Xueguang Ma
University of Waterloo PhD; works on IR, retrieval-augmented generation, and LLM evaluation.
- Role
- grad-student
- Currently at
- Independent
- twitter.com/xueguang_ma
- GitHub
- github.com/MXueguang
- Scholar
- scholar.google.com/citations
- Papers
- 20
Cite
Notes
Only stored in your browser.
Authored papers
20OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
arXiv 2026
General-Reasoner: Advancing LLM Reasoning Across All Domains
arXiv 2025
Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality
arXiv 2025
Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning
arXiv 2025
BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent
arXiv 2025
DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers
arXiv 2025
ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations
arXiv 2025
Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks
arXiv 2025
Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval
arXiv 2025
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
NeurIPS
PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval
arXiv 2024
Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard
arXiv 2023
SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes
arXiv 2023
TheoremQA: A Theorem-driven Question Answering dataset
arXiv 2023
Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models
arXiv 2023
Augmenting Black-box LLMs with Medical Textbooks for Biomedical Question Answering (Published in Findings of EMNLP 2024)
arXiv 2023
Precise Zero-Shot Dense Retrieval without Relevance Labels
arXiv 2022
Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks
arXiv 2022
Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval
EMNLP (MRL) 2021 11
Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback: A Reproducibility Study
arXiv 2021
Affiliations
Frequent co-authors
10from 20 papers