Concepedia

Language Model Calibration

Language Model Calibration is the systematic adjustment of predicted probability distributions in a language model to accurately reflect the true likelihood of generated outputs, ensuring that confidence estimates align with empirical correctness.

73

Publications

3.1K

Citations

327

Authors

81

Institutions

Publications per year

2017–2026

54

Parents

Publications

73

Language Models (Mostly) Know What They Know

Saurav Kadavath, Tom Conerly, Amanda Askell et al. · arXiv (Cornell University) · 2022 · 163 citations · Full text

, , +11

How Can We Know <i>When</i> Language Models Know? On the Calibration of Language Models for Question Answering

Zhengbao Jiang, Jun Araki, Haibo Ding et al. · Transactions of the Association for Computational Linguistics · 2021 · 159 citations · Full text

, , +11

What large language models know and what people think they know

Mark Steyvers, Heliodoro Tejeda, Aakriti Kumar et al. · Nature Machine Intelligence · 2025 · 129 citations · Full text

, , +16

On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation

Ruidan He, Linlin Liu, Hai Ye et al. · 2021 · 123 citations · Full text

, , +9

On calibration of language recognition scores

Niko Brümmer, David A. van Leeuwen · 2006 · 114 citations

, , +15

1–5 of 73

Authors

327

  1. ZS
    Zhifang Sui

    Peking University, China

    3 publications · 136 citations

    3

    h-index

  2. GN
    Graham Neubig

    Carnegie Mellon University, United States

    3 publications · 220 citations

    3

    h-index

  3. JL
    Jia-Wei Low

    Singapore University of Technology and Design, Singapore

    2 publications · 137 citations

    2

    h-index

  4. BD
    Bosheng Ding

    Nanyang Technological University, Singapore

    2 publications · 137 citations

    2

    h-index

  5. HD
    Haibo Ding

    Southeast University, China

    2 publications · 199 citations

    2

    h-index

1–5 of 327

Institutions

81

  1. Carnegie Mellon University

    Pittsburgh, United States

    5 h-index

    11 publications

    586 citations

  2. Peking University

    Beijing, China

    4 h-index

    18 publications

    566 citations

  3. Stanford University

    Stanford, United States

    3 h-index

    11 publications

    919 citations

  4. The University of Texas at Austin

    Austin, United States

    3 h-index

    4 publications

    158 citations

  5. Singapore University of Technology and Design

    Singapore, Singapore

    2 h-index

    10 publications

    685 citations

  6. Tencent (China)

    Shenzhen, China

    2 h-index

    10 publications

    285 citations

  7. Georgia Institute of Technology

    Atlanta, United States

    2 h-index

    7 publications

    356 citations

  8. National University of Singapore

    Singapore, Singapore

    2 h-index

    2 publications

    137 citations

1–8 of 81

Venues

  1. arXiv (Cornell University)

    Repository · 13 publications · 629 citations

    12

    h-index

  2. Computer Speech & Language

    3 publications · 143 citations

    3

    h-index

  3. 3

    h-index

  4. Nature Machine Intelligence

    2 publications · 243 citations

    2

    h-index

  5. 2

    h-index

1–5