PersonaFeedback provides a human-labeled benchmark showing current LLMs, including strong reasoners, score only about 65-70 percent on hard personalization choices, and explicit persona information helps more than retrieval.
Llama 3 model card
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalization
PersonaFeedback provides a human-labeled benchmark showing current LLMs, including strong reasoners, score only about 65-70 percent on hard personalization choices, and explicit persona information helps more than retrieval.