@inproceedings{eskandari-etal-2026-minds,
title = "{MINDS} at {S}em{E}val-2026-Task 1: Enhancing Humor Generation through {RAG} and Synthetic {DPO} Alignment",
author = "Eskandari, Sina and
Mousavi, Seyed Amirreza and
Rahimi, Amirreza and
Pouresmaeil, Mona and
Vitaggio, Marcello and
Savelli, Claudio and
Coppola, Riccardo and
Giobergia, Flavio",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.372/",
pages = "2967--2971",
ISBN = "979-8-89176-414-9",
abstract = "Humor generation presents significant challenges due to subjectivity and the limitations of automatic metrics. In this work, we address Task 1 of SemEval 2026 (Subtask A) by evaluating three instruction-tuned models (Llama 3.1, Gemma 2, and Qwen 2.5) via a round-robin LLM judging framework. We investigate the impact of Retrieval-Augmented Generation and Direct Preference Optimization (DPO) on performance. Our results identify Llama 3.1 as the strongest baseline and demonstrate that DPO consistently improves humor quality across configurations. These findings confirm the efficacy of LLM-based judging as a practical training signal for optimizing subjective generation tasks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eskandari-etal-2026-minds">
<titleInfo>
<title>MINDS at SemEval-2026-Task 1: Enhancing Humor Generation through RAG and Synthetic DPO Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Eskandari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyed</namePart>
<namePart type="given">Amirreza</namePart>
<namePart type="family">Mousavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amirreza</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Pouresmaeil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Vitaggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudio</namePart>
<namePart type="family">Savelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riccardo</namePart>
<namePart type="family">Coppola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flavio</namePart>
<namePart type="family">Giobergia</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 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</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">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>Humor generation presents significant challenges due to subjectivity and the limitations of automatic metrics. In this work, we address Task 1 of SemEval 2026 (Subtask A) by evaluating three instruction-tuned models (Llama 3.1, Gemma 2, and Qwen 2.5) via a round-robin LLM judging framework. We investigate the impact of Retrieval-Augmented Generation and Direct Preference Optimization (DPO) on performance. Our results identify Llama 3.1 as the strongest baseline and demonstrate that DPO consistently improves humor quality across configurations. These findings confirm the efficacy of LLM-based judging as a practical training signal for optimizing subjective generation tasks.</abstract>
<identifier type="citekey">eskandari-etal-2026-minds</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.372/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2967</start>
<end>2971</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MINDS at SemEval-2026-Task 1: Enhancing Humor Generation through RAG and Synthetic DPO Alignment
%A Eskandari, Sina
%A Mousavi, Seyed Amirreza
%A Rahimi, Amirreza
%A Pouresmaeil, Mona
%A Vitaggio, Marcello
%A Savelli, Claudio
%A Coppola, Riccardo
%A Giobergia, Flavio
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F eskandari-etal-2026-minds
%X Humor generation presents significant challenges due to subjectivity and the limitations of automatic metrics. In this work, we address Task 1 of SemEval 2026 (Subtask A) by evaluating three instruction-tuned models (Llama 3.1, Gemma 2, and Qwen 2.5) via a round-robin LLM judging framework. We investigate the impact of Retrieval-Augmented Generation and Direct Preference Optimization (DPO) on performance. Our results identify Llama 3.1 as the strongest baseline and demonstrate that DPO consistently improves humor quality across configurations. These findings confirm the efficacy of LLM-based judging as a practical training signal for optimizing subjective generation tasks.
%U https://aclanthology.org/2026.semeval-1.372/
%P 2967-2971
Markdown (Informal)
[MINDS at SemEval-2026-Task 1: Enhancing Humor Generation through RAG and Synthetic DPO Alignment](https://aclanthology.org/2026.semeval-1.372/) (Eskandari et al., SemEval 2026)
ACL
- Sina Eskandari, Seyed Amirreza Mousavi, Amirreza Rahimi, Mona Pouresmaeil, Marcello Vitaggio, Claudio Savelli, Riccardo Coppola, and Flavio Giobergia. 2026. MINDS at SemEval-2026-Task 1: Enhancing Humor Generation through RAG and Synthetic DPO Alignment. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 2967–2971, San Diego, California, USA. Association for Computational Linguistics.