2026
Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality
Wen Luo, Guangyue Peng, Liang Wang, et al.
Ph.D. Student · Computational Linguistics
Guangyue Peng
Ph.D. student at the School of Computer Science, Peking University, advised by Prof. Houfeng Wang.
[0]reasoningp = 0.94
[1]retrieval-augp = 0.96
[2]memoryp = 0.91
About
My research centers on large language models, with a particular focus on reasoning faithfulness, retrieval-augmented generation, and long-term memory. I study how models can reason more faithfully and reliably, how they can ground generation in retrieved knowledge, and how they can keep learning over time without forgetting.
Feel free to reach out if you are interested in collaboration or have related research ideas.
Publications11 entries
2026
SWE-Ext: Scaling and Extending Augmented Data for Mid-Training of Repository-Level Coding Tasks
Wei Li, Xin Zhang, Shaohang Wei, Wen Luo, Feifan Song, Guangyue Peng, et al.
2026
Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation
Guangyue Peng, Zongchao Chen, Wen Luo, et al.
2026
Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations
Wen Luo, Guangyue Peng, Wei Li, et al.
2026
PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning
Ruixiang Feng, ..., Guangyue Peng, et al.
2026
Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts
Chen Yang, Guangyue Peng, Jiahao Zhu, et al.
2025
Learn to Memorize: Scalable Continual Learning in Semiparametric Models with Mixture-of-Neighbors Induction Memory
Guangyue Peng, Tao Ge, Wen Luo, et al.
2025
Odysseus Navigates the Sirens' Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation
Wen Luo, Feifan Song, Wei Li, Guangyue Peng, et al.
2025
FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation
Wei Li, Xin Zhang, ..., Wen Luo, Guangyue Peng, et al.
2025
Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction
Guangyue Peng, Wei Li, Wen Luo, et al.
2025
Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction
Wei Li, Wen Luo, Guangyue Peng, et al.
Honors & Awards06
2025
Huawei Scholarship, School of Computer Science, Peking University
2025
BOSS Zhipin Scholarship
2024
Merit Student, Peking University
2022
Outstanding Individual Contribution, Beijing Winter Olympics & Paralympics
2021
Fenjiu Group Public Welfare Scholarship, Peking University
2019
Freshman Scholarship, Peking UniversityThird Prize
Education
2023.09 — 2028.07
(expected)
(expected)
Ph.D., Peking UniversitySchool of Computer Science
2019.09 — 2023.07
Undergraduate, Peking UniversityData Science and Big Data Technology, Yuanpei College
Internships
2025.04 — 2026.04
BOSS ZhipinResearch Intern, Algorithm Engineering Group · Beijing
2023.09 — 2024.08
Peking University & Founder GroupUniversity-Enterprise Cooperation Project · Beijing
2022.09 — 2023.06
Microsoft Research AsiaResearch Intern, Innovation Engineering Group · Beijing