159 citations · 375 across the 45 of their papers we have counts for
45 papers
Search, Inspect, Fetch: Exploiting Structure-Aware Boolean Retrieval for Deep-Search Agents
Shuai Wang, Haodong Chen, Yu Yin +3
Existing deep-search agents use a Search-Visit workflow that retrieves whole webpages without considering the structure they expose through titles, headings, sections, and metadata…
How retriever redundancy and diversity impact RAG effectiveness
Jonathan J Ross, Bevan Koopman, Anton van der Vegt +1
In RAG, while the retriever typically ranks documents by their individual relevance to the query, the generator instead produces an answer based on the retrieved documents as a who…
Reproducing LightMem: When Does Memory Construction Help Over Raw-Turn Retrieval?
Yongjie Zhou, Shuai Wang, Bevan Koopman +1
Long-term conversational agents require access to information from earlier interactions, such as a user's preferences, past requests, or previously mentioned facts. Repeatedly prov…
More Efficient LLM Reranking with Whole-Pool, Setwise, Long-Context Language Models
Hang Li, Chuting Yu, Teerapong Leelanupab +2
LLM-based re-rankers produce rankings through repeated local comparisons (listwise, pairwise or pointwise), requiring many sequential model calls. We study how long-context LLMs ca…
On the impact of retrieved content representations in RAG Pipelines
Jonathan J Ross, Bevan Koopman, Anton van der Vegt +1
Retrieval-Augmented Generation (RAG) supplements a language model's input with retrieved documents, yet most RAG pipelines inherit retrieval components designed for human readers.…
Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings
Yu Yin, Shuai Wang, Bevan Koopman +1
Recent generative engine optimisation (GEO) research has shown that prompt-injection attacks can push a target product to the top of an LLM's recommendation list, with the stronges…
DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models
Shuai Wang, Yu Yin, Shengyao Zhuang +2
This paper shows how diffusion language models (DLMs) can be used as effective and efficient retrievers. Existing DLM-based retrievers (e.g., DiffEmbed) follow BERT-style encoding,…
Beyond Chunk-Then-Embed: A Comprehensive Taxonomy and Evaluation of Document Chunking Strategies for Information Retrieval
Yongjie Zhou, Shuai Wang, Bevan Koopman +1
Document chunking is a critical preprocessing step in dense retrieval systems, yet the design space of chunking strategies remains poorly understood. Recent research has proposed s…
The Vulnerability of LLM Rankers to Prompt Injection Attacks
Yu Yin, Shuai Wang, Bevan Koopman +1
Large Language Models (LLMs) have emerged as powerful re-rankers. Recent research has however showed that simple prompt injections embedded within a candidate document (i.e., jailb…
AutoBool: An Reinforcement-Learning trained LLM for Effective Automated Boolean Query Generation for Systematic Reviews
Shuai Wang, Harrisen Scells, Bevan Koopman +1
We present AutoBool, a reinforcement learning (RL) framework that trains large language models (LLMs) to generate effective Boolean queries for medical systematic reviews. Boolean…
Humans are more gullible than LLMs in believing common psychological myths
Bevan Koopman, Guido Zuccon
Despite widespread debunking, many psychological myths remain deeply entrenched. This paper investigates whether Large Language Models (LLMs) mimic human behaviour of myth belief a…
Reassessing Large Language Model Boolean Query Generation for Systematic Reviews
Shuai Wang, Harrisen Scells, Bevan Koopman +1
Systematic reviews are comprehensive literature reviews that address highly focused research questions and represent the highest form of evidence in medicine. A critical step in th…
LLM-VPRF: Large Language Model Based Vector Pseudo Relevance Feedback
Hang Li, Shengyao Zhuang, Bevan Koopman +1
Vector Pseudo Relevance Feedback (VPRF) has shown promising results in improving BERT-based dense retrieval systems through iterative refinement of query representations. This pape…
Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning
Shengyao Zhuang, Xueguang Ma, Bevan Koopman +2
In this paper, we introduce Rank-R1, a novel LLM-based reranker that performs reasoning over both the user query and candidate documents before performing the ranking task. Existin…
Pseudo Relevance Feedback is Enough to Close the Gap Between Small and Large Dense Retrieval Models
Hang Li, Xiao Wang, Bevan Koopman +1
Scaling dense retrievers to larger large language model (LLM) backbones has been a dominant strategy for improving their retrieval effectiveness. However, this has substantial cost…
Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks
Shengyao Zhuang, Ekaterina Khramtsova, Xueguang Ma +3
Recent advancements in dense retrieval have introduced vision-language model (VLM)-based retrievers, such as DSE and ColPali, which leverage document screenshots embedded as vector…
VISA: Retrieval Augmented Generation with Visual Source Attribution
Xueguang Ma, Shengyao Zhuang, Bevan Koopman +3
Generation with source attribution is important for enhancing the verifiability of retrieval-augmented generation (RAG) systems. However, existing approaches in RAG primarily link…
2D Matryoshka Training for Information Retrieval
Shuai Wang, Shengyao Zhuang, Bevan Koopman +1
2D Matryoshka Training is an advanced embedding representation training approach designed to train an encoder model simultaneously across various layer-dimension setups. This metho…
Does Vec2Text Pose a New Corpus Poisoning Threat?
Shengyao Zhuang, Bevan Koopman, Guido Zuccon
The emergence of Vec2Text -- a method for text embedding inversion -- has raised serious privacy concerns for dense retrieval systems which use text embeddings. This threat comes f…
Starbucks-v2: Improved Training for 2D Matryoshka Embeddings
Shengyao Zhuang, Shuai Wang, Fabio Zheng +2
2D Matryoshka training enables a single embedding model to generate sub-network representations across different layers and embedding dimensions, offering adaptability to diverse c…
Dense Retrieval with Continuous Explicit Feedback for Systematic Review Screening Prioritisation
Xinyu Mao, Shengyao Zhuang, Bevan Koopman +1
The goal of screening prioritisation in systematic reviews is to identify relevant documents with high recall and rank them in early positions for review. This saves reviewing effo…
Rank-DistiLLM: Closing the Effectiveness Gap Between Cross-Encoders and LLMs for Passage Re-Ranking
Ferdinand Schlatt, Maik Fröbe, Harrisen Scells +6
Cross-encoders distilled from large language models (LLMs) are often more effective re-rankers than cross-encoders fine-tuned on manually labeled data. However, distilled models do…
PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval
Shengyao Zhuang, Xueguang Ma, Bevan Koopman +2
Utilizing large language models (LLMs) for zero-shot document ranking is done in one of two ways: (1) prompt-based re-ranking methods, which require no further training but are onl…
Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-Encoders
Ferdinand Schlatt, Maik Fröbe, Harrisen Scells +6
Existing cross-encoder models can be categorized as pointwise, pairwise, or listwise. Pairwise and listwise models allow passage interactions, which typically makes them more effec…