@inproceedings{tran-etal-2025-improving,
title = "Improving In-context Learning Example Retrieval for Classroom Discussion Assessment with Re-ranking and Label Ratio Regulation",
author = "Tran, Nhat and
Litman, Diane and
Pierce, Benjamin and
Correnti, Richard and
Matsumura, Lindsay Clare",
editor = {Kochmar, Ekaterina and
Alhafni, Bashar and
Bexte, Marie and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Tack, Ana{\"i}s and
Yaneva, Victoria and
Yuan, Zheng},
booktitle = "Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.bea-1.54/",
doi = "10.18653/v1/2025.bea-1.54",
pages = "752--764",
ISBN = "979-8-89176-270-1",
abstract = "Recent advancements in natural language processing, particularly large language models (LLMs), are making the automated evaluation of classroom discussions more achievable. In this work, we propose a method to improve the performance of LLMs on classroom discussion quality assessment by utilizing in-context learning (ICL) example retrieval. Specifically, we leverage example re-ranking and label ratio regulation, which forces a specific ratio of different types of examples on the ICL examples.While a standard ICL example retrieval approach shows inferior performance compared to using a predetermined set of examples, our approach improves performance in all tested dimensions. We also conducted experiments to examine the ineffectiveness of the generic ICL example retrieval approach and found that the lack of positive and hard negative examples can be a potential cause. Our analyses emphasize the importance of maintaining a balanced distribution of classes (positive, non-hard negative, and hard negative examples) in creating a good set of ICL examples, especially when we can utilize educational knowledge to identify instances of hard negative examples."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tran-etal-2025-improving">
<titleInfo>
<title>Improving In-context Learning Example Retrieval for Classroom Discussion Assessment with Re-ranking and Label Ratio Regulation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nhat</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diane</namePart>
<namePart type="family">Litman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Pierce</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Correnti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lindsay</namePart>
<namePart type="given">Clare</namePart>
<namePart type="family">Matsumura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)</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">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Bexte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-270-1</identifier>
</relatedItem>
<abstract>Recent advancements in natural language processing, particularly large language models (LLMs), are making the automated evaluation of classroom discussions more achievable. In this work, we propose a method to improve the performance of LLMs on classroom discussion quality assessment by utilizing in-context learning (ICL) example retrieval. Specifically, we leverage example re-ranking and label ratio regulation, which forces a specific ratio of different types of examples on the ICL examples.While a standard ICL example retrieval approach shows inferior performance compared to using a predetermined set of examples, our approach improves performance in all tested dimensions. We also conducted experiments to examine the ineffectiveness of the generic ICL example retrieval approach and found that the lack of positive and hard negative examples can be a potential cause. Our analyses emphasize the importance of maintaining a balanced distribution of classes (positive, non-hard negative, and hard negative examples) in creating a good set of ICL examples, especially when we can utilize educational knowledge to identify instances of hard negative examples.</abstract>
<identifier type="citekey">tran-etal-2025-improving</identifier>
<identifier type="doi">10.18653/v1/2025.bea-1.54</identifier>
<location>
<url>https://aclanthology.org/2025.bea-1.54/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>752</start>
<end>764</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving In-context Learning Example Retrieval for Classroom Discussion Assessment with Re-ranking and Label Ratio Regulation
%A Tran, Nhat
%A Litman, Diane
%A Pierce, Benjamin
%A Correnti, Richard
%A Matsumura, Lindsay Clare
%Y Kochmar, Ekaterina
%Y Alhafni, Bashar
%Y Bexte, Marie
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%S Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-270-1
%F tran-etal-2025-improving
%X Recent advancements in natural language processing, particularly large language models (LLMs), are making the automated evaluation of classroom discussions more achievable. In this work, we propose a method to improve the performance of LLMs on classroom discussion quality assessment by utilizing in-context learning (ICL) example retrieval. Specifically, we leverage example re-ranking and label ratio regulation, which forces a specific ratio of different types of examples on the ICL examples.While a standard ICL example retrieval approach shows inferior performance compared to using a predetermined set of examples, our approach improves performance in all tested dimensions. We also conducted experiments to examine the ineffectiveness of the generic ICL example retrieval approach and found that the lack of positive and hard negative examples can be a potential cause. Our analyses emphasize the importance of maintaining a balanced distribution of classes (positive, non-hard negative, and hard negative examples) in creating a good set of ICL examples, especially when we can utilize educational knowledge to identify instances of hard negative examples.
%R 10.18653/v1/2025.bea-1.54
%U https://aclanthology.org/2025.bea-1.54/
%U https://doi.org/10.18653/v1/2025.bea-1.54
%P 752-764
Markdown (Informal)
[Improving In-context Learning Example Retrieval for Classroom Discussion Assessment with Re-ranking and Label Ratio Regulation](https://aclanthology.org/2025.bea-1.54/) (Tran et al., BEA 2025)
ACL