@inproceedings{talsania-etal-2026-faithfulness,
title = "Faithfulness Beyond Plausibility: Auditing Human Explanations in Educational Assessment",
author = "Talsania, Ria and
Shah, Dhruv Ritesh and
Dhage, Sudhir",
editor = "T.Y.S.S., Santosh and
Rodriguez, Juan Diego and
de Gibert, Ona",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-srw.55/",
pages = "621--631",
ISBN = "979-8-89176-393-7",
abstract = "When rubric-based feedback tools explain a grade, students and instructors assume those explanations reflect how the score was actually determined. Yet it remains unclear whether explanation components such as rubric assignments and evidence spans reflect how scores are constructed or primarily serve as post-hoc justifications. This gap has direct implications for automated essay scoring and rubric-based feedback tools, where explanation reliability is often assumed but rarely evaluated.We introduce a knowledge graph framework that represents human tutor grading traces as structured objects, enabling controlled counterfactual testing of explanation components. Using 400 grading traces from 10 expert human tutors evaluating 100 narrative essays, we define a reconstruction-based diagnostic to measure how explanation components contribute to score interpretation, independent of prediction. Our results reveal a consistent asymmetry: removing rubric-level information leads to substantial changes in reconstructed scores, while removing evidence spans has minimal impact. This suggests that rubric structure is central to score interpretation, whereas cited evidence spans may function primarily as post-hoc justifications. We further observe tutor-specific variation in grading behavior. These findings highlight the need for explanation mechanisms that better align with scoring processes, ensuring that feedback provided to learners is both interpretable and functionally relevant."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="talsania-etal-2026-faithfulness">
<titleInfo>
<title>Faithfulness Beyond Plausibility: Auditing Human Explanations in Educational Assessment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ria</namePart>
<namePart type="family">Talsania</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhruv</namePart>
<namePart type="given">Ritesh</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudhir</namePart>
<namePart type="family">Dhage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<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">Juan</namePart>
<namePart type="given">Diego</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ona</namePart>
<namePart type="family">de Gibert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-393-7</identifier>
</relatedItem>
<abstract>When rubric-based feedback tools explain a grade, students and instructors assume those explanations reflect how the score was actually determined. Yet it remains unclear whether explanation components such as rubric assignments and evidence spans reflect how scores are constructed or primarily serve as post-hoc justifications. This gap has direct implications for automated essay scoring and rubric-based feedback tools, where explanation reliability is often assumed but rarely evaluated.We introduce a knowledge graph framework that represents human tutor grading traces as structured objects, enabling controlled counterfactual testing of explanation components. Using 400 grading traces from 10 expert human tutors evaluating 100 narrative essays, we define a reconstruction-based diagnostic to measure how explanation components contribute to score interpretation, independent of prediction. Our results reveal a consistent asymmetry: removing rubric-level information leads to substantial changes in reconstructed scores, while removing evidence spans has minimal impact. This suggests that rubric structure is central to score interpretation, whereas cited evidence spans may function primarily as post-hoc justifications. We further observe tutor-specific variation in grading behavior. These findings highlight the need for explanation mechanisms that better align with scoring processes, ensuring that feedback provided to learners is both interpretable and functionally relevant.</abstract>
<identifier type="citekey">talsania-etal-2026-faithfulness</identifier>
<location>
<url>https://aclanthology.org/2026.acl-srw.55/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>621</start>
<end>631</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Faithfulness Beyond Plausibility: Auditing Human Explanations in Educational Assessment
%A Talsania, Ria
%A Shah, Dhruv Ritesh
%A Dhage, Sudhir
%Y T.Y.S.S., Santosh
%Y Rodriguez, Juan Diego
%Y de Gibert, Ona
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-393-7
%F talsania-etal-2026-faithfulness
%X When rubric-based feedback tools explain a grade, students and instructors assume those explanations reflect how the score was actually determined. Yet it remains unclear whether explanation components such as rubric assignments and evidence spans reflect how scores are constructed or primarily serve as post-hoc justifications. This gap has direct implications for automated essay scoring and rubric-based feedback tools, where explanation reliability is often assumed but rarely evaluated.We introduce a knowledge graph framework that represents human tutor grading traces as structured objects, enabling controlled counterfactual testing of explanation components. Using 400 grading traces from 10 expert human tutors evaluating 100 narrative essays, we define a reconstruction-based diagnostic to measure how explanation components contribute to score interpretation, independent of prediction. Our results reveal a consistent asymmetry: removing rubric-level information leads to substantial changes in reconstructed scores, while removing evidence spans has minimal impact. This suggests that rubric structure is central to score interpretation, whereas cited evidence spans may function primarily as post-hoc justifications. We further observe tutor-specific variation in grading behavior. These findings highlight the need for explanation mechanisms that better align with scoring processes, ensuring that feedback provided to learners is both interpretable and functionally relevant.
%U https://aclanthology.org/2026.acl-srw.55/
%P 621-631
Markdown (Informal)
[Faithfulness Beyond Plausibility: Auditing Human Explanations in Educational Assessment](https://aclanthology.org/2026.acl-srw.55/) (Talsania et al., ACL 2026)
ACL