@inproceedings{chowdhury-etal-2026-scope,
title = "{SC}o{PE}: Planning for Hybrid Querying over Clinical Trial Data",
author = "Chowdhury, Suparno and
Choudhury, Manan and
Anvekar, Tejas and
Khan, Muhammed and
Khakwani, Kaneez and
Sonbol, Mohamad and
Riaz, Irbaz and
Gupta, Vivek",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "{B}io{NLP} 2026",
month = jul,
year = "2026",
address = "San Diego, California",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.bionlp-1.76/",
pages = "944--954",
ISBN = "979-8-89176-434-7",
abstract = "Systematic reviews of clinical trials require analysts to extract attributes that are rarely stored as ready-made columns. For example, the drug class of an immunotherapy named in a regimen, the additional agents combined with it, or whether a listed endpoint is a primary or secondary outcome. These attributes must be inferred from the visible content of other fields through normalization, classification, or structured extraction, and existing approaches such as direct LLM prompting, text-to-SQL, and agentic pipelines leave this reasoning implicit in a single generation step or pay a heavy execution cost for limited accuracy gains. We propose SCOPE (Structured Clinical hybrid Planning for Evidence retrieval in clinical trials), a multi-LLM planner-based framework that decomposes the task into row selection, structured planning, and execution. The planner makes the source field, reasoning rules, and output constraints explicit before answer generation, reducing ambiguity relative to direct prompting. We evaluate SCOPE on 1,500 hybrid reasoning questions over oncology clinical-trial tables against zero-shot, few-shot, chain-of-thought, TableGPT2, BlendSQL, and EHRAgent. Results show that explicit multi-LLM planning improves accuracy for reasoning-based questions while offering a stronger accuracy-efficiency tradeoff than heavier agentic baselines. Our findings position clinical trial reasoning as a distinct table understanding problem and highlight hybrid planner-based decomposition as an effective solution."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chowdhury-etal-2026-scope">
<titleInfo>
<title>SCoPE: Planning for Hybrid Querying over Clinical Trial Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Suparno</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manan</namePart>
<namePart type="family">Choudhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tejas</namePart>
<namePart type="family">Anvekar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammed</namePart>
<namePart type="family">Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaneez</namePart>
<namePart type="family">Khakwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamad</namePart>
<namePart type="family">Sonbol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irbaz</namePart>
<namePart type="family">Riaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</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>BioNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</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">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-434-7</identifier>
</relatedItem>
<abstract>Systematic reviews of clinical trials require analysts to extract attributes that are rarely stored as ready-made columns. For example, the drug class of an immunotherapy named in a regimen, the additional agents combined with it, or whether a listed endpoint is a primary or secondary outcome. These attributes must be inferred from the visible content of other fields through normalization, classification, or structured extraction, and existing approaches such as direct LLM prompting, text-to-SQL, and agentic pipelines leave this reasoning implicit in a single generation step or pay a heavy execution cost for limited accuracy gains. We propose SCOPE (Structured Clinical hybrid Planning for Evidence retrieval in clinical trials), a multi-LLM planner-based framework that decomposes the task into row selection, structured planning, and execution. The planner makes the source field, reasoning rules, and output constraints explicit before answer generation, reducing ambiguity relative to direct prompting. We evaluate SCOPE on 1,500 hybrid reasoning questions over oncology clinical-trial tables against zero-shot, few-shot, chain-of-thought, TableGPT2, BlendSQL, and EHRAgent. Results show that explicit multi-LLM planning improves accuracy for reasoning-based questions while offering a stronger accuracy-efficiency tradeoff than heavier agentic baselines. Our findings position clinical trial reasoning as a distinct table understanding problem and highlight hybrid planner-based decomposition as an effective solution.</abstract>
<identifier type="citekey">chowdhury-etal-2026-scope</identifier>
<location>
<url>https://aclanthology.org/2026.bionlp-1.76/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>944</start>
<end>954</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SCoPE: Planning for Hybrid Querying over Clinical Trial Data
%A Chowdhury, Suparno
%A Choudhury, Manan
%A Anvekar, Tejas
%A Khan, Muhammed
%A Khakwani, Kaneez
%A Sonbol, Mohamad
%A Riaz, Irbaz
%A Gupta, Vivek
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S BioNLP 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California
%@ 979-8-89176-434-7
%F chowdhury-etal-2026-scope
%X Systematic reviews of clinical trials require analysts to extract attributes that are rarely stored as ready-made columns. For example, the drug class of an immunotherapy named in a regimen, the additional agents combined with it, or whether a listed endpoint is a primary or secondary outcome. These attributes must be inferred from the visible content of other fields through normalization, classification, or structured extraction, and existing approaches such as direct LLM prompting, text-to-SQL, and agentic pipelines leave this reasoning implicit in a single generation step or pay a heavy execution cost for limited accuracy gains. We propose SCOPE (Structured Clinical hybrid Planning for Evidence retrieval in clinical trials), a multi-LLM planner-based framework that decomposes the task into row selection, structured planning, and execution. The planner makes the source field, reasoning rules, and output constraints explicit before answer generation, reducing ambiguity relative to direct prompting. We evaluate SCOPE on 1,500 hybrid reasoning questions over oncology clinical-trial tables against zero-shot, few-shot, chain-of-thought, TableGPT2, BlendSQL, and EHRAgent. Results show that explicit multi-LLM planning improves accuracy for reasoning-based questions while offering a stronger accuracy-efficiency tradeoff than heavier agentic baselines. Our findings position clinical trial reasoning as a distinct table understanding problem and highlight hybrid planner-based decomposition as an effective solution.
%U https://aclanthology.org/2026.bionlp-1.76/
%P 944-954
Markdown (Informal)
[SCoPE: Planning for Hybrid Querying over Clinical Trial Data](https://aclanthology.org/2026.bionlp-1.76/) (Chowdhury et al., BioNLP 2026)
ACL
- Suparno Chowdhury, Manan Choudhury, Tejas Anvekar, Muhammed Khan, Kaneez Khakwani, Mohamad Sonbol, Irbaz Riaz, and Vivek Gupta. 2026. SCoPE: Planning for Hybrid Querying over Clinical Trial Data. In BioNLP 2026, pages 944–954, San Diego, California. Association for Computational Linguistics.