Seven of 27 tested LLMs (25.93%) exhibited identity confusion, which the authors link to hallucination and show reduces user trust, especially in critical tasks.
Human chatgpt comparison corpus (hc3)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
I'm Spartacus, No, I'm Spartacus: Measuring and Understanding LLM Identity Confusion
Seven of 27 tested LLMs (25.93%) exhibited identity confusion, which the authors link to hallucination and show reduces user trust, especially in critical tasks.