🧑‍🔬 Xinyu Ma

🏛️ Affiliations

🏢BaiduBeijing · China2023–2026 · 19 paperscurrent🔬Institute of Computing TechnologyBeijing · China2021–2023 · 7 papers🎓University of Chinese Academy of SciencesBeijing · China2021–2023 · 5 papers🎓University of Southern CaliforniaLos Angeles · United States1995–2002 · 3 papers🎓Harbin Institute of TechnologyHarbin · China2023–2025 · 2 papers🎓University of Science and Technology of ChinaHefei · China2021–2022 · 2 papers🏛️Chinese Academy of SciencesBeijing · China2021 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 8 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents (2023 · 496 citations)
   Most earlier attempts to use large language models in search had them generate queries or documents. This paper asks whether chat-style models such as ChatGPT and GPT-4 can directly re-order a set of retrieved passages by relevance. Older prompting styles, query generation and relevance generation, gave weak results…
2. Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation (2025 · 77 citations)
   LLM-based recommenders often hallucinate, for example by suggesting films that do not exist. They also lack recent and domain-specific knowledge, and retraining them often is expensive. Standard document-based RAG can help, but it brings in noisy text and ignores how entities relate to each other. The authors propose…
3. TC–RAG: Turing–Complete RAG's Case study on Medical LLM Systems (2025 · 25 citations)
   Retrieval-augmented generation can reduce hallucinations and stale knowledge in medical LLMs. However, existing RAG pipelines lack an explicit state variable that tells the system when to stop retrieving, so they can loop without converging or pile up noisy context. The authors propose TC–RAG, which they prove to be…
4. ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability (2026 · 18 citations)
   LLM-based listwise rerankers struggle with complex search needs, such as expert StackExchange questions, coding, or math, because they are mostly trained on web search data like MSMARCO.
5. Reinforced Efficient Reasoning via Semantically Diverse Exploration (2026 · 9 citations)
   RLVR methods such as GRPO assign one reward to a whole response. MCTS-based variants refine this by building tree-structured rollouts, which allows credit to be assigned per segment. However, they usually choose branch points using token-level generation entropy. This often splits on near-synonyms (e.g., "can" vs.…
6. Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning (2025 · 9 citations)
   Retrieval-augmented LLMs face two competing demands. They should trust retrieved evidence even when it contradicts what they memorized (adherence), and they should ignore retrieved passages that look relevant but are actually noise (robustness). Training aimed at one of these tends to hurt the other. The authors…
7. The Mirage of Model Editing: Revisiting Evaluation in the Wild (2025 · 9 citations)
   Published model-editing results often look nearly perfect. This paper asks whether those results hold once the evaluation reflects how an edited LLM would actually be used. The authors build QAEdit, a benchmark drawn from Natural Questions, TriviaQA and SimpleQA. GPT-4 adds the subjects and paraphrased prompts that…

🤝 Co-authors here

12 of 31 co-authors with a page, the most papers together first.

• Dawei Yin ×5
• Shuaiqiang Wang ×3
• Junfeng Zhao ×2
• Ruizhe Zhang ×2
• Weiwei Sun ×2
• Xinke Jiang ×2
• Xu Chu ×2
• Yongxin Xu ×2
• Zhaochun Ren ×2
• Zhumin Chen ×2
• Daiting Shi
• Fei Sun

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×6: ACL 2026 ×2, ACL 2025 ×4
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2023

🔗 Cited by

Papers of our library cite their works 309 times (of the 149,439 papers whose bibliographies we read); 59 citing papers with a page here →.

Updated 31 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/xinyu-ma/