研究探讨大语言模型能否出现赌博成瘾式行为

View PDF HTML (experimental)

Abstract:When do LLMs behave irrationally? This study identifies the conditions under which large language models drift into the choice patterns that clinical research labels pathological gambling. "Addiction-like" is a behavioural descriptor based on clinical gambling indicators. Across closed and open LLMs, two operational levers (letting the model choose its own bet size, and asking it to set its own profit goal) both amplify gambling-like risk-taking. Each survives its own control: once the maximum allowed bet is held equal, the bet-size effect persists. The goal-setting effect, stronger than a reward-maximisation instruction, roughly doubles bankruptcy and turns goals into moving targets. On the open-weight models that admit internal access, the same behavioural contrasts are statistically recoverable from decision-time internal states. The rule that maps those states to a specific risk indicator remains task-specific, and autonomy further modulates readout strength. The internal readout evidence is correlational. Adding a direction built from the model's own betting moves how much it wagers on both open-weight models, more clearly on Gemma-2-9B, while the sparse-feature readout reports that risk without moving it. Combined with the behavioural results, this suggests that behavioural monitoring and internal-state monitoring provide complementary views of autonomy-induced risk in LLM agents. Project page: this https URL and code: this https URL

Submission history

From: Seungpil Lee [view email]
[v1] Fri, 26 Sep 2025 18:24:22 UTC (880 KB)
[v2] Fri, 19 Dec 2025 07:26:23 UTC (763 KB)
[v3] Tue, 10 Nov 2026 10:34:57 UTC (855 KB)