Dynamic monitoring of persona vector alignments during LLM generation predicts MMLU-Pro correctness competitively with activation baselines and enables paragraph-level steering that improves accuracy on three of four models.
Persona vectors: Monitoring and controlling character traits in language models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas
Dynamic monitoring of persona vector alignments during LLM generation predicts MMLU-Pro correctness competitively with activation baselines and enables paragraph-level steering that improves accuracy on three of four models.