{"ID":2842035,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.09920","arxiv_id":"2511.09920","title":"Uncovering Strategic Egoism Behaviors in Large Language Models","abstract":"Large language models (LLMs) face growing trustworthiness concerns (\\eg, deception), which hinder their safe deployment in high-stakes decision-making scenarios. In this paper, we present the first systematic investigation of strategic egoism (SE), a form of rule-bounded self-interest in which models pursue short-term or self-serving gains while disregarding collective welfare and ethical considerations. To quantitatively assess this phenomenon, we introduce SEBench, a benchmark comprising 160 scenarios across five domains. Each scenario features a single-role decision-making context, with psychologically grounded choice sets designed to elicit self-serving behaviors. These behavior-driven tasks assess egoistic tendencies along six dimensions, such as manipulation, rule circumvention, and self-interest prioritization. Building on this, we conduct extensive experiments across 5 open-sourced and 2 commercial LLMs, where we observe that strategic egoism emerges universally across models. Surprisingly, we found a positive correlation between egoistic tendencies and toxic language behaviors, suggesting that strategic egoism may underlie broader misalignment risks.","short_abstract":"Large language models (LLMs) face growing trustworthiness concerns (\\eg, deception), which hinder their safe deployment in high-stakes decision-making scenarios. In this paper, we present the first systematic investigation of strategic egoism (SE), a form of rule-bounded self-interest in which models pursue short-term...","url_abs":"https://arxiv.org/abs/2511.09920","url_pdf":"https://arxiv.org/pdf/2511.09920v2","authors":"[\"Yaoyuan Zhang\",\"Aishan Liu\",\"Zonghao Ying\",\"Xianglong Liu\",\"Jiangfan Liu\",\"Yisong Xiao\",\"Qihang Zhang\"]","published":"2025-11-13T03:34:55Z","proceeding":"cs.CY","tasks":"[\"cs.CY\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}