RoleConflictBench generates role-conflict scenarios by varying situational urgency to measure whether LLMs follow dynamic context or learned role preferences, finding that tested models mostly follow the latter.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RoleConflictBench: A Benchmark of Role Conflict Scenarios for Evaluating LLMs' Contextual Sensitivity
RoleConflictBench generates role-conflict scenarios by varying situational urgency to measure whether LLMs follow dynamic context or learned role preferences, finding that tested models mostly follow the latter.