CoPA is a new benchmark that evaluates LLMs on personalized QA by measuring alignment with six cognitive factors derived from community-individual preference divergences in 1,985 user profiles.
It must contain at least five pairs of contrasting examples, with one supporting a choice (a positive example) and one opposing it (a negative example)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CoPA: Benchmarking Personalized Question Answering with Data-Informed Cognitive Factors
CoPA is a new benchmark that evaluates LLMs on personalized QA by measuring alignment with six cognitive factors derived from community-individual preference divergences in 1,985 user profiles.