{"ID":2874308,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.09704","arxiv_id":"2509.09704","title":"Temporal Preferences in Language Models for Long-Horizon Assistance","abstract":"We study whether language models (LMs) exhibit future- versus present-oriented preferences in intertemporal choice and whether those preferences can be systematically manipulated. Using adapted human experimental protocols, we evaluate multiple LMs on time-tradeoff tasks and benchmark them against a sample of human decision makers. We introduce an operational metric, the Manipulability of Time Orientation (MTO), defined as the change in an LM's revealed time preference between future- and present-oriented prompts. In our tests, reasoning-focused models (e.g., DeepSeek-Reasoner and grok-3-mini) choose later options under future-oriented prompts but only partially personalize decisions across identities or geographies. Moreover, models that correctly reason about time orientation internalize a future orientation for themselves as AI decision makers. We discuss design implications for AI assistants that should align with heterogeneous, long-horizon goals and outline a research agenda on personalized contextual calibration and socially aware deployment.","short_abstract":"We study whether language models (LMs) exhibit future- versus present-oriented preferences in intertemporal choice and whether those preferences can be systematically manipulated. Using adapted human experimental protocols, we evaluate multiple LMs on time-tradeoff tasks and benchmark them against a sample of human dec...","url_abs":"https://arxiv.org/abs/2509.09704","url_pdf":"https://arxiv.org/pdf/2509.09704v1","authors":"[\"Ali Mazyaki\",\"Mohammad Naghizadeh\",\"Samaneh Ranjkhah Zonouzaghi\",\"Hossein Setareh\"]","published":"2025-09-05T16:21:23Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.CY\"]","methods":"[\"Language Model\"]","has_code":false}