<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="burleigh-etal-2025-beyond">
    <titleInfo>
        <title>Beyond the Hint: Using Self-Critique to Constrain LLM Feedback in Conversation-Based Assessment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tyler</namePart>
        <namePart type="family">Burleigh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jenny</namePart>
        <namePart type="family">Han</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kristen</namePart>
        <namePart type="family">Dicerbo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Joshua</namePart>
            <namePart type="family">Wilson</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Christopher</namePart>
            <namePart type="family">Ormerod</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Magdalen</namePart>
            <namePart type="family">Beiting Parrish</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>National Council on Measurement in Education (NCME)</publisher>
            <place>
                <placeTerm type="text">Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-218-84230-7</identifier>
    </relatedItem>
    <abstract>Large Language Models in Conversation-Based Assessment tend to provide inappropriate hints that compromise validity. We demonstrate that self-critique – a simple prompt engineering technique – effectively constrains this behavior.Through two studies using synthetic conversations and real-world high school math pilot data, self-critique reduced inappropriate hints by 90.7% and 24-75% respectively. Human experts validated ground truth labels while LLM judges enabled scale. This immediately deployable solution addresses the critical tension in intermediate-stakes assessment: maintaining student engagement while ensuring fair comparisons. Our findings show prompt engineering can meaningfully safeguard assessment integrity without model fine-tuning.</abstract>
    <identifier type="citekey">burleigh-etal-2025-beyond</identifier>
    <location>
        <url>https://aclanthology.org/2025.aimecon-sessions.9/</url>
    </location>
    <part>
        <date>2025-10</date>
        <extent unit="page">
            <start>79</start>
            <end>85</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Beyond the Hint: Using Self-Critique to Constrain LLM Feedback in Conversation-Based Assessment
%A Burleigh, Tyler
%A Han, Jenny
%A Dicerbo, Kristen
%Y Wilson, Joshua
%Y Ormerod, Christopher
%Y Beiting Parrish, Magdalen
%S Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers
%D 2025
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-218-84230-7
%F burleigh-etal-2025-beyond
%X Large Language Models in Conversation-Based Assessment tend to provide inappropriate hints that compromise validity. We demonstrate that self-critique – a simple prompt engineering technique – effectively constrains this behavior.Through two studies using synthetic conversations and real-world high school math pilot data, self-critique reduced inappropriate hints by 90.7% and 24-75% respectively. Human experts validated ground truth labels while LLM judges enabled scale. This immediately deployable solution addresses the critical tension in intermediate-stakes assessment: maintaining student engagement while ensuring fair comparisons. Our findings show prompt engineering can meaningfully safeguard assessment integrity without model fine-tuning.
%U https://aclanthology.org/2025.aimecon-sessions.9/
%P 79-85

Markdown (Informal)

[Beyond the Hint: Using Self-Critique to Constrain LLM Feedback in Conversation-Based Assessment](https://aclanthology.org/2025.aimecon-sessions.9/) (Burleigh et al., AIME-Con 2025)

• Beyond the Hint: Using Self-Critique to Constrain LLM Feedback in Conversation-Based Assessment (Burleigh et al., AIME-Con 2025)

ACL

• Tyler Burleigh, Jenny Han, and Kristen Dicerbo. 2025. Beyond the Hint: Using Self-Critique to Constrain LLM Feedback in Conversation-Based Assessment. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers, pages 79–85, Wyndham Grand Pittsburgh, Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).