@inproceedings{dehouck-etal-2026-lattice,
title = "Lattice at {S}em{E}val-2026 Task 1: Why did the prompt engineer break up with their {LLM}? Because zero-shot was zero-fun.",
author = "Dehouck, Mathieu and
Seminck, Olga and
Delaborde, Marine and
Dupont, Yoann and
Durandard, No{\'e}",
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-1.117/",
pages = "849--861",
ISBN = "979-8-89176-414-9",
abstract = "This paper describes the contribution of theLattice Team to the humor generation MWA-HAHA Sem-Eval shared task on the Englishdata set for subtask A. During the developmentphase, we experimented with two different ap-proaches, but after a quick comparison of theoutputs, it turned out that one was clearly moresuccessful than the other. The winning strategycan be seen as consisting of two phases: first,we used a few-shot framework to let Deepseek-R1 32B generate multiple jokes based on theinput (headlines and word pairs). Second, weset up a voting protocol for Llama-3.1 8B torank the generated jokes and find the funniestone. The other strategy also consisted in twophases: first, we generate many more jokesin a zero-shot way with lighter, faster models,and then we turn back to ranking the generatedjokes, but since we have about ten time morejokes in this second setting, we follow a knock-out tournament procedure in order to find thebest jokes. Our Deepseek-R1 based model isone of the nine systems that shared a first placeon the English data set that received a total of32 valid submissions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dehouck-etal-2026-lattice">
<titleInfo>
<title>Lattice at SemEval-2026 Task 1: Why did the prompt engineer break up with their LLM? Because zero-shot was zero-fun.</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mathieu</namePart>
<namePart type="family">Dehouck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Seminck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Delaborde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoann</namePart>
<namePart type="family">Dupont</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noé</namePart>
<namePart type="family">Durandard</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>This paper describes the contribution of theLattice Team to the humor generation MWA-HAHA Sem-Eval shared task on the Englishdata set for subtask A. During the developmentphase, we experimented with two different ap-proaches, but after a quick comparison of theoutputs, it turned out that one was clearly moresuccessful than the other. The winning strategycan be seen as consisting of two phases: first,we used a few-shot framework to let Deepseek-R1 32B generate multiple jokes based on theinput (headlines and word pairs). Second, weset up a voting protocol for Llama-3.1 8B torank the generated jokes and find the funniestone. The other strategy also consisted in twophases: first, we generate many more jokesin a zero-shot way with lighter, faster models,and then we turn back to ranking the generatedjokes, but since we have about ten time morejokes in this second setting, we follow a knock-out tournament procedure in order to find thebest jokes. Our Deepseek-R1 based model isone of the nine systems that shared a first placeon the English data set that received a total of32 valid submissions.</abstract>
<identifier type="citekey">dehouck-etal-2026-lattice</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.117/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>849</start>
<end>861</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lattice at SemEval-2026 Task 1: Why did the prompt engineer break up with their LLM? Because zero-shot was zero-fun.
%A Dehouck, Mathieu
%A Seminck, Olga
%A Delaborde, Marine
%A Dupont, Yoann
%A Durandard, Noé
%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 dehouck-etal-2026-lattice
%X This paper describes the contribution of theLattice Team to the humor generation MWA-HAHA Sem-Eval shared task on the Englishdata set for subtask A. During the developmentphase, we experimented with two different ap-proaches, but after a quick comparison of theoutputs, it turned out that one was clearly moresuccessful than the other. The winning strategycan be seen as consisting of two phases: first,we used a few-shot framework to let Deepseek-R1 32B generate multiple jokes based on theinput (headlines and word pairs). Second, weset up a voting protocol for Llama-3.1 8B torank the generated jokes and find the funniestone. The other strategy also consisted in twophases: first, we generate many more jokesin a zero-shot way with lighter, faster models,and then we turn back to ranking the generatedjokes, but since we have about ten time morejokes in this second setting, we follow a knock-out tournament procedure in order to find thebest jokes. Our Deepseek-R1 based model isone of the nine systems that shared a first placeon the English data set that received a total of32 valid submissions.
%U https://aclanthology.org/2026.semeval-1.117/
%P 849-861
Markdown (Informal)
[Lattice at SemEval-2026 Task 1: Why did the prompt engineer break up with their LLM? Because zero-shot was zero-fun.](https://aclanthology.org/2026.semeval-1.117/) (Dehouck et al., SemEval 2026)
ACL