Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas

arXiv:2605.09159v2 Announce Type: replace Abstract: Recent work shows that large language models (LLMs) encode behavioral traits ("personas") as linear directions in activation space, often called "persona vectors". Prior work has used such directions as static handles for behavioral steering. We instead treat them as dynamic signals: probes we can monitor and intervene on as reasoning unfolds. We use the term polylogue to denote the time series of alignments between persona vectors and hidden activations over the course of generation. Experiments across four open-weight models show that polylogue features contain predictive signal for correctness comparable to low-dimensional activation summaries, while remaining interpretable through their associated persona directions. They also suggest concrete steering targets, namely, which latent directions to modulate at different stages of a response. We instantiate this as a simple paragraph-conditioned intervention that improves accuracy on three of the four models but degrades the fourth, suggesting that stage-aware latent steering is possible but not yet robust. Together, this positions the polylogue as an interpretable tool for reasoning-time monitoring and intervention.

Title:Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas

Abstract:Recent work shows that large language models (LLMs) encode behavioral traits ("personas") as linear directions in activation space, often called "persona vectors". Prior work has used such directions as static handles for behavioral steering. We instead treat them as dynamic signals: probes we can monitor and intervene on as reasoning unfolds. We use the term polylogue to denote the time series of alignments between persona vectors and hidden activations over the course of generation. Experiments across four open-weight models show that polylogue features contain predictive signal for correctness comparable to low-dimensional activation summaries, while remaining interpretable through their associated persona directions. They also suggest concrete steering targets, namely, which latent directions to modulate at different stages of a response. We instantiate this as a simple paragraph-conditioned intervention that improves accuracy on three of the four models but degrades the fourth, suggesting that stage-aware latent steering is possible but not yet robust. Together, this positions the polylogue as an interpretable tool for reasoning-time monitoring and intervention.

Artificial Intelligence (cs.AI)

arXiv:2605.09159 [cs.AI]

(or arXiv:2605.09159v2 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2605.09159 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas

Related coverage