@inproceedings{nguyen-zhang-2024-gavx,
title = "{GAV}x at {S}em{E}val-2024 Task 10: Emotion Flip Reasoning via Stacked Instruction Finetuning of {LLM}s",
author = "Nguyen, Vy and
Zhang, Xiuzhen",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Tayyar Madabushi, Harish and
Da San Martino, Giovanni and
Rosenthal, Sara and
Ros{\'a}, Aiala},
booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.semeval-1.50",
doi = "10.18653/v1/2024.semeval-1.50",
pages = "326--336",
abstract = "The Emotion Flip Reasoning task at SemEval 2024 aims at identifying the utterance(s) that trigger a speaker to shift from an emotion to another in a multi-party conversation. The spontaneous, informal, and occasionally multilingual dynamics of conversations make the task challenging. In this paper, we propose a supervised stacked instruction-based framework to finetune large language models to tackle this task. Utilising the annotated datasets provided, we curate multiple instruction sets involving chain-of-thoughts, feedback, and self-evaluation instructions, for a multi-step finetuning pipeline. We utilise the self-consistency inference strategy to enhance prediction consistency. Experimental results reveal commendable performance, achieving mean F1 scores of 0.77 and 0.76 for triggers in the Hindi-English and English-only tracks respectively. This led to us earning the second highest ranking in both tracks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-zhang-2024-gavx">
<titleInfo>
<title>GAVx at SemEval-2024 Task 10: Emotion Flip Reasoning via Stacked Instruction Finetuning of LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vy</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiuzhen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Emotion Flip Reasoning task at SemEval 2024 aims at identifying the utterance(s) that trigger a speaker to shift from an emotion to another in a multi-party conversation. The spontaneous, informal, and occasionally multilingual dynamics of conversations make the task challenging. In this paper, we propose a supervised stacked instruction-based framework to finetune large language models to tackle this task. Utilising the annotated datasets provided, we curate multiple instruction sets involving chain-of-thoughts, feedback, and self-evaluation instructions, for a multi-step finetuning pipeline. We utilise the self-consistency inference strategy to enhance prediction consistency. Experimental results reveal commendable performance, achieving mean F1 scores of 0.77 and 0.76 for triggers in the Hindi-English and English-only tracks respectively. This led to us earning the second highest ranking in both tracks.</abstract>
<identifier type="citekey">nguyen-zhang-2024-gavx</identifier>
<identifier type="doi">10.18653/v1/2024.semeval-1.50</identifier>
<location>
<url>https://aclanthology.org/2024.semeval-1.50</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>326</start>
<end>336</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GAVx at SemEval-2024 Task 10: Emotion Flip Reasoning via Stacked Instruction Finetuning of LLMs
%A Nguyen, Vy
%A Zhang, Xiuzhen
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Tayyar Madabushi, Harish
%Y Da San Martino, Giovanni
%Y Rosenthal, Sara
%Y Rosá, Aiala
%S Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F nguyen-zhang-2024-gavx
%X The Emotion Flip Reasoning task at SemEval 2024 aims at identifying the utterance(s) that trigger a speaker to shift from an emotion to another in a multi-party conversation. The spontaneous, informal, and occasionally multilingual dynamics of conversations make the task challenging. In this paper, we propose a supervised stacked instruction-based framework to finetune large language models to tackle this task. Utilising the annotated datasets provided, we curate multiple instruction sets involving chain-of-thoughts, feedback, and self-evaluation instructions, for a multi-step finetuning pipeline. We utilise the self-consistency inference strategy to enhance prediction consistency. Experimental results reveal commendable performance, achieving mean F1 scores of 0.77 and 0.76 for triggers in the Hindi-English and English-only tracks respectively. This led to us earning the second highest ranking in both tracks.
%R 10.18653/v1/2024.semeval-1.50
%U https://aclanthology.org/2024.semeval-1.50
%U https://doi.org/10.18653/v1/2024.semeval-1.50
%P 326-336
Markdown (Informal)
[GAVx at SemEval-2024 Task 10: Emotion Flip Reasoning via Stacked Instruction Finetuning of LLMs](https://aclanthology.org/2024.semeval-1.50) (Nguyen & Zhang, SemEval 2024)
ACL