Testing two crowd-sourcing prompts on GPT-3.5 and GPT-4 shows that an awareness reminder (AwaRe) reduces several cognitive biases in LLM evaluation, while a social-projection prompt (SoPro) is mostly ineffective or harmful.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Cognitive Biases in Large Language Models: A Survey and Mitigation Experiments
Testing two crowd-sourcing prompts on GPT-3.5 and GPT-4 shows that an awareness reminder (AwaRe) reduces several cognitive biases in LLM evaluation, while a social-projection prompt (SoPro) is mostly ineffective or harmful.