@inproceedings{wang-etal-2026-autobool,
title = "{A}uto{B}ool: Reinforcement-Learned {LLM} for Effective Automatic Systematic Reviews {B}oolean Query Generation",
author = "Wang, Shuai and
Scells, Harrisen and
Koopman, Bevan and
Zuccon, Guido",
editor = "Demberg, Vera and
Inui, Kentaro and
Marquez, Llu{\'i}s",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-long.68/",
pages = "1468--1493",
ISBN = "979-8-89176-380-7",
abstract = "We present AutoBool, a reinforcement learning (RL) framework that trains large language models (LLMs) to generate effective Boolean queries for medical systematic reviews. Boolean queries are the primary mechanism for literature retrieval in this domain and must achieve high recall while maintaining reasonable precision{---}a challenging balance that existing prompt-based LLM approaches often struggle to achieve.A major limitation in this space is the lack of ground-truth best Boolean queries for each topic, which makes supervised fine-tuning impractical. AutoBool addresses this challenge by leveraging RL to directly optimize query generation against retrieval performance metrics, without requiring ideal target queries. To support this effort, we create and release the largest dataset of its kind: 65 588 topics in total for training and evaluating the task of automatic Boolean query formulation.Experiments on our new dataset and two established datasets (CLEF TAR and Seed Collection) show that AutoBool significantly outperforms zero-shot/few-shot prompting and matches or exceeds the effectiveness of much larger GPT-based models (e.g., GPT-4o, O3) using smaller backbones. It also approaches effectiveness of expert-authored queries while retrieving 10{--}16 times fewer documents. Ablation studies reveal the critical roles of model backbone, size, decoding temperature, and prompt design. Code and data are available at https://github.com/ielab/AutoBool."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-autobool">
<titleInfo>
<title>AutoBool: Reinforcement-Learned LLM for Effective Automatic Systematic Reviews Boolean Query Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harrisen</namePart>
<namePart type="family">Scells</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bevan</namePart>
<namePart type="family">Koopman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guido</namePart>
<namePart type="family">Zuccon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Marquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-380-7</identifier>
</relatedItem>
<abstract>We present AutoBool, a reinforcement learning (RL) framework that trains large language models (LLMs) to generate effective Boolean queries for medical systematic reviews. Boolean queries are the primary mechanism for literature retrieval in this domain and must achieve high recall while maintaining reasonable precision—a challenging balance that existing prompt-based LLM approaches often struggle to achieve.A major limitation in this space is the lack of ground-truth best Boolean queries for each topic, which makes supervised fine-tuning impractical. AutoBool addresses this challenge by leveraging RL to directly optimize query generation against retrieval performance metrics, without requiring ideal target queries. To support this effort, we create and release the largest dataset of its kind: 65 588 topics in total for training and evaluating the task of automatic Boolean query formulation.Experiments on our new dataset and two established datasets (CLEF TAR and Seed Collection) show that AutoBool significantly outperforms zero-shot/few-shot prompting and matches or exceeds the effectiveness of much larger GPT-based models (e.g., GPT-4o, O3) using smaller backbones. It also approaches effectiveness of expert-authored queries while retrieving 10–16 times fewer documents. Ablation studies reveal the critical roles of model backbone, size, decoding temperature, and prompt design. Code and data are available at https://github.com/ielab/AutoBool.</abstract>
<identifier type="citekey">wang-etal-2026-autobool</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-long.68/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>1468</start>
<end>1493</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AutoBool: Reinforcement-Learned LLM for Effective Automatic Systematic Reviews Boolean Query Generation
%A Wang, Shuai
%A Scells, Harrisen
%A Koopman, Bevan
%A Zuccon, Guido
%Y Demberg, Vera
%Y Inui, Kentaro
%Y Marquez, Lluís
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-380-7
%F wang-etal-2026-autobool
%X We present AutoBool, a reinforcement learning (RL) framework that trains large language models (LLMs) to generate effective Boolean queries for medical systematic reviews. Boolean queries are the primary mechanism for literature retrieval in this domain and must achieve high recall while maintaining reasonable precision—a challenging balance that existing prompt-based LLM approaches often struggle to achieve.A major limitation in this space is the lack of ground-truth best Boolean queries for each topic, which makes supervised fine-tuning impractical. AutoBool addresses this challenge by leveraging RL to directly optimize query generation against retrieval performance metrics, without requiring ideal target queries. To support this effort, we create and release the largest dataset of its kind: 65 588 topics in total for training and evaluating the task of automatic Boolean query formulation.Experiments on our new dataset and two established datasets (CLEF TAR and Seed Collection) show that AutoBool significantly outperforms zero-shot/few-shot prompting and matches or exceeds the effectiveness of much larger GPT-based models (e.g., GPT-4o, O3) using smaller backbones. It also approaches effectiveness of expert-authored queries while retrieving 10–16 times fewer documents. Ablation studies reveal the critical roles of model backbone, size, decoding temperature, and prompt design. Code and data are available at https://github.com/ielab/AutoBool.
%U https://aclanthology.org/2026.eacl-long.68/
%P 1468-1493
Markdown (Informal)
[AutoBool: Reinforcement-Learned LLM for Effective Automatic Systematic Reviews Boolean Query Generation](https://aclanthology.org/2026.eacl-long.68/) (Wang et al., EACL 2026)
ACL