通过模拟对话双方推理，实现无需训练的可控文本生成。
RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework
- 基于对话双方角色的递归推理机制控制文本属性。
- 在多种模型上实现强属性控制且保持语言流畅性。
- 自适应理性参数可随上下文自动调节控制强度。
尽管自然语言生成取得显著进展，但控制语言模型生成具有特定属性的文本仍面临挑战。本文提出RSA-Control，一种基于语用学的无训练可控文本生成框架。该框架通过模拟虚拟说话者与听者的递归推理过程，提升目标属性在干扰信息下的正确解读概率。此外，引入自适应理性参数，可根据上下文自动调节控制强度。在两种任务类型和两种语言模型上的实验表明，RSA-Control在保持语言流畅性和内容一致性的同时，实现了强大的属性控制能力。代码已开源：https://github.com/Ewanwong/RSA-Control。
原文摘要 · Abstract (English)
Despite significant advancements in natural language generation, controlling language models to produce texts with desired attributes remains a formidable challenge. In this work, we introduce RSA-Control, a training-free controllable text generation framework grounded in pragmatics. RSA-Control directs the generation process by recursively reasoning between imaginary speakers and listeners, enhancing the likelihood that target attributes are correctly interpreted by listeners amidst distractors. Additionally, we introduce a self-adjustable rationality parameter, which allows for automatic adjustment of control strength based on context. Our experiments, conducted with two task types and two types of language models, demonstrate that RSA-Control achieves strong attribute control while maintaining language fluency and content consistency. Our code is available at https://github.com/Ewanwong/RSA-Control.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。