Persona Vectors: Monitoring and Controlling Character Traits in Language Models · HackerPapers discussions

Persona Vectors: Monitoring and Controlling Character Traits in Language Models — mentioned by vessenes

Sun, 08 Mar 2026 01:48:30 GMT

I asked Gemini for a literature search and it came back with this: References Chen, R., Arditi, A., Sleight, H., Evans, O., & Lindsey, J. (2025). Persona Vectors: Monitoring and Controlling Character Traits in Language Models. arXiv. https://doi.org/10.48550/arxiv.2507.21509 Cited by: 97 Greenblatt, R., Denison, C., Wright, B., Roger, F., MacDiarmid, M., Marks, S., Treutlein, J., Belonax, T., Chen, J., Duvenaud, D., Khan, A., Michael, J., Mindermann, S., Perez, E., Petrini, L., Uesato, J., Kaplan, J., Shlegeris, B., Bowman, S. R., & Hubinger, E. (2024). Alignment faking in large language…

Paper and discussion history. A mention is not an endorsement.

Persona Vectors: Monitoring and Controlling Character Traits in Language Models — mentioned by acmiyaguchi

Sat, 01 Nov 2025 21:29:49 GMT

This does exist to some degree, as far as I understand, along the lines of style-transfer and ControlNet in visual domains. Anthropic has some research called "persona vectors" which effectively push generative behaviors toward or away from particular traits. [0] https://www.anthropic.com/research/persona-vectors [1] https://arxiv.org/abs/2507.21509

Paper and discussion history. A mention is not an endorsement.

Persona Vectors: Monitoring and Controlling Character Traits in Language Models — mentioned by tzury

Fri, 01 Aug 2025 19:25:18 GMT

https://arxiv.org/pdf/2507.21509

Paper and discussion history. A mention is not an endorsement.