Covert Influence Between Language Models

MATS Fellow:

Jay Chooi, Avi Shah

Authors:

Citations

Citations

Abstract:

As language models increasingly consume one another's outputs, covert influence -- a phenomenon where a sender's payload (the behavioral disposition it is conditioned to propagate) transfers to a receiver through carriers undetectable by humans -- becomes a growing risk. We characterize this risk across three interfaces: supervised fine-tuning, on-policy distillation, and in-context learning, and find that they vary in the scale of influence achievable without leaving behind human-visible traces. Using inference-time per-sample attribution scores, we study covert influence across all three interfaces with the ability to select carriers that amplify training-time influence, unlocking payload transfers that prior work could not achieve. We further provide evidence that covert influence with natural-language carriers is a distinct phenomenon from prior studies using number carriers, as the latter is more resistant to human detection and less portable across model families. Together, these results suggest that the risk surface for covert influence is broader than previously recognized, and we study pointwise attribution scoring methods as a tool to investigate and mitigate it.

Recent research

Building Comparative Motivation Profiles with Instrumental Interventions

Authors:

David Vella Zarb, Rustem Turtayev, Taywon Min

Date:

June 6, 2026

Citations:

Covert Influence Between Language Models

Authors:

Jay Chooi, Avi Shah

Date:

June 2, 2026

Citations:

Frequently asked questions

What is the MATS Program?
How long does the program last?