ReALM：參考解析作為語言建模

摘要

參考消解是一個重要的問題，對於理解和成功處理各種不同類型的語境至關重要。這些語境包括先前的對話轉折和涉及非對話實體的語境，例如用戶螢幕上的實體或在背景運行的實體。儘管長文本模型已被證明在各種任務中非常強大，但它們在參考消解方面的應用，特別是對於非對話實體，仍然被低估。本文展示了如何利用長文本模型來創建一個極其有效的系統來解決各種類型的參考，方法是將參考消解轉換為語言建模問題，儘管牽涉到螢幕上的實體等傳統上不易納入僅限於文本模式的形式。我們展示了相對於現有具有相似功能的系統，我們的最小模型在不同類型的參考中取得了絕對增益，螢幕上的參考增益超過5%。我們還與GPT-3.5和GPT-4進行了基準測試，我們的最小模型實現了與GPT-4相當的性能，而我們的較大模型則明顯優於它。

English

Reference resolution is an important problem, one that is essential to understand and successfully handle context of different kinds. This context includes both previous turns and context that pertains to non-conversational entities, such as entities on the user's screen or those running in the background. While LLMs have been shown to be extremely powerful for a variety of tasks, their use in reference resolution, particularly for non-conversational entities, remains underutilized. This paper demonstrates how LLMs can be used to create an extremely effective system to resolve references of various types, by showing how reference resolution can be converted into a language modeling problem, despite involving forms of entities like those on screen that are not traditionally conducive to being reduced to a text-only modality. We demonstrate large improvements over an existing system with similar functionality across different types of references, with our smallest model obtaining absolute gains of over 5% for on-screen references. We also benchmark against GPT-3.5 and GPT-4, with our smallest model achieving performance comparable to that of GPT-4, and our larger models substantially outperforming it.

ReALM：參考解析作為語言建模

ReALM: Reference Resolution As Language Modeling

摘要

Summary

Support

Support