@inproceedings{xiong-etal-2025-sarc7,
title = "Sarc7: Evaluating Sarcasm Detection and Generation with Seven Types and Emotion-Informed Techniques",
author = "Xiong, Lang and
Gao, Raina and
Jeong, Alyssa",
editor = "Zhang, Chen and
Allaway, Emily and
Shen, Hua and
Miculicich, Lesly and
Li, Yinqiao and
M'hamdi, Meryem and
Limkonchotiwat, Peerat and
Bai, Richard He and
T.y.s.s., Santosh and
Han, Sophia Simeng and
Thapa, Surendrabikram and
Rim, Wiem Ben",
booktitle = "Proceedings of the 9th Widening NLP Workshop",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.winlp-main.25/",
pages = "157--166",
ISBN = "979-8-89176-351-7",
abstract = "Sarcasm is a complex linguistic and pragmatic phenomenon where expressions convey meanings that contrast with their literal interpretations, requiring sensitivity to the speaker{'}s intent and context. Misinterpreting sarcasm in collaborative human{--}AI settings can lead to under- or overreliance on LLM outputs, with consequences ranging from breakdowns in communication to critical safety failures. We introduce Sarc7, a benchmark for fine-grained sarcasm evaluation based on the MUStARD dataset, annotated with seven pragmatically defined sarcasm types: self-deprecating, brooding, deadpan, polite, obnoxious, raging, and manic. These categories are adapted from prior linguistic work and used to create a structured dataset suitable for LLM evaluation. For classification, we evaluate multiple prompting strategies{---}zero-shot, few-shot, chain-of-thought (CoT), and a novel emotion-based technique{---}across five major LLMs. Emotion-based prompting yields the highest macro-averaged F1 score of 0.3664 (Gemini 2.5), outperforming CoT for several models and demonstrating its effectiveness in sarcasm type recognition. For sarcasm generation, we design structured prompts using fixed values across four sarcasm-relevant dimensions: incongruity, shock value, context dependency, and emotion. Using Claude 3.5 Sonnet, this approach produces more subtype-aligned outputs, with human evaluators preferring emotion-based generations 38.46{\%} more often than zero-shot baselines. Sarc7 offers a foundation for evaluating nuanced sarcasm understanding and controllable generation in LLMs, pushing beyond binary classification toward interpretable, emotion-informed language modeling."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiong-etal-2025-sarc7">
<titleInfo>
<title>Sarc7: Evaluating Sarcasm Detection and Generation with Seven Types and Emotion-Informed Techniques</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lang</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raina</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alyssa</namePart>
<namePart type="family">Jeong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th Widening NLP Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Allaway</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lesly</namePart>
<namePart type="family">Miculicich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinqiao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meryem</namePart>
<namePart type="family">M’hamdi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peerat</namePart>
<namePart type="family">Limkonchotiwat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="given">He</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.y.s.s.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="given">Simeng</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Surendrabikram</namePart>
<namePart type="family">Thapa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wiem</namePart>
<namePart type="given">Ben</namePart>
<namePart type="family">Rim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-351-7</identifier>
</relatedItem>
<abstract>Sarcasm is a complex linguistic and pragmatic phenomenon where expressions convey meanings that contrast with their literal interpretations, requiring sensitivity to the speaker’s intent and context. Misinterpreting sarcasm in collaborative human–AI settings can lead to under- or overreliance on LLM outputs, with consequences ranging from breakdowns in communication to critical safety failures. We introduce Sarc7, a benchmark for fine-grained sarcasm evaluation based on the MUStARD dataset, annotated with seven pragmatically defined sarcasm types: self-deprecating, brooding, deadpan, polite, obnoxious, raging, and manic. These categories are adapted from prior linguistic work and used to create a structured dataset suitable for LLM evaluation. For classification, we evaluate multiple prompting strategies—zero-shot, few-shot, chain-of-thought (CoT), and a novel emotion-based technique—across five major LLMs. Emotion-based prompting yields the highest macro-averaged F1 score of 0.3664 (Gemini 2.5), outperforming CoT for several models and demonstrating its effectiveness in sarcasm type recognition. For sarcasm generation, we design structured prompts using fixed values across four sarcasm-relevant dimensions: incongruity, shock value, context dependency, and emotion. Using Claude 3.5 Sonnet, this approach produces more subtype-aligned outputs, with human evaluators preferring emotion-based generations 38.46% more often than zero-shot baselines. Sarc7 offers a foundation for evaluating nuanced sarcasm understanding and controllable generation in LLMs, pushing beyond binary classification toward interpretable, emotion-informed language modeling.</abstract>
<identifier type="citekey">xiong-etal-2025-sarc7</identifier>
<location>
<url>https://aclanthology.org/2025.winlp-main.25/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>157</start>
<end>166</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sarc7: Evaluating Sarcasm Detection and Generation with Seven Types and Emotion-Informed Techniques
%A Xiong, Lang
%A Gao, Raina
%A Jeong, Alyssa
%Y Zhang, Chen
%Y Allaway, Emily
%Y Shen, Hua
%Y Miculicich, Lesly
%Y Li, Yinqiao
%Y M’hamdi, Meryem
%Y Limkonchotiwat, Peerat
%Y Bai, Richard He
%Y T.y.s.s., Santosh
%Y Han, Sophia Simeng
%Y Thapa, Surendrabikram
%Y Rim, Wiem Ben
%S Proceedings of the 9th Widening NLP Workshop
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-351-7
%F xiong-etal-2025-sarc7
%X Sarcasm is a complex linguistic and pragmatic phenomenon where expressions convey meanings that contrast with their literal interpretations, requiring sensitivity to the speaker’s intent and context. Misinterpreting sarcasm in collaborative human–AI settings can lead to under- or overreliance on LLM outputs, with consequences ranging from breakdowns in communication to critical safety failures. We introduce Sarc7, a benchmark for fine-grained sarcasm evaluation based on the MUStARD dataset, annotated with seven pragmatically defined sarcasm types: self-deprecating, brooding, deadpan, polite, obnoxious, raging, and manic. These categories are adapted from prior linguistic work and used to create a structured dataset suitable for LLM evaluation. For classification, we evaluate multiple prompting strategies—zero-shot, few-shot, chain-of-thought (CoT), and a novel emotion-based technique—across five major LLMs. Emotion-based prompting yields the highest macro-averaged F1 score of 0.3664 (Gemini 2.5), outperforming CoT for several models and demonstrating its effectiveness in sarcasm type recognition. For sarcasm generation, we design structured prompts using fixed values across four sarcasm-relevant dimensions: incongruity, shock value, context dependency, and emotion. Using Claude 3.5 Sonnet, this approach produces more subtype-aligned outputs, with human evaluators preferring emotion-based generations 38.46% more often than zero-shot baselines. Sarc7 offers a foundation for evaluating nuanced sarcasm understanding and controllable generation in LLMs, pushing beyond binary classification toward interpretable, emotion-informed language modeling.
%U https://aclanthology.org/2025.winlp-main.25/
%P 157-166
Markdown (Informal)
[Sarc7: Evaluating Sarcasm Detection and Generation with Seven Types and Emotion-Informed Techniques](https://aclanthology.org/2025.winlp-main.25/) (Xiong et al., WiNLP 2025)
ACL