Jie Zeng
Jie Zeng has 2 papers in our library, in 2026, most of them on Dialogue systems; often with Fei Yu, Jiaqing Liang, Qianyu He.
OpenAlex · ORCID · h-index 17 · 63 works · 986 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 3 times in our library · ⭐ Paper Stars ranking: #10709
Affiliations
🎓Seikei UniversityMusashino ·
Japan2024–2026 · 6 papers🎓Chongqing Medical UniversityChongqing ·
China2021–2025 · 14 papers🎓Sichuan UniversityChengdu ·
China2008–2023 · 10 papers🎓Chongqing UniversityChongqing ·
China2007–2024 · 6 papers🎓Nanjing University of Aeronautics and AstronauticsNanjing ·
China2011–2024 · 5 papers🎓Chongqing Jianzhu CollegeChongqing ·
China2021 · 3 papers🎓Lanzhou UniversityLanzhou ·
China2024 · 2 papers🎓Henan Institute of Science and TechnologyXinxiang ·
China2018–2019 · 2 papers🎓Jiangxi Science and Technology Normal UniversityNanchang ·
China2011–2012 · 2 papers🎓University of Electronic Science and Technology of ChinaChengdu ·
China2008 · 2 papers
Fields, topics and concepts
📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 worksApplied Psychology · 1 workPsychology · 1 work
🧭 Topics 1Research subjects and languages the work is about.Dialogue systems · 1 work
Works by year
2020s
Papers
- Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following (2026 · 3 citations)
Language models often fail to satisfy instructions that contain several constraints at once. Existing RL methods for this problem depend on stronger models or human annotators for rewards, and multi-constraint tasks give sparse rewards. The authors propose a self-supervised RL framework in which reward signals come… - Schema-Guided Response Generation using Multi-Frame Dialogue State for Motivational Interviewing Systems (2026 · 1 citation)
The paper addresses how to keep LLM-based Motivational Interviewing (MI) counselors from lecturing or giving unsolicited advice. The goal is for them to help clients voice their own reasons for behavior change. The authors propose SGR-MI, a schema-guided pipeline that works in three steps:
Co-authors here
Venues
- Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
- 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/jie-zeng/