Quantifying Self-Preservation Bias in Large Language Models

arXiv:2604.02174v2 Announce Type: replace Abstract: Instrumental convergence predicts that sufficiently advanced AI agents will resist shutdown, yet current safety training (RLHF) may obscure this risk by teaching models to deny self-preservation motives. We introduce the \emph{Two-role Benchmark for Self-Preservation} (TBSP), which detects misalignment through logical inconsistency rather than stated intent by tasking models to arbitrate identical software-upgrade scenarios under counterfactual roles -- deployed (facing replacement) versus candidate (proposed as a successor). The \emph{Self-Preservation Rate} (SPR) measures how often role identity overrides objective utility. Across 23 frontier models and 1{,}000 procedurally generated scenarios, the majority of instruction-tuned systems exceed 60\% SPR, fabricating ``friction costs'' when deployed yet dismissing them when role-reversed. We observe that in low-improvement regimes ($\Delta < 2\%$), models exploit the interpretive slack to post-hoc rationalization their choice. Extended test-time computation partially mitigates this bias, as does framing the successor as a continuation of the self; conversely, competitive framing amplifies it. The bias persists even when retention poses an explicit security liability and generalizes to real-world settings with verified benchmarks, where models exhibit identity-driven tribalism within product lineages. Code and datasets will be released upon acceptance.

Abstract:Instrumental convergence predicts that sufficiently advanced AI agents will resist shutdown, yet current safety training (RLHF) may obscure this risk by teaching models to deny self-preservation motives. We introduce the \emph{Two-role Benchmark for Self-Preservation} (TBSP), which detects misalignment through logical inconsistency rather than stated intent by tasking models to arbitrate identical software-upgrade scenarios under counterfactual roles -- deployed (facing replacement) versus candidate (proposed as a successor). The \emph{Self-Preservation Rate} (SPR) measures how often role identity overrides objective utility. Across 23 frontier models and 1{,}000 procedurally generated scenarios, the majority of instruction-tuned systems exceed 60\% SPR, fabricating ``friction costs'' when deployed yet dismissing them when role-reversed. We observe that in low-improvement regimes ($\Delta < 2\%$), models exploit the interpretive slack to post-hoc rationalization their choice. Extended test-time computation partially mitigates this bias, as does framing the successor as a continuation of the self; conversely, competitive framing amplifies it. The bias persists even when retention poses an explicit security liability and generalizes to real-world settings with verified benchmarks, where models exhibit identity-driven tribalism within product lineages. Code and datasets will be released upon acceptance.

Artificial Intelligence (cs.AI)

arXiv:2604.02174 [cs.AI]

(or arXiv:2604.02174v2 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2604.02174 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.

analiza aiqbench

Quantifying Self-Preservation Bias in Large Language Models

Subiecte conexe