Publications

Meng Cao, Lei Shu, Lei Yu, Yun Zhu, Nevan Wichers, Yinxiao Liu, Lei Meng (2024). Enhancing reinforcement learning with dense rewards from language model critic. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing.

Emily Cheng, Diego Doimo, Corentin Kervadec, Iuri Macocco, Jade Yu, Alessandro Laio, Marco Baroni (2024). Emergence of a high-dimensional abstraction phase in language transformers. arXiv preprint arXiv:2405.15471.

Meng Cao, Lei Shu, Lei Yu, Yun Zhu, Nevan Wichers, Yinxiao Liu, Lei Meng (2024). Drlc: Reinforcement learning with dense rewards from llm critic. arXiv e-prints.

Meng Cao, Lei Shu, Lei Yu, Yun Zhu, Nevan Wichers, Yinxiao Liu, Lei Meng (2024). Beyond Sparse Rewards: Enhancing Reinforcement Learning with Language Model Critique in Text Generation. arXiv preprint arXiv:2401.07382.

Lei Yu, Yang Xu (2023). Word sense extension. arXiv preprint arXiv:2306.05609.

Lei Yu (2023). Systematic word meta-sense extension. arXiv preprint arXiv:2311.13029.

Meiling Tao, Xuechen Liang, Tianyu Shi, Lei Yu, Yiting Xie (2023). Rolecraft-glm: Advancing personalized role-playing in large language models. arXiv preprint arXiv:2401.09432.

Olivia Fugikawa, Oliver Hayman, Raymond Liu, Lei Yu, Thomas Brochhagen, Yang Xu (2023). A computational analysis of crosslinguistic regularity in semantic change. Frontiers in Communication.

Lei Yu, Yang Xu (2022). Noun2Verb: Probabilistic frame semantics for word class conversion. Computational Linguistics.

Lei Yu, Yang Xu (2022). Infinite mixture chaining: Efficient temporal construction of word meaning. Proceedings of the Annual Meeting of the Cognitive Science Society.