BK
Bevan Koopman
cs.IRcs.CLcs.AIcs.CVcs.LGNatural Language ProcessingDeath CertificatesMachine LearningNatural language processingCancer classification
On Valency
published · living versionsW_zdvx78df·v1 · currentpublished
Do Conversational Agents Need Explicit Memory? A Controlled Comparison with Raw-History Retrieval
with Yongjie Zhou, Shuai Wang, Guido Zuccon
1 version
Preprints & journals
63 papers in the corpus · 2012–2026Do Conversational Agents Need Explicit Memory? A Controlled Comparison with Raw-History Retrieval2610.24671v1 · Yongjie Zhou, Shuai Wang, Bevan Koopman et al.2026 · 0 citationsarXivon Valency
How retriever redundancy and diversity impact RAG effectiveness2608.13956v1 · Jonathan J Ross, Bevan Koopman, Anton van der Vegt et al.2026 · 0 citationsarXiv
Search, Inspect, Fetch: Exploiting Structure-Aware Boolean Retrieval for Deep-Search Agents2608.02751v3 · Shuai Wang, Haodong Chen, Yu Yin et al.2026 · 0 citationsarXiv
Reproducing LightMem: When Does Memory Construction Help Over Raw-Turn Retrieval?2607.29104v2 · Yongjie Zhou, Shuai Wang, Bevan Koopman et al.2026 · 0 citationsarXiv
More Efficient LLM Reranking with Whole-Pool, Setwise, Long-Context Language Models2606.01782v3 · Hang Li, Chuting Yu, Bevan Koopman et al.2026 · 0 citationsarXiv
On the impact of retrieved content representations in RAG Pipelines2605.30790v1 · Jonathan J Ross, Bevan Koopman, Anton van der Vegt et al.2026 · 0 citationsarXiv
Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings2605.28017v2 · Yu Yin, Shuai Wang, Bevan Koopman et al.2026 · 0 citationsarXiv
DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models2605.07210v2 · Shuai Wang, Yu Yin, Shengyao Zhuang et al.2026 · 0 citationsarXiv
CXRMate-2: Structured Multimodal Temporal Embeddings and Tractable Reinforcement Learning for Clinically Acceptable Chest X-ray Radiology Report Generation2604.18967v2 · Aaron Nicolson, Elizabeth J. Cooper, Hwan-Jin Yoon et al.2026 · 0 citationsarXiv
Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval2602.16974v1 · Yongjie Zhou, Shuai Wang, Bevan Koopman et al.2026 · 0 citationsarXiv
The Vulnerability of LLM Rankers to Prompt Injection Attacks2602.16752v1 · Yu Yin, Shuai Wang, Bevan Koopman et al.2026 · 0 citationsSIGIR 2026
Automated Chest X-ray Report Generation Remains Unsolved.41758145 · Zhang, Xiaoman, Acosta, Julian Nicolas, Yang, Xiaoli et al.2026 · 2 citationsPacific Symposium on Biocomputing. Pacific Symposium on Biocomputing. 2026;31:236-250
AutoBool: An Reinforcement-Learning trained LLM for Effective Automated Boolean Query Generation for Systematic Reviews2602.00005v1 · Shuai Wang, Harrisen Scells, Bevan Koopman et al.2025 · 0 citationsarXiv
Humans are more gullible than LLMs in believing common psychological myths2507.12296v1 · Bevan Koopman, Guido Zuccon2025 · 0 citationsarXiv
Reassessing Large Language Model Boolean Query Generation for Systematic Reviews2505.07155v2 · Shuai Wang, Harrisen Scells, Bevan Koopman et al.2025 · 4 citationsarXiv
LLM-VPRF: Large Language Model Based Vector Pseudo Relevance Feedback2504.01448v1 · Hang Li, Shengyao Zhuang, Bevan Koopman et al.2025 · 1 citationarXiv
Pseudo Relevance Feedback is Enough to Close the Gap Between Small and Large Dense Retrieval Models2503.14887v2 · Hang Li, Xiao Wang, Bevan Koopman et al.2025 · 0 citationsarXiv
Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning2503.06034v1 · Shengyao Zhuang, Xueguang Ma, Bevan Koopman et al.2025 · 3 citationsarXiv
Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks2501.16902v1 · Shengyao Zhuang, Ekaterina Khramtsova, Xueguang Ma et al.2025 · 4 citationsarXiv
VISA: Retrieval Augmented Generation with Visual Source Attribution2412.14457v1 · Xueguang Ma, Shengyao Zhuang, Bevan Koopman et al.2024 · 12 citationsarXiv
2D Matryoshka Training for Information Retrieval2411.17299v1 · Shuai Wang, Shengyao Zhuang, Bevan Koopman et al.2024 · 2 citationsarXiv
Generating synthetic clinical text with local large language models to identify misdiagnosed limb fractures in radiology reports.39580897 · Liu, Jinghui, Koopman, Bevan, Brown, Nathan J et al.2024 · 12 citationsArtificial intelligence in medicine. 2025;159:103027
Starbucks-v2: Improved Training for 2D Matryoshka Embeddings2410.13230v3 · Shengyao Zhuang, Shuai Wang, Fabio Zheng et al.2024 · 0 citationsarXiv
Does Vec2Text Pose a New Corpus Poisoning Threat?2410.06628v1 · Shengyao Zhuang, Bevan Koopman, Guido Zuccon2024 · 1 citationarXiv
e-Health CSIRO at RRG24: Entropy-Augmented Self-Critical Sequence Training for Radiology Report Generation2408.03500v1 · Aaron Nicolson, Jinghui Liu, Jason Dowling et al.2024 · 6 citationsarXiv
e-Health CSIRO at "Discharge Me!" 2024: Generating Discharge Summary Sections with Fine-tuned Language Models2407.02723v1 · Jinghui Liu, Aaron Nicolson, Jason Dowling et al.2024 · 5 citationsarXiv
Dense Retrieval with Continuous Explicit Feedback for Systematic Review Screening Prioritisation2407.00635v2 · Xinyu Mao, Shengyao Zhuang, Bevan Koopman et al.2024 · 4 citationsarXiv
The Impact of Auxiliary Patient Data on Automated Chest X-Ray Report Generation and How to Incorporate It2406.13181v2 · Aaron Nicolson, Shengyao Zhuang, Jason Dowling et al.2024 · 1 citationarXiv
Rank-DistiLLM: Closing the Effectiveness Gap Between Cross-Encoders and LLMs for Passage Re-Ranking2405.07920v4 · Ferdinand Schlatt, Maik Frobe, Harrisen Scells et al.2024 · 12 citationsarXiv
PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval2404.18424v3 · Shengyao Zhuang, Xueguang Ma, Bevan Koopman et al.2024 · 29 citationsarXiv
Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-Encoders2404.06912v5 · Ferdinand Schlatt, Maik Frobe, Harrisen Scells et al.2024 · 7 citationsarXiv
Understanding and Mitigating the Threat of Vec2Text to Dense Retrieval Systems2402.12784v2 · Shengyao Zhuang, Bevan Koopman, Xiaoran Chu et al.2024 · 9 citationsarXiv
ReSLLM: Large Language Models are Strong Resource Selectors for Federated Search2401.17645v1 · Shuai Wang, Shengyao Zhuang, Bevan Koopman et al.2024 · 4 citationsarXiv
TPRF: A Transformer-based Pseudo-Relevance Feedback Model for Efficient and Effective Retrieval2401.13509v2 · Hang Li, Chuting Yu, Ahmed Mourad et al.2024 · 0 citationsarXiv
A Reproducibility Study of Goldilocks: Just-Right Tuning of BERT for TAR2401.08104v1 · Xinyu Mao, Bevan Koopman, Guido Zuccon2024 · 6 citationsarXiv
Zero-shot Generative Large Language Models for Systematic Review Screening Automation2401.06320v2 · Shuai Wang, Harrisen Scells, Shengyao Zhuang et al.2024 · 28 citationsarXiv
From Free-text Drug Labels to Structured Medication Terminology with BERT and GPT.38222391 · Ngo, Duy-Hoa, Koopman, Bevan2024 · 2 citationsAMIA ... Annual Symposium proceedings. AMIA Symposium. 2023;2023:540-549
Team IELAB at TREC Clinical Trial Track 2023: Enhancing Clinical Trial Retrieval with Neural Rankers and Large Language Models2401.01566v1 · Shengyao Zhuang, Bevan Koopman, Guido Zuccon2024 · 2 citationsarXiv
Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking2310.13243v1 · Shengyao Zhuang, Bing Liu, Bevan Koopman et al.2023 · 36 citationsarXiv
A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models2310.09497v2 · Shengyao Zhuang, Honglei Zhuang, Bevan Koopman et al.2023 · 61 citationsarXiv
ChatGPT Hallucinates when Attributing Answers2309.09401v1 · Guido Zuccon, Bevan Koopman, Razia Shaik2023 · 55 citationsarXiv
Generating Natural Language Queries for More Effective Systematic Review Screening Prioritisation2309.05238v3 · Shuai Wang, Harrisen Scells, Martin Potthast et al.2023 · 11 citationsarXiv
Improving chest X-ray report generation by leveraging warm starting.37783533 · Nicolson, Aaron, Dowling, Jason, Koopman, Bevan2023 · 160 citationsArtificial intelligence in medicine. 2023;144:102633
Longitudinal Data and a Semantic Similarity Reward for Chest X-Ray Report Generation2307.09758v4 · Aaron Nicolson, Jason Dowling, Bevan Koopman2023 · 26 citationsarXiv
Dr ChatGPT, tell me what I want to hear: How prompt knowledge impacts health answer correctness2302.13793v1 · Guido Zuccon, Bevan Koopman2023 · 33 citationsarXiv
Can ChatGPT Write a Good Boolean Query for Systematic Review Literature Search?2302.03495v3 · Shuai Wang, Harrisen Scells, Bevan Koopman et al.2023 · 241 citationsarXiv
AgAsk: An Agent to Help Answer Farmer's Questions From Scientific Documents2212.10762v1 · Bevan Koopman, Ahmed Mourad, Hang Li et al.2022 · 12 citationsarXiv
Neural Rankers for Effective Screening Prioritisation in Medical Systematic Review Literature Search2212.09017v1 · Shuai Wang, Harrisen Scells, Bevan Koopman et al.2022 · 20 citationsarXiv
Automated MeSH Term Suggestion for Effective Query Formulation in Systematic Reviews Literature Search2209.08687v1 · Shuai Wang, Harrisen Scells, Bevan Koopman et al.2022 · 32 citationsarXiv
How does Feedback Signal Quality Impact Effectiveness of Pseudo Relevance Feedback for Passage Retrieval?2205.05888v1 · Hang Li, Ahmed Mourad, Bevan Koopman et al.2022 · 6 citationsarXiv
Career total: at least 210 works. 63 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.