@inproceedings{bexte-etal-2024-scoring,
title = "Scoring with Confidence? {--} Exploring High-confidence Scoring for Saving Manual Grading Effort",
author = {Bexte, Marie and
Horbach, Andrea and
Sch{\"u}tzler, Lena and
Christ, Oliver and
Zesch, Torsten},
editor = {Kochmar, Ekaterina 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 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.bea-1.11/",
pages = "119--124",
abstract = "A possible way to save manual grading effort in short answer scoring is to automatically score answers for which the classifier is highly confident. We explore the feasibility of this approach in a high-stakes exam setting, evaluating three different similarity-based scoring methods, where the similarity score is a direct proxy for model confidence. The decision on an appropriate level of confidence should ideally be made before scoring a new prompt. We thus probe to what extent confidence thresholds are consistent across different datasets and prompts. We find that high-confidence thresholds vary on a prompt-to-prompt basis, and that the overall potential of increased performance at a reasonable cost of additional manual effort is limited."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bexte-etal-2024-scoring">
<titleInfo>
<title>Scoring with Confidence? – Exploring High-confidence Scoring for Saving Manual Grading Effort</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Bexte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lena</namePart>
<namePart type="family">Schützler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Christ</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</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 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024)</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">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">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A possible way to save manual grading effort in short answer scoring is to automatically score answers for which the classifier is highly confident. We explore the feasibility of this approach in a high-stakes exam setting, evaluating three different similarity-based scoring methods, where the similarity score is a direct proxy for model confidence. The decision on an appropriate level of confidence should ideally be made before scoring a new prompt. We thus probe to what extent confidence thresholds are consistent across different datasets and prompts. We find that high-confidence thresholds vary on a prompt-to-prompt basis, and that the overall potential of increased performance at a reasonable cost of additional manual effort is limited.</abstract>
<identifier type="citekey">bexte-etal-2024-scoring</identifier>
<location>
<url>https://aclanthology.org/2024.bea-1.11/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>119</start>
<end>124</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Scoring with Confidence? – Exploring High-confidence Scoring for Saving Manual Grading Effort
%A Bexte, Marie
%A Horbach, Andrea
%A Schützler, Lena
%A Christ, Oliver
%A Zesch, Torsten
%Y Kochmar, Ekaterina
%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 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F bexte-etal-2024-scoring
%X A possible way to save manual grading effort in short answer scoring is to automatically score answers for which the classifier is highly confident. We explore the feasibility of this approach in a high-stakes exam setting, evaluating three different similarity-based scoring methods, where the similarity score is a direct proxy for model confidence. The decision on an appropriate level of confidence should ideally be made before scoring a new prompt. We thus probe to what extent confidence thresholds are consistent across different datasets and prompts. We find that high-confidence thresholds vary on a prompt-to-prompt basis, and that the overall potential of increased performance at a reasonable cost of additional manual effort is limited.
%U https://aclanthology.org/2024.bea-1.11/
%P 119-124
Markdown (Informal)
[Scoring with Confidence? – Exploring High-confidence Scoring for Saving Manual Grading Effort](https://aclanthology.org/2024.bea-1.11/) (Bexte et al., BEA 2024)
ACL