Unconditional Text Generation

Unconditional Text Generation is a text generation paradigm that produces coherent sequences of natural language without conditioning on any specific input context or prompt, distinguishing itself from conditional approaches by relying solely on internal model dynamics and learned language patterns.

14

Publications

1.4K

Citations

53

Authors

13

Institutions

Publications per year

2017–2026

14

Authors

53

  1. XL
    Xiao Liu

    Tsinghua University, China

    3 publications · 980 citations

    3

    h-index

  2. YQ
    Yujie Qian

    Massachusetts Institute of Technology, United States

    3 publications · 980 citations

    3

    h-index

  3. MD
    Ming Ding

    Harbin Engineering University, China

    3 publications · 980 citations

    3

    h-index

  4. ZD
    Zhengxiao Du

    Tsinghua University, China

    3 publications · 980 citations

    3

    h-index

  5. JQ
    Jiezhong Qiu

    Tsinghua University, China

    3 publications · 980 citations

    3

    h-index

1–5 of 53

Venues

  1. arXiv (Cornell University)

    Repository · 9 publications · 383 citations

    9

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 2 publications · 40 citations

    2

    h-index

  3. 1

    h-index

  4. PubMed

    Repository · 1 publications · 10 citations

1–4