LLM（Large Language Models）在與 Polis 進行可擴展辯論的機會與風險

摘要

Polis 是一個利用機器智能來擴大審議過程的平台。在本文中，我們探討應用大型語言模型（LLMs）處理促進、管理和總結 Polis 參與結果的挑戰所涉及的機會和風險。特別是，我們通過使用 Anthropic 的 Claude 進行試驗來展示，LLMs確實可以增強人類智能，以幫助更有效地運行 Polis 對話。特別是，我們發現總結能力使得全新的方法具有巨大潛力，可以賦予公眾在集體意義創造練習中更大的力量。值得注意的是，LLM 的上下文限制對這些結果的洞察力和質量有顯著影響。然而，這些機會伴隨著風險。我們討論了其中一些風險，以及表徵和減輕這些風險的原則和技術，以及對可能使用LLMs的其他審議或政治系統的影響。最後，我們結論了幾個未來開放研究方向，以增強像 Polis 這樣的工具與LLMs的能力。

English

Polis is a platform that leverages machine intelligence to scale up deliberative processes. In this paper, we explore the opportunities and risks associated with applying Large Language Models (LLMs) towards challenges with facilitating, moderating and summarizing the results of Polis engagements. In particular, we demonstrate with pilot experiments using Anthropic's Claude that LLMs can indeed augment human intelligence to help more efficiently run Polis conversations. In particular, we find that summarization capabilities enable categorically new methods with immense promise to empower the public in collective meaning-making exercises. And notably, LLM context limitations have a significant impact on insight and quality of these results. However, these opportunities come with risks. We discuss some of these risks, as well as principles and techniques for characterizing and mitigating them, and the implications for other deliberative or political systems that may employ LLMs. Finally, we conclude with several open future research directions for augmenting tools like Polis with LLMs.

LLM（Large Language Models）在與 Polis 進行可擴展辯論的機會與風險

Opportunities and Risks of LLMs for Scalable Deliberation with Polis

摘要

Support