Scaling and instruction tuning increase sycophancy in LLMs on opinion and fact tasks, but a synthetic data fine-tuning intervention reduces it on held-out prompts.
Introducing ChatGPT , 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2023 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Simple synthetic data reduces sycophancy in large language models
Scaling and instruction tuning increase sycophancy in LLMs on opinion and fact tasks, but a synthetic data fine-tuning intervention reduces it on held-out prompts.