@inproceedings{abdulmujeeb-aryal-2026-howard,
title = "{H}oward {U}niversity-{AI}4{PC} at {S}em{E}val-2026 Task 1: Exploring Prompt Strategies for Automatic Humor Generation",
author = "Abdulmujeeb, Lawal and
Aryal, Saurav",
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-1.319/",
pages = "2527--2532",
ISBN = "979-8-89176-414-9",
abstract = "We present our solution system for SemEval-2026 Task 1-Subtask A, a humor generation task requiring systems to generate jokes, given either a news headline or word-pair inputs. Our approach used the Llama-3.1-8B-Instruct model and we selected this model after comparing several candidate models and humor strategies across our experiments. For the headline inputs, we used a two-shot prompt to frame the output as a tweet and specifying the tone proved to be a particularly important factor in output quality. As for the word-pair inputs, we instructed the model to commit to an everyday situation and generate a funny thought based on that. Also, while experimenting, we noticed that models would start a joke one way with the first word and abruptly shift context mid-joke just to include the second word, and committing to a single situation helped handle that. We also made use of personas here, specifically using Dave Chappelle. Our final system shared 2nd place with 3 other systems out of 32 total systems and achieved an Elo score of 1020. Achieving these results, with no fine-tuning, suggests that careful prompt design alone can yield competitive results."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abdulmujeeb-aryal-2026-howard">
<titleInfo>
<title>Howard University-AI4PC at SemEval-2026 Task 1: Exploring Prompt Strategies for Automatic Humor Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lawal</namePart>
<namePart type="family">Abdulmujeeb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saurav</namePart>
<namePart type="family">Aryal</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>We present our solution system for SemEval-2026 Task 1-Subtask A, a humor generation task requiring systems to generate jokes, given either a news headline or word-pair inputs. Our approach used the Llama-3.1-8B-Instruct model and we selected this model after comparing several candidate models and humor strategies across our experiments. For the headline inputs, we used a two-shot prompt to frame the output as a tweet and specifying the tone proved to be a particularly important factor in output quality. As for the word-pair inputs, we instructed the model to commit to an everyday situation and generate a funny thought based on that. Also, while experimenting, we noticed that models would start a joke one way with the first word and abruptly shift context mid-joke just to include the second word, and committing to a single situation helped handle that. We also made use of personas here, specifically using Dave Chappelle. Our final system shared 2nd place with 3 other systems out of 32 total systems and achieved an Elo score of 1020. Achieving these results, with no fine-tuning, suggests that careful prompt design alone can yield competitive results.</abstract>
<identifier type="citekey">abdulmujeeb-aryal-2026-howard</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.319/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2527</start>
<end>2532</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Howard University-AI4PC at SemEval-2026 Task 1: Exploring Prompt Strategies for Automatic Humor Generation
%A Abdulmujeeb, Lawal
%A Aryal, Saurav
%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 abdulmujeeb-aryal-2026-howard
%X We present our solution system for SemEval-2026 Task 1-Subtask A, a humor generation task requiring systems to generate jokes, given either a news headline or word-pair inputs. Our approach used the Llama-3.1-8B-Instruct model and we selected this model after comparing several candidate models and humor strategies across our experiments. For the headline inputs, we used a two-shot prompt to frame the output as a tweet and specifying the tone proved to be a particularly important factor in output quality. As for the word-pair inputs, we instructed the model to commit to an everyday situation and generate a funny thought based on that. Also, while experimenting, we noticed that models would start a joke one way with the first word and abruptly shift context mid-joke just to include the second word, and committing to a single situation helped handle that. We also made use of personas here, specifically using Dave Chappelle. Our final system shared 2nd place with 3 other systems out of 32 total systems and achieved an Elo score of 1020. Achieving these results, with no fine-tuning, suggests that careful prompt design alone can yield competitive results.
%U https://aclanthology.org/2026.semeval-1.319/
%P 2527-2532
Markdown (Informal)
[Howard University-AI4PC at SemEval-2026 Task 1: Exploring Prompt Strategies for Automatic Humor Generation](https://aclanthology.org/2026.semeval-1.319/) (Abdulmujeeb & Aryal, SemEval 2026)
ACL