@inproceedings{rao-etal-2026-innov8rs,
title = "Innov8rs at {CRF} Filling 2026: An Iterative Multi-{LLM} Ensemble Pipeline with Dynamic Few-Shot Retrieval and Data-Driven Precision Filtering",
author = "Rao, Samminga Sainath and
Mishra, Sumit and
Suman, Chanchal",
editor = "Gupta, Deepak and
Thompson, Paul and
Ananiadou, Sophia and
Demner-Fushman, Dina",
booktitle = "Proceedings of the Third Workshop on Patient-Oriented Language Processing ({CL}4{H}ealth) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.cl4health-1.35/",
doi = "10.63317/2eg7dfwaf4o5",
pages = "390--394",
abstract = "In this paper, we present the technical report on the CL4Health 2026 Shared Task on Case Report Form (CRF) filling for our team Innov8rs. The paper explains the complete development of our system for the CL4Health 2026 Shared Task. We describe every phase of our system {--} from initial catastrophic failures with small models producing over 4,800 false positives, through prompt engineering breakthroughs, to our final multi-LLM ensemble combining Gemini 2.5 Flash and Llama 3.3 70B with dynamic TF-IDF-based few-shot retrieval. The main contribution of this work is a data-driven precision filter that suppresses predictions for CRF items with historically high false-positive rates. This single intervention reduced false positives from 816 to 171 on the English development set, boosting macro-F1 from 0.541 to 0.703. We document the engineering challenges of multi-API-key rotation across 11 Google API keys and 2 Groq keys, the design of four distinct ensemble strategies, and the critical analysis of why development-calibrated filters suffered from distribution shift on test data (final test F1: 0.47)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rao-etal-2026-innov8rs">
<titleInfo>
<title>Innov8rs at CRF Filling 2026: An Iterative Multi-LLM Ensemble Pipeline with Dynamic Few-Shot Retrieval and Data-Driven Precision Filtering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samminga</namePart>
<namePart type="given">Sainath</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sumit</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chanchal</namePart>
<namePart type="family">Suman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present the technical report on the CL4Health 2026 Shared Task on Case Report Form (CRF) filling for our team Innov8rs. The paper explains the complete development of our system for the CL4Health 2026 Shared Task. We describe every phase of our system – from initial catastrophic failures with small models producing over 4,800 false positives, through prompt engineering breakthroughs, to our final multi-LLM ensemble combining Gemini 2.5 Flash and Llama 3.3 70B with dynamic TF-IDF-based few-shot retrieval. The main contribution of this work is a data-driven precision filter that suppresses predictions for CRF items with historically high false-positive rates. This single intervention reduced false positives from 816 to 171 on the English development set, boosting macro-F1 from 0.541 to 0.703. We document the engineering challenges of multi-API-key rotation across 11 Google API keys and 2 Groq keys, the design of four distinct ensemble strategies, and the critical analysis of why development-calibrated filters suffered from distribution shift on test data (final test F1: 0.47).</abstract>
<identifier type="citekey">rao-etal-2026-innov8rs</identifier>
<identifier type="doi">10.63317/2eg7dfwaf4o5</identifier>
<location>
<url>https://aclanthology.org/2026.cl4health-1.35/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>390</start>
<end>394</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Innov8rs at CRF Filling 2026: An Iterative Multi-LLM Ensemble Pipeline with Dynamic Few-Shot Retrieval and Data-Driven Precision Filtering
%A Rao, Samminga Sainath
%A Mishra, Sumit
%A Suman, Chanchal
%Y Gupta, Deepak
%Y Thompson, Paul
%Y Ananiadou, Sophia
%Y Demner-Fushman, Dina
%S Proceedings of the Third Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F rao-etal-2026-innov8rs
%X In this paper, we present the technical report on the CL4Health 2026 Shared Task on Case Report Form (CRF) filling for our team Innov8rs. The paper explains the complete development of our system for the CL4Health 2026 Shared Task. We describe every phase of our system – from initial catastrophic failures with small models producing over 4,800 false positives, through prompt engineering breakthroughs, to our final multi-LLM ensemble combining Gemini 2.5 Flash and Llama 3.3 70B with dynamic TF-IDF-based few-shot retrieval. The main contribution of this work is a data-driven precision filter that suppresses predictions for CRF items with historically high false-positive rates. This single intervention reduced false positives from 816 to 171 on the English development set, boosting macro-F1 from 0.541 to 0.703. We document the engineering challenges of multi-API-key rotation across 11 Google API keys and 2 Groq keys, the design of four distinct ensemble strategies, and the critical analysis of why development-calibrated filters suffered from distribution shift on test data (final test F1: 0.47).
%R 10.63317/2eg7dfwaf4o5
%U https://aclanthology.org/2026.cl4health-1.35/
%U https://doi.org/10.63317/2eg7dfwaf4o5
%P 390-394
Markdown (Informal)
[Innov8rs at CRF Filling 2026: An Iterative Multi-LLM Ensemble Pipeline with Dynamic Few-Shot Retrieval and Data-Driven Precision Filtering](https://aclanthology.org/2026.cl4health-1.35/) (Rao et al., CL4Health 2026)
ACL