@inproceedings{an-etal-2025-blcu,
title = "{BLCU}-{ICALL} at {BEA} 2025 Shared Task: Multi-Strategy Evaluation of {AI} Tutors",
author = "An, Jiyuan and
Fu, Xiang and
Liu, Bo and
Zong, Xuquan and
Kong, Cunliang and
Liu, Shuliang and
Wang, Shuo and
Liu, Zhenghao and
Yang, Liner and
Fan, Hanghang and
Yang, Erhong",
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-1.84/",
doi = "10.18653/v1/2025.bea-1.84",
pages = "1084--1097",
ISBN = "979-8-89176-270-1",
abstract = "This paper describes our approaches for the BEA-2025 Shared Task on assessing pedagogical ability and attributing tutor identities in AI-powered tutoring systems. We explored three methodological paradigms: in-context learning (ICL), supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF). Results indicate clear methodological strengths: SFT is highly effective for structured classification tasks such as mistake identification and feedback actionability, while ICL with advanced prompting excels at open-ended tasks involving mistake localization and instructional guidance. Additionally, fine-tuned models demonstrated strong performance in identifying tutor authorship. Our findings highlight the importance of aligning methodological strategy and task structure, providing insights toward more effective evaluations of educational AI systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="an-etal-2025-blcu">
<titleInfo>
<title>BLCU-ICALL at BEA 2025 Shared Task: Multi-Strategy Evaluation of AI Tutors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiyuan</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuquan</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cunliang</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuliang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenghao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liner</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanghang</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erhong</namePart>
<namePart type="family">Yang</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>This paper describes our approaches for the BEA-2025 Shared Task on assessing pedagogical ability and attributing tutor identities in AI-powered tutoring systems. We explored three methodological paradigms: in-context learning (ICL), supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF). Results indicate clear methodological strengths: SFT is highly effective for structured classification tasks such as mistake identification and feedback actionability, while ICL with advanced prompting excels at open-ended tasks involving mistake localization and instructional guidance. Additionally, fine-tuned models demonstrated strong performance in identifying tutor authorship. Our findings highlight the importance of aligning methodological strategy and task structure, providing insights toward more effective evaluations of educational AI systems.</abstract>
<identifier type="citekey">an-etal-2025-blcu</identifier>
<identifier type="doi">10.18653/v1/2025.bea-1.84</identifier>
<location>
<url>https://aclanthology.org/2025.bea-1.84/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1084</start>
<end>1097</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BLCU-ICALL at BEA 2025 Shared Task: Multi-Strategy Evaluation of AI Tutors
%A An, Jiyuan
%A Fu, Xiang
%A Liu, Bo
%A Zong, Xuquan
%A Kong, Cunliang
%A Liu, Shuliang
%A Wang, Shuo
%A Liu, Zhenghao
%A Yang, Liner
%A Fan, Hanghang
%A Yang, Erhong
%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 an-etal-2025-blcu
%X This paper describes our approaches for the BEA-2025 Shared Task on assessing pedagogical ability and attributing tutor identities in AI-powered tutoring systems. We explored three methodological paradigms: in-context learning (ICL), supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF). Results indicate clear methodological strengths: SFT is highly effective for structured classification tasks such as mistake identification and feedback actionability, while ICL with advanced prompting excels at open-ended tasks involving mistake localization and instructional guidance. Additionally, fine-tuned models demonstrated strong performance in identifying tutor authorship. Our findings highlight the importance of aligning methodological strategy and task structure, providing insights toward more effective evaluations of educational AI systems.
%R 10.18653/v1/2025.bea-1.84
%U https://aclanthology.org/2025.bea-1.84/
%U https://doi.org/10.18653/v1/2025.bea-1.84
%P 1084-1097
Markdown (Informal)
[BLCU-ICALL at BEA 2025 Shared Task: Multi-Strategy Evaluation of AI Tutors](https://aclanthology.org/2025.bea-1.84/) (An et al., BEA 2025)
ACL
- Jiyuan An, Xiang Fu, Bo Liu, Xuquan Zong, Cunliang Kong, Shuliang Liu, Shuo Wang, Zhenghao Liu, Liner Yang, Hanghang Fan, and Erhong Yang. 2025. BLCU-ICALL at BEA 2025 Shared Task: Multi-Strategy Evaluation of AI Tutors. In Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025), pages 1084–1097, Vienna, Austria. Association for Computational Linguistics.