LLMs outperform humans at writing effective HR emails in a new simulator (48-54% vs 23.5% pass rate), with LLM-rewritten human emails doing best and larger judge models converging on subtle communication norms.
A scattered list of dis- parate or unrelated fixes is also low tact
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CY 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Moral Mazes in the Era of LLMs
LLMs outperform humans at writing effective HR emails in a new simulator (48-54% vs 23.5% pass rate), with LLM-rewritten human emails doing best and larger judge models converging on subtle communication norms.