Improving Interpersonal Communication by Simulating Audiences with Language Models

📄 arXiv: 2311.00687v2 📥 PDF

作者: Ryan Liu, Howard Yen, Raja Marjieh, Thomas L. Griffiths, Ranjay Krishna

分类: cs.AI, cs.CL, cs.HC, cs.LG

发布日期: 2023-11-01 (更新: 2023-11-03)

备注: 16 pages (main paper), 7 tables and figures (main)


💡 一句话要点

提出EGS框架以提升人际沟通效果

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 人际沟通 大型语言模型 探索生成模拟 沟通效果 受众模拟

📋 核心要点

  1. 现有沟通方法面临经验有限、偏见和推理困难等挑战,影响沟通效果。
  2. 提出的EGS框架通过模拟受众反应,探索多样化建议并生成候选发言,旨在提升沟通效果。
  3. 实验结果表明,EGS框架选择的候选在多个场景中优于传统生成机制,且与人类评审者意见一致性较高。

📝 摘要(中文)

我们如何与他人沟通以实现目标?我们利用以往经验或他人建议,或通过预测他人反应来构建候选发言。然而,经验有限且存在偏见,推理潜在结果也具有挑战性。本文探讨如何利用大型语言模型(LLM)模拟来改善沟通。我们提出了探索-生成-模拟(EGS)框架,该框架输入任何个体与目标受众沟通的场景。EGS(1)通过生成与场景相关的多样化建议来探索解决方案空间,(2)基于建议的子集生成沟通候选,(3)模拟不同受众的反应以确定最佳候选和建议。我们在八个场景中评估该框架,结果显示EGS选择的候选优于流行的生成机制,并且在五个场景中与人类评审者的意见高度一致。最后,我们展示了EGS在真实场景中的广泛适用性,表明其在目标导向沟通中的有效性和成果。

🔬 方法详解

问题定义:本文旨在解决人际沟通中因经验有限和推理困难导致的沟通效果不佳的问题。现有方法往往依赖于个人经验和直觉,缺乏系统性和多样性。

核心思路:EGS框架通过模拟受众反应,结合多样化建议生成候选发言,帮助用户更有效地进行目标导向的沟通。这种设计使得用户能够在复杂的沟通场景中获得更好的支持。

技术框架:EGS框架分为三个主要模块:探索模块生成与场景相关的建议,生成模块基于建议生成候选发言,模拟模块评估不同候选在受众中的反应。

关键创新:EGS框架的核心创新在于将大型语言模型应用于人际沟通的模拟,提供了一种系统化的方式来探索和生成沟通内容,与传统方法相比,具有更高的灵活性和适应性。

关键设计:在EGS框架中,建议生成采用多样性策略,确保覆盖不同的观点和反应;候选生成则基于条件生成技术,确保与建议的相关性;模拟模块则通过对比分析,确保选择的候选在实际应用中的有效性。

🖼️ 关键图片

fig_0
img_1

📊 实验亮点

实验结果显示,EGS框架选择的候选在八个场景中均优于传统生成机制,如Chain-of-Thought,且在五个场景中与人类评审者的意见一致性达到较高水平,展示了EGS在提升沟通效果方面的显著优势。

🎯 应用场景

该研究的潜在应用领域包括教育、心理咨询、商业谈判等,能够帮助用户在复杂的沟通场景中更有效地达成目标。EGS框架的应用可能会改变人们的沟通方式,提高决策效率,促进更好的社会互动。

📄 摘要(原文)

How do we communicate with others to achieve our goals? We use our prior experience or advice from others, or construct a candidate utterance by predicting how it will be received. However, our experiences are limited and biased, and reasoning about potential outcomes can be difficult and cognitively challenging. In this paper, we explore how we can leverage Large Language Model (LLM) simulations to help us communicate better. We propose the Explore-Generate-Simulate (EGS) framework, which takes as input any scenario where an individual is communicating to an audience with a goal they want to achieve. EGS (1) explores the solution space by producing a diverse set of advice relevant to the scenario, (2) generates communication candidates conditioned on subsets of the advice, and (3) simulates the reactions from various audiences to determine both the best candidate and advice to use. We evaluate the framework on eight scenarios spanning the ten fundamental processes of interpersonal communication. For each scenario, we collect a dataset of human evaluations across candidates and baselines, and showcase that our framework's chosen candidate is preferred over popular generation mechanisms including Chain-of-Thought. We also find that audience simulations achieve reasonably high agreement with human raters across 5 of the 8 scenarios. Finally, we demonstrate the generality of our framework by applying it to real-world scenarios described by users on web forums. Through evaluations and demonstrations, we show that EGS enhances the effectiveness and outcomes of goal-oriented communication across a variety of situations, thus opening up new possibilities for the application of large language models in revolutionizing communication and decision-making processes.