0

Xueguang Ma

University of Waterloo PhD; works on IR, retrieval-augmented generation, and LLM evaluation.

Role
grad-student
Currently at
Independent
Papers
20

Cite

Notes

Only stored in your browser.

20papers

Authored papers

20

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

arXiv 2026

2026

General-Reasoner: Advancing LLM Reasoning Across All Domains

arXiv 2025

2025

Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality

arXiv 2025

2025

Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning

arXiv 2025

2025

BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

arXiv 2025

2025

DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers

arXiv 2025

2025

ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations

arXiv 2025

2025

Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks

arXiv 2025

2025

Fixing Data That Hurts Performance: Cascading LLMs to Relabel Hard Negatives for Robust Information Retrieval

arXiv 2025

2025

MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

NeurIPS

2024

PromptReps: Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval

arXiv 2024

2024

Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard

arXiv 2023

2023

SLIM: Sparsified Late Interaction for Multi-Vector Retrieval with Inverted Indexes

arXiv 2023

2023

TheoremQA: A Theorem-driven Question Answering dataset

arXiv 2023

2023

Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models

arXiv 2023

2023

Augmenting Black-box LLMs with Medical Textbooks for Biomedical Question Answering (Published in Findings of EMNLP 2024)

arXiv 2023

2023

Precise Zero-Shot Dense Retrieval without Relevance Labels

arXiv 2022

2022

Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks

arXiv 2022

2022

Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval

EMNLP (MRL) 2021 11

2021

Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback: A Reproducibility Study

arXiv 2021

2021

Affiliations

Currently at

Independent

grad-student · community

Frequent co-authors

10

from 20 papers