<ul data-eligibleForWebStory="true"><li>Decision-makers often lack sufficient information to make confident decisions and can undertake actions to acquire necessary information.</li><li>Different ways of acquiring information have varying costs, making it challenging to select informative and cost-effective actions.</li><li>A heuristic-based policy called CuriosiTree is proposed for zero-shot information acquisition in large language models (LLMs).</li><li>CuriosiTree uses greedy tree search to estimate expected information gain of actions and strategically selects actions balancing information gain and cost.</li><li>Empirical validation in a clinical diagnosis simulation demonstrates that CuriosiTree enables cost-effective integration of heterogeneous information sources.</li><li>CuriosiTree outperforms baseline strategies in selecting action sequences for accurate diagnosis.</li></ul>

The Curious Language Model: Strategic Test-Time Information Acquisition

Discover more