Yann Dubois
Yann Dubois has 2 papers in our library, in 2023; often with Jimmy Lei Ba, Tatsunori Hashimoto, Andrew Wang.
OpenAlex · h-index 5 · 5 works · 132 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 731 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #4022
Affiliations
Fields, topics and concepts
📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArtificial Intelligence · 2 worksDecision Sciences · 1 workManagement Science and Operations Research · 1 workSocial Sciences · 1 workSafety Research · 1 workSoftware · 1 work
Works by year
2020s
Papers
- AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback (2023 · 456 citations)
Training instruction-following LLMs with human feedback is costly and slow to iterate on. It is also hard to evaluate reliably, and commercial vendors document it poorly. AlpacaFarm is a sandbox for cheaply studying learning from pairwise feedback (LPF). It has three parts: - Identifying the Risks of LM Agents with an LM-Emulated Sandbox (2023 · 96 citations)
LM agents that call external tools, such as banking APIs, terminals or smart-home devices, can cause serious harm when they misread a request.
All works
- AlpacaFarm: A Simulation Framework for Methods that Learn from Human FeedbackConference on Neural Information Processing Systems (NeurIPS)Yann Dubois, Xuechen Li, Rohan Taori, et al.2023 · 456 citations
- Identifying the Risks of LM Agents with an LM-Emulated SandboxarXiv:2309.15817Yangjun Ruan, Honghua Dong, Andrew Wang, et al.2023 · 96 citations
- Improving Self-Supervised Learning by Characterizing Idealized Representations ↗neural information processing systems · no summary yetYann Dubois et al.2022 · 11 citations
Co-authors here
- Jimmy Lei Ba ×2
- Tatsunori Hashimoto ×2
- Andrew Wang
- Carlos Guestrin
- Chris J. Maddison
- Honghua Dong
- Ishaan Gulrajani
- Percy Liang
- Silviu Pitis
- Tianyi Zhang
- Yangjun Ruan
- Yongchao Zhou
Venues
- Conference on Neural Information Processing Systems (NeurIPS): NeurIPS 2023
- neural information processing systems
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/yann-dubois/