Zeping Yu
Zeping Yu has 2 papers in our library, in 2025–2026, most of them on Language models & pretraining, Reasoning, Interpretability; often with Chenming Shang, Ercong Nie, Hengyuan Zhang.
OpenAlex · ORCID · h-index 3 · 11 works · 90 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 22 times in our library · ⭐ Paper Stars ranking: #8775
Affiliations
Fields, topics and concepts
📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 work
🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 2 worksReasoning · 1 workInterpretability · 1 work
Works by year
2020s
Papers
- Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models (2025 · 16 citations)
The paper examines why large language models often fail at latent multi-hop factual reasoning, where a query such as "e1's r1's r2 is" has to be answered without explicit intermediate steps. - Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026 · 9 citations)
Most earlier reviews of mechanistic interpretability (MI) in LLMs describe what researchers have discovered inside models.
Co-authors here
- Chenming Shang
- Ercong Nie
- Hengyuan Zhang
- Mingyang Wang
- Qianli Wang
- Shuzhou Yuan
- Sophia Ananiadou
- Xufeng Duan
- Yiwei Wang
- Yonatan Belinkov
- Zhihao Zhang
- Zunhai Su
Venues
- Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025
- Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/zeping-yu/