2026
Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality
Wen Luo, Guangyue Peng, Liang Wang, et al.
arXivPh.D. Student · Computational Linguistics
Wen Luo
Ph.D. student at the Institute of Computational Linguistics, School of Computer Science, Peking University, advised by Prof. Houfeng Wang.
[0]hallucinationp = 0.98
[1]factualityp = 0.95
[2]interpretabilityp = 0.92
About
My research focuses on building reliable and trustworthy large generative models, with a particular emphasis on hallucination, factuality, and mechanistic interpretability. I am broadly interested in developing AI systems that are more truthful, interpretable, and aligned with human expectations.
Feel free to reach out if you are interested in collaboration or have related research ideas.
Publications13 entries
2026
Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations
Wen Luo, Guangyue Peng, Wei Li, et al.
arXiv2026
Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation
Guangyue Peng, Zongchao Chen, Wen Luo, et al.
arXiv2025
Odysseus Navigates the Sirens’ Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text Generation
Wen Luo, Feifan Song, Wei Li, et al.
ACL Anthology2025
Encode Errors: Representational Retrieval of In-Context Demonstrations for Multilingual Grammatical Error Correction
Guangyue Peng, Wei Li, Wen Luo, et al.
ACL Anthology2025
Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding
Feifan Song, Shaohang Wei, Wen Luo, et al.
ACL Anthology2025
Learn to Memorize: Scalable Continual Learning in Semiparametric Models with Mixture-of-Neighbors Induction Memory
Guangyue Peng, Tao Ge, Wen Luo, et al.
ACL Anthology2025
TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios
Shaohang Wei, Wei Li, Feifan Song, Wen Luo, et al.
arXiv2025
FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation
Wei Li, Xin Zhang, Zhongxin Guo, Shaoguang Mao, Wen Luo, et al.
ACL Anthology2025
Explanation based In-Context Demonstrations Retrieval for Multilingual Grammatical Error Correction
Wei Li, Wen Luo, Guangyue Peng, Houfeng Wang
ACL Anthology2025
Mitigating Overthinking through Reasoning Shaping
Feifan Song, Shaohang Wei, Baoxin Gao, Yiwei Wang, Wen Luo, et al.
arXiv2024
Shapley Value-based Contrastive Alignment for Multimodal Information Extraction
Wen Luo, Yu Xia, Tianshu Shen, et al.
ACM DL2024
HalluDial: A Large-Scale Benchmark for Automatic Dialogue-Level Hallucination Evaluation
Wen Luo, Tianshu Shen, Wei Li, et al.
arXivHonors & Awards04
2025
President's Scholarship, Peking UniversityTop 1%
2025
BOSS Zhipin Scholarship
2025
Award for Scientific Research, Peking University
2022
Ubiquant Scholarship
Education
2024.09 — 2029.06
(expected)
(expected)
Ph.D., Peking UniversityInstitute of Computational Linguistics, School of Computer Science
2020.09 — 2024.06
Undergraduate, Peking UniversitySchool of Electronics Engineering and Computer Science
Internships
2025.08 — Present
Microsoft Research AsiaNowBeijing
2023.05 — 2024.08
Beijing Academy of Artificial Intelligence (BAAI)Beijing