@inproceedings{sharma-etal-2026-blue-smm4h,
title = "blue at {SMM}4{H}-{H}ea{RD} 2026: Class-Weighted Transformer Ensembles with Structured Decoding and Chain-of-Thought Blending across Six Health {NLP} Shared Tasks",
author = "Sharma, Krish and
Singhal, Rhea and
Bedi, Jatin",
editor = "Lopez-Garcia, Guillermo and
Gonzalez-Hernandez, Graciela",
booktitle = "Proceedings of the 11th Social Media Mining for Health Research and Applications ({SMM}4{H}-{H}ea{RD} 2026) Workshop and Shared Tasks",
month = jul,
year = "2026",
address = "San Diego, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.smm4h-1.13/",
pages = "72--81",
ISBN = "979-8-89176-432-3",
abstract = "We describe team blue{'}s participation across six SMM4H-HeaRD 2026 shared tasks spanning multilingual adverse drug event detection (Task 1), influenza vaccine effectiveness estimation (Task 3), patient metadata classification (Task 5), TNM cancer staging (Task 6), opioid impact span detection (Task 7), and multilingual clinical NER with cross-lingual annotation projection (Task 8). Despite the heterogeneity of these tasks, binary, multi-class, multi-label, and sequence-labelling, our systems share three recurring design principles: (i) inverse-frequency class weighting to handle severe imbalance, (ii) multi-seed and/or multi-backbone ensembling to reduce variance, and (iii) post-hoc calibration of decision boundaries. Key results include micro-F1 of 0.990 on TNM staging (Task 6), 0.872/0.918 on flu vaccination/test classification surpassing the 70B CoT baseline on vaccination (Task 3), F1 of 0.764 on patient metadata approaching the fine-tuning benchmark of 0.776 (Task 5), and competitive performance on ADE detection (Task 1, F1 = 0.580), opioid spans (Task 7, relaxed F1 = 0.59), and multilingual clinical NER (Task 8, strict F1 0.20{--}0.41 across 7 languages)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharma-etal-2026-blue-smm4h">
<titleInfo>
<title>blue at SMM4H-HeaRD 2026: Class-Weighted Transformer Ensembles with Structured Decoding and Chain-of-Thought Blending across Six Health NLP Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Krish</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rhea</namePart>
<namePart type="family">Singhal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jatin</namePart>
<namePart type="family">Bedi</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 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guillermo</namePart>
<namePart type="family">Lopez-Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-432-3</identifier>
</relatedItem>
<abstract>We describe team blue’s participation across six SMM4H-HeaRD 2026 shared tasks spanning multilingual adverse drug event detection (Task 1), influenza vaccine effectiveness estimation (Task 3), patient metadata classification (Task 5), TNM cancer staging (Task 6), opioid impact span detection (Task 7), and multilingual clinical NER with cross-lingual annotation projection (Task 8). Despite the heterogeneity of these tasks, binary, multi-class, multi-label, and sequence-labelling, our systems share three recurring design principles: (i) inverse-frequency class weighting to handle severe imbalance, (ii) multi-seed and/or multi-backbone ensembling to reduce variance, and (iii) post-hoc calibration of decision boundaries. Key results include micro-F1 of 0.990 on TNM staging (Task 6), 0.872/0.918 on flu vaccination/test classification surpassing the 70B CoT baseline on vaccination (Task 3), F1 of 0.764 on patient metadata approaching the fine-tuning benchmark of 0.776 (Task 5), and competitive performance on ADE detection (Task 1, F1 = 0.580), opioid spans (Task 7, relaxed F1 = 0.59), and multilingual clinical NER (Task 8, strict F1 0.20–0.41 across 7 languages).</abstract>
<identifier type="citekey">sharma-etal-2026-blue-smm4h</identifier>
<location>
<url>https://aclanthology.org/2026.smm4h-1.13/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>72</start>
<end>81</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T blue at SMM4H-HeaRD 2026: Class-Weighted Transformer Ensembles with Structured Decoding and Chain-of-Thought Blending across Six Health NLP Shared Tasks
%A Sharma, Krish
%A Singhal, Rhea
%A Bedi, Jatin
%Y Lopez-Garcia, Guillermo
%Y Gonzalez-Hernandez, Graciela
%S Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, United States
%@ 979-8-89176-432-3
%F sharma-etal-2026-blue-smm4h
%X We describe team blue’s participation across six SMM4H-HeaRD 2026 shared tasks spanning multilingual adverse drug event detection (Task 1), influenza vaccine effectiveness estimation (Task 3), patient metadata classification (Task 5), TNM cancer staging (Task 6), opioid impact span detection (Task 7), and multilingual clinical NER with cross-lingual annotation projection (Task 8). Despite the heterogeneity of these tasks, binary, multi-class, multi-label, and sequence-labelling, our systems share three recurring design principles: (i) inverse-frequency class weighting to handle severe imbalance, (ii) multi-seed and/or multi-backbone ensembling to reduce variance, and (iii) post-hoc calibration of decision boundaries. Key results include micro-F1 of 0.990 on TNM staging (Task 6), 0.872/0.918 on flu vaccination/test classification surpassing the 70B CoT baseline on vaccination (Task 3), F1 of 0.764 on patient metadata approaching the fine-tuning benchmark of 0.776 (Task 5), and competitive performance on ADE detection (Task 1, F1 = 0.580), opioid spans (Task 7, relaxed F1 = 0.59), and multilingual clinical NER (Task 8, strict F1 0.20–0.41 across 7 languages).
%U https://aclanthology.org/2026.smm4h-1.13/
%P 72-81
Markdown (Informal)
[blue at SMM4H-HeaRD 2026: Class-Weighted Transformer Ensembles with Structured Decoding and Chain-of-Thought Blending across Six Health NLP Shared Tasks](https://aclanthology.org/2026.smm4h-1.13/) (Sharma et al., SMM4H 2026)
ACL