@inproceedings{bubus-2026-team,
title = "Team Bubus at {SHROOM}-Visions: Probe{--}Judge Fusion for Hallucination Span Detection",
author = "Bubus, Berk",
editor = {Aziz, Wilker and
Berant, Jonathan and
Eikema, Bryan and
Ilia, Evgenia and
de Marneffe, Marie-Catherine and
Plank, Barbara and
Shelmanov, Artem and
Swayamdipta, Swabha and
Tiedemann, J{\"o}rg and
Vazhentsev, Artem and
V{\'a}zquez, Ra{\'u}l and
Zerva, Chrysoula},
booktitle = "The Proceedings of the Third Workshop on Uncertainty-Aware {NLP}",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.uncertainlp-main.50/",
pages = "760--770",
ISBN = "979-8-89176-486-6",
abstract = "We describe the Bubus submission to the SHROOM-Visions shared task on character-level hallucination span detection in image-conditioned LVLM outputs (English track). Our system fuses two complementary signals: (i) a cross-model supervised probe ensemble {---} per-layer logistic regressions over the hidden states of Qwen3-VL-32B and InternVL3-38B, each teacher-forcing the response under evaluation {---} and (ii) a K=8 role-diverse multi-sample LLM judge whose per-character marking fraction matches the annotator-fraction shape of the gold signal. A fixed two-weight late fusion with an abstain gate reaches Spearman correlation 0.411 and character IoU 0.381 on a leakage-controlled held-out split, measured once, post-competition (majority baseline 0.249). On the official test set the system scores Cor 0.413 / IoU 0.379 / Cor{\_}lbl 0.282 {---} ranks 14/12/16 of 28 teams, the last on the primary ranking metric {---} agreeing with the held-out measurement within 0.002 on Cor and IoU, consistent with a leakage-free protocol. Beyond the positive recipe, we contribute (a) an unusually broad set of controlled negative results {---} zero-shot white-box signals all fail in the shared-task setting, which we attribute to the mismatch between self-generated and teacher-forced foreign text; (b) evidence that error-map-driven prompt engineering recovers precisely the targeted deficits at no precision cost; and (c) two external-data attempts that a pre-specified bootstrap gate correctly rejected."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bubus-2026-team">
<titleInfo>
<title>Team Bubus at SHROOM-Visions: Probe–Judge Fusion for Hallucination Span Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Berk</namePart>
<namePart type="family">Bubus</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>The Proceedings of the Third Workshop on Uncertainty-Aware NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wilker</namePart>
<namePart type="family">Aziz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Berant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="family">Eikema</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evgenia</namePart>
<namePart type="family">Ilia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Vazhentsev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">Vázquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chrysoula</namePart>
<namePart type="family">Zerva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-486-6</identifier>
</relatedItem>
<abstract>We describe the Bubus submission to the SHROOM-Visions shared task on character-level hallucination span detection in image-conditioned LVLM outputs (English track). Our system fuses two complementary signals: (i) a cross-model supervised probe ensemble — per-layer logistic regressions over the hidden states of Qwen3-VL-32B and InternVL3-38B, each teacher-forcing the response under evaluation — and (ii) a K=8 role-diverse multi-sample LLM judge whose per-character marking fraction matches the annotator-fraction shape of the gold signal. A fixed two-weight late fusion with an abstain gate reaches Spearman correlation 0.411 and character IoU 0.381 on a leakage-controlled held-out split, measured once, post-competition (majority baseline 0.249). On the official test set the system scores Cor 0.413 / IoU 0.379 / Cor_lbl 0.282 — ranks 14/12/16 of 28 teams, the last on the primary ranking metric — agreeing with the held-out measurement within 0.002 on Cor and IoU, consistent with a leakage-free protocol. Beyond the positive recipe, we contribute (a) an unusually broad set of controlled negative results — zero-shot white-box signals all fail in the shared-task setting, which we attribute to the mismatch between self-generated and teacher-forced foreign text; (b) evidence that error-map-driven prompt engineering recovers precisely the targeted deficits at no precision cost; and (c) two external-data attempts that a pre-specified bootstrap gate correctly rejected.</abstract>
<identifier type="citekey">bubus-2026-team</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.50/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>760</start>
<end>770</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team Bubus at SHROOM-Visions: Probe–Judge Fusion for Hallucination Span Detection
%A Bubus, Berk
%Y Aziz, Wilker
%Y Berant, Jonathan
%Y Eikema, Bryan
%Y Ilia, Evgenia
%Y de Marneffe, Marie-Catherine
%Y Plank, Barbara
%Y Shelmanov, Artem
%Y Swayamdipta, Swabha
%Y Tiedemann, Jörg
%Y Vazhentsev, Artem
%Y Vázquez, Raúl
%Y Zerva, Chrysoula
%S The Proceedings of the Third Workshop on Uncertainty-Aware NLP
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-486-6
%F bubus-2026-team
%X We describe the Bubus submission to the SHROOM-Visions shared task on character-level hallucination span detection in image-conditioned LVLM outputs (English track). Our system fuses two complementary signals: (i) a cross-model supervised probe ensemble — per-layer logistic regressions over the hidden states of Qwen3-VL-32B and InternVL3-38B, each teacher-forcing the response under evaluation — and (ii) a K=8 role-diverse multi-sample LLM judge whose per-character marking fraction matches the annotator-fraction shape of the gold signal. A fixed two-weight late fusion with an abstain gate reaches Spearman correlation 0.411 and character IoU 0.381 on a leakage-controlled held-out split, measured once, post-competition (majority baseline 0.249). On the official test set the system scores Cor 0.413 / IoU 0.379 / Cor_lbl 0.282 — ranks 14/12/16 of 28 teams, the last on the primary ranking metric — agreeing with the held-out measurement within 0.002 on Cor and IoU, consistent with a leakage-free protocol. Beyond the positive recipe, we contribute (a) an unusually broad set of controlled negative results — zero-shot white-box signals all fail in the shared-task setting, which we attribute to the mismatch between self-generated and teacher-forced foreign text; (b) evidence that error-map-driven prompt engineering recovers precisely the targeted deficits at no precision cost; and (c) two external-data attempts that a pre-specified bootstrap gate correctly rejected.
%U https://aclanthology.org/2026.uncertainlp-main.50/
%P 760-770
Markdown (Informal)
[Team Bubus at SHROOM-Visions: Probe–Judge Fusion for Hallucination Span Detection](https://aclanthology.org/2026.uncertainlp-main.50/) (Bubus, UncertaiNLP 2026)
ACL