@inproceedings{bazzo-etal-2026-inf,
title = "{INF}-rsrs at {S}em{E}val-2026 Task 1: Is the best really better? The limits of creative work in the era of {LLM}s",
author = "Bazzo, Guilherme and
Fa{\'e}, Eduardo and
Junqueira, J{\'u}lia and
Moreira, Higor and
Costella Pessutto, Lucas Rafael",
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-1.396/",
pages = "3156--3164",
ISBN = "979-8-89176-414-9",
abstract = "Generating humor is a complex and challenging task for Large Language Models (LLMs), requiring both linguistic creativity and strict adherence to constraints. This paper presents INF-rsrs, our solution for SemEval 2026 Task{\textasciitilde}1: Humor Generation, which tasks models with creating jokes from headlines and word pairs without labeled data. We propose a two-stage framework: a production stage and a selection stage. The production stage employs diverse model families and hyperparameter configurations to generate a wide range of candidate jokes, with each candidate generated by an LLM prompted in the role of a comedian under structured constraints to ensure relevance and humor. Our system was designed to substantiate our claim that the direct use of LLMs in creative works, such as humor generation, hits a hard ceiling that is inescapable through simple prompting. Our proposed system tied in first place in the task ranking, obtaining a top-tier performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bazzo-etal-2026-inf">
<titleInfo>
<title>INF-rsrs at SemEval-2026 Task 1: Is the best really better? The limits of creative work in the era of LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guilherme</namePart>
<namePart type="family">Bazzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduardo</namePart>
<namePart type="family">Faé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Júlia</namePart>
<namePart type="family">Junqueira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Higor</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="given">Rafael</namePart>
<namePart type="family">Costella Pessutto</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>Generating humor is a complex and challenging task for Large Language Models (LLMs), requiring both linguistic creativity and strict adherence to constraints. This paper presents INF-rsrs, our solution for SemEval 2026 Task~1: Humor Generation, which tasks models with creating jokes from headlines and word pairs without labeled data. We propose a two-stage framework: a production stage and a selection stage. The production stage employs diverse model families and hyperparameter configurations to generate a wide range of candidate jokes, with each candidate generated by an LLM prompted in the role of a comedian under structured constraints to ensure relevance and humor. Our system was designed to substantiate our claim that the direct use of LLMs in creative works, such as humor generation, hits a hard ceiling that is inescapable through simple prompting. Our proposed system tied in first place in the task ranking, obtaining a top-tier performance.</abstract>
<identifier type="citekey">bazzo-etal-2026-inf</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.396/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3156</start>
<end>3164</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T INF-rsrs at SemEval-2026 Task 1: Is the best really better? The limits of creative work in the era of LLMs
%A Bazzo, Guilherme
%A Faé, Eduardo
%A Junqueira, Júlia
%A Moreira, Higor
%A Costella Pessutto, Lucas Rafael
%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 bazzo-etal-2026-inf
%X Generating humor is a complex and challenging task for Large Language Models (LLMs), requiring both linguistic creativity and strict adherence to constraints. This paper presents INF-rsrs, our solution for SemEval 2026 Task~1: Humor Generation, which tasks models with creating jokes from headlines and word pairs without labeled data. We propose a two-stage framework: a production stage and a selection stage. The production stage employs diverse model families and hyperparameter configurations to generate a wide range of candidate jokes, with each candidate generated by an LLM prompted in the role of a comedian under structured constraints to ensure relevance and humor. Our system was designed to substantiate our claim that the direct use of LLMs in creative works, such as humor generation, hits a hard ceiling that is inescapable through simple prompting. Our proposed system tied in first place in the task ranking, obtaining a top-tier performance.
%U https://aclanthology.org/2026.semeval-1.396/
%P 3156-3164
Markdown (Informal)
[INF-rsrs at SemEval-2026 Task 1: Is the best really better? The limits of creative work in the era of LLMs](https://aclanthology.org/2026.semeval-1.396/) (Bazzo et al., SemEval 2026)
ACL