all AI news
Prototypical Calibration for Few-shot Learning of Language Models. (arXiv:2205.10183v1 [cs.CL])
May 23, 2022, 1:12 a.m. | Zhixiong Han, Yaru Hao, Li Dong, Furu Wei
cs.CL updates on arXiv.org arxiv.org
In-context learning of GPT-like models has been recognized as fragile across
different hand-crafted templates, and demonstration permutations. In this work,
we propose prototypical calibration to adaptively learn a more robust decision
boundary for zero- and few-shot classification, instead of greedy decoding.
Concretely, our method first adopts Gaussian mixture distribution to estimate
the prototypical clusters for all categories. Then we assign each cluster to
the corresponding label by solving a weighted bipartite matching problem. Given
an example, its prediction is calibrated …
More from arxiv.org / cs.CL updates on arXiv.org
VAL: Interactive Task Learning with GPT Dialog Parsing
1 day, 10 hours ago |
arxiv.org
DBCopilot: Scaling Natural Language Querying to Massive Databases
1 day, 10 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Staff Software Engineer, Generative AI, Google Cloud AI
@ Google | Mountain View, CA, USA; Sunnyvale, CA, USA
Expert Data Sciences
@ Gainwell Technologies | Any city, CO, US, 99999