ReALM：参考解析作为语言建模

摘要

指代消解是一个重要问题，对于理解和成功处理各种上下文至关重要。这些上下文既包括之前的对话轮次，也涉及与非对话实体相关的背景信息，例如用户屏幕上的实体或后台运行的实体。尽管大语言模型（LLMs）在多种任务中展现出极强的能力，但在指代消解，尤其是非对话实体的指代消解方面，其应用仍未得到充分开发。本文展示了如何利用LLMs构建一个极其有效的系统来解决各类指代问题，通过展示如何将指代消解转化为一个语言建模问题，尽管涉及屏幕上的实体等形式，这些实体传统上并不易于简化为纯文本模式。我们在不同类型的指代消解上，相较于现有具备类似功能的系统，展示了大幅度的改进，其中最小的模型在屏幕指代上获得了超过5%的绝对提升。我们还与GPT-3.5和GPT-4进行了基准测试，我们的最小模型达到了与GPT-4相当的性能，而更大规模的模型则显著超越了GPT-4。

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：参考解析作为语言建模

ReALM: Reference Resolution As Language Modeling

摘要

Summary

Support

Support