112 citations · 432 across the 34 of their papers we have counts for
35 papers
Towards Retrieving Interaction Spaces for Agentic Search
Shengyao Zhuang, Yuansheng Ni, Hengxin Fun +2
Retrieval for search agents is still inherited from non-agentic information retrieval: a retriever ranks the corpus and the agent reads a small set of returned documents. Recent di…
ORBIT: Scalable and Verifiable Data Generation for Search Agents on a Tight Budget
Nandan Thakur, Zijian Chen, Xueguang Ma +1
Search agents, which integrate language models (LMs) with web search, are becoming crucial for answering complex user queries. Constructing training datasets for deep research task…
AgentIR: Reasoning-Aware Retrieval for Deep Research Agents
Zijian Chen, Xueguang Ma, Shengyao Zhuang +3
Deep Research agents are rapidly emerging as primary consumers of modern retrieval systems. Unlike human users who issue and refine queries without documenting their intermediate t…
BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
Zijian Chen, Xueguang Ma, Shengyao Zhuang +17
Deep-Research agents, which integrate large language models (LLMs) with search tools, have shown success in improving the effectiveness of handling complex queries that require ite…
MAGMaR Shared Task System Description: Video Retrieval with OmniEmbed
Jiaqi Samantha Zhan, Crystina Zhang, Shengyao Zhuang +2
Effective video retrieval remains challenging due to the complexity of integrating visual, auditory, and textual modalities. In this paper, we explore unified retrieval methods usi…
General-Reasoner: Advancing LLM Reasoning Across All Domains
Xueguang Ma, Qian Liu, Dongfu Jiang +3
Reinforcement learning (RL) has recently demonstrated strong potential in enhancing the reasoning capabilities of large language models (LLMs). Particularly, the "Zero" reinforceme…
Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality
Xueguang Ma, Luyu Gao, Shengyao Zhuang +3
Recent advancements in large language models (LLMs) have driven interest in billion-scale retrieval models with strong generalization across retrieval tasks and languages. Addition…
Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs
Nandan Thakur, Crystina Zhang, Xueguang Ma +1
Training robust retrieval and reranker models typically relies on large-scale retrieval datasets; for example, the BGE collection contains 1.6 million query-passage pairs sourced f…
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…
DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers
Xueguang Ma, Xi Victoria Lin, Barlas Oguz +3
Large language models (LLMs) have demonstrated strong effectiveness and robustness while fine-tuned as dense retrievers. However, their large parameter size brings significant infe…
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…
Unifying Multimodal Retrieval via Document Screenshot Embedding
Xueguang Ma, Sheng-Chieh Lin, Minghan Li +2
In the real world, documents are organized in different formats and varied modalities. Traditional retrieval pipelines require tailored document parsing techniques and content extr…
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
Yubo Wang, Xueguang Ma, Ge Zhang +14
In the age of large-scale language models, benchmarks like the Massive Multitask Language Understanding (MMLU) have been pivotal in pushing the boundaries of what AI can achieve in…
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…
Fine-Tuning LLaMA for Multi-Stage Text Retrieval
Xueguang Ma, Liang Wang, Nan Yang +2
The effectiveness of multi-stage text retrieval has been solidly demonstrated since before the era of pre-trained language models. However, most existing studies utilize models tha…
Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models
Raphael Tang, Xinyu Zhang, Xueguang Ma +2
Large language models (LLMs) exhibit positional bias in how they use context, which especially complicates listwise ranking. To address this, we propose permutation self-consistenc…
Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard
Ehsan Kamalloo, Nandan Thakur, Carlos Lassance +3
BEIR is a benchmark dataset for zero-shot evaluation of information retrieval models across 18 different domain/task combinations. In recent years, we have witnessed the growing po…
Few-shot In-context Learning for Knowledge Base Question Answering
Tianle Li, Xueguang Ma, Alex Zhuang +3
Question answering over knowledge bases is considered a difficult problem due to the challenge of generalizing to a wide variety of possible natural language questions. Additionall…
Zero-Shot Listwise Document Reranking with a Large Language Model
Xueguang Ma, Xinyu Zhang, Ronak Pradeep +1
Supervised ranking methods based on bi-encoder or cross-encoder architectures have shown success in multi-stage text ranking tasks, but they require large amounts of relevance judg…
TheoremQA: A Theorem-driven Question Answering dataset
Wenhu Chen, Ming Yin, Max Ku +6
The recent LLMs like GPT-4 and PaLM-2 have made tremendous progress in solving fundamental math problems like GSM8K by achieving over 90% accuracy. However, their capabilities to s…
Anserini Gets Dense Retrieval: Integration of Lucene's HNSW Indexes
Xueguang Ma, Tommaso Teofili, Jimmy Lin
Anserini is a Lucene-based toolkit for reproducible information retrieval research in Java that has been gaining traction in the community. It provides retrieval capabilities for b…
SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes
Minghan Li, Sheng-Chieh Lin, Xueguang Ma +1
This paper introduces Sparsified Late Interaction for Multi-vector (SLIM) retrieval with inverted indexes. Multi-vector retrieval methods have demonstrated their effectiveness on v…
Precise Zero-Shot Dense Retrieval without Relevance Labels
Luyu Gao, Xueguang Ma, Jimmy Lin +1
While dense retrieval has been shown effective and efficient across tasks and languages, it remains difficult to create effective fully zero-shot dense retrieval systems when no re…