<namePart type="family">Cimino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuyuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Carenini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincenzo</namePart>
<namePart type="family">Deufemia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatically evaluating dialogue quality remains a major challenge due to the complexity and contextual variability of human interactions. This paper introduces DIET, a novel unsupervised, reference-free metric that uses follow-up utterances to assess dialogue quality. Unlike existing reference-free metrics, which rely on follow-ups derived from annotated data and apply a uniform set of utterances across all dialogues, DIET generates follow-ups using open-source Large Language Models (LLMs) and refines them through a selection process. Two strategies are explored: SELFMAP, where generation and evaluation are performed by the same model to ensure internal coherence, and CRAFT, where multiple models collaborate to generate diverse and complementary follow-ups, enhancing robustness and reducing model bias. Dialogue quality is measured via the likelihood of an LLM continuing the dialogue from selected follow-ups. Experiments show DIET better correlates with human judgments than existing reference-free metrics across multiple meta-evaluation datasets.</abstract>
<identifier type="citekey">cimino-etal-2026-meta</identifier>
<identifier type="doi">10.63317/4i8vxn9qi57r</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.220/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>2812</start>
<end>2824</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Meta-Prompting Follow-Ups for Unsupervised Dialogue Evaluation Using Open-Source Large Language Models
%A Cimino, Gaetano
%A Li, Chuyuan
%A Carenini, Giuseppe
%A Deufemia, Vincenzo
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F cimino-etal-2026-meta
%X Automatically evaluating dialogue quality remains a major challenge due to the complexity and contextual variability of human interactions. This paper introduces DIET, a novel unsupervised, reference-free metric that uses follow-up utterances to assess dialogue quality. Unlike existing reference-free metrics, which rely on follow-ups derived from annotated data and apply a uniform set of utterances across all dialogues, DIET generates follow-ups using open-source Large Language Models (LLMs) and refines them through a selection process. Two strategies are explored: SELFMAP, where generation and evaluation are performed by the same model to ensure internal coherence, and CRAFT, where multiple models collaborate to generate diverse and complementary follow-ups, enhancing robustness and reducing model bias. Dialogue quality is measured via the likelihood of an LLM continuing the dialogue from selected follow-ups. Experiments show DIET better correlates with human judgments than existing reference-free metrics across multiple meta-evaluation datasets.
%R 10.63317/4i8vxn9qi57r
%U https://aclanthology.org/2026.lrec-1.220/
%U https://doi.org/10.63317/4i8vxn9qi57r
%P 2812-2824
Markdown (Informal)
[Meta-Prompting Follow-Ups for Unsupervised Dialogue Evaluation Using Open-Source Large Language Models](https://aclanthology.org/2026.lrec-1.220/) (Cimino et al., LREC 2026)
ACL