@inproceedings{bulut-etal-2026-scoring,
title = "The Scoring Paradox: Multi-Agent Architectures for Unbiased Feedback Optimization",
author = "Bulut, Okan and
Tan, Bin and
Mazzullo, Elisabetta and
Walsh, Cole",
editor = "Wilson, Joshua and
Ormerod, Christopher and
Beiting-Parrish, Magdalen",
booktitle = "Proceedings of the Artificial Intelligence in Measurement and Education Conference ({AIME}-Con): Coordinated Session Papers",
month = oct,
year = "2026",
address = "Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States",
publisher = "National Council on Measurement in Education (NCME)",
url = "https://aclanthology.org/2026.aimecon-sessions.30/",
pages = "274--283",
ISBN = "979-8-9983004-2-4",
abstract = "Does grade awareness bias automatically generated feedback? We present a multi-agent artificial intelligence (AI) framework that contrasts score-blind and score-informed evaluators and reconciles their critiques. Across 908 feedback blocks, score exposure systematically biased the model{'}s critique: harsher at low grades, warmer at high (halo/horn effects). Isolating a score-blind judgment improved score-alignment without sacrificing faithfulness."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bulut-etal-2026-scoring">
<titleInfo>
<title>The Scoring Paradox: Multi-Agent Architectures for Unbiased Feedback Optimization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Okan</namePart>
<namePart type="family">Bulut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisabetta</namePart>
<namePart type="family">Mazzullo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cole</namePart>
<namePart type="family">Walsh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</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">979-8-9983004-2-4</identifier>
</relatedItem>
<abstract>Does grade awareness bias automatically generated feedback? We present a multi-agent artificial intelligence (AI) framework that contrasts score-blind and score-informed evaluators and reconciles their critiques. Across 908 feedback blocks, score exposure systematically biased the model’s critique: harsher at low grades, warmer at high (halo/horn effects). Isolating a score-blind judgment improved score-alignment without sacrificing faithfulness.</abstract>
<identifier type="citekey">bulut-etal-2026-scoring</identifier>
<location>
<url>https://aclanthology.org/2026.aimecon-sessions.30/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>274</start>
<end>283</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Scoring Paradox: Multi-Agent Architectures for Unbiased Feedback Optimization
%A Bulut, Okan
%A Tan, Bin
%A Mazzullo, Elisabetta
%A Walsh, Cole
%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 2026
%8 October
%I National Council on Measurement in Education (NCME)
%C Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States
%@ 979-8-9983004-2-4
%F bulut-etal-2026-scoring
%X Does grade awareness bias automatically generated feedback? We present a multi-agent artificial intelligence (AI) framework that contrasts score-blind and score-informed evaluators and reconciles their critiques. Across 908 feedback blocks, score exposure systematically biased the model’s critique: harsher at low grades, warmer at high (halo/horn effects). Isolating a score-blind judgment improved score-alignment without sacrificing faithfulness.
%U https://aclanthology.org/2026.aimecon-sessions.30/
%P 274-283
Markdown (Informal)
[The Scoring Paradox: Multi-Agent Architectures for Unbiased Feedback Optimization](https://aclanthology.org/2026.aimecon-sessions.30/) (Bulut et al., AIME-Con 2026)
ACL
- Okan Bulut, Bin Tan, Elisabetta Mazzullo, and Cole Walsh. 2026. The Scoring Paradox: Multi-Agent Architectures for Unbiased Feedback Optimization. In Proceedings of the Artificial Intelligence in Measurement and Education Conference (AIME-Con): Coordinated Session Papers, pages 274–283, Wyndham Grand Pittsburgh Downtown, Pittsburgh, Pennsylvania, United States. National Council on Measurement in Education (NCME).