Temporal Preference Concepts and their Functions in a Large Language Model 事件

Temporal Preference Concepts and their Functions in a Large Language Model arXiv:2606.05194v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly being deployed to make decisions that require trading off near-term gains against long-term consequences, yet little is known about how they internally represent or resolve these tradeoffs. In this work, we causally localize an underlying subgraph for temporal preference in a distilled LLM (Qwen3-4B-Instruct-2507), identifying