Meta-Prompting Follow-Ups for Unsupervised Dialogue Evaluation Using Open-Source Large Language Models

Gaetano Cimino, Chuyuan Li, Giuseppe Carenini, Vincenzo Deufemia


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.
Anthology ID:
2026.lrec-1.220
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
2812–2824
Language:
External URL:
https://lrec.elra.info/lrec2026-main-220
DOI:
10.63317/4i8vxn9qi57r
Bibkey:
Cite (ACL):
Gaetano Cimino, Chuyuan Li, Giuseppe Carenini, and Vincenzo Deufemia. 2026. Meta-Prompting Follow-Ups for Unsupervised Dialogue Evaluation Using Open-Source Large Language Models. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 2812–2824, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
Meta-Prompting Follow-Ups for Unsupervised Dialogue Evaluation Using Open-Source Large Language Models (Cimino et al., LREC 2026)
Copy Citation: