利用多方面 AI 反馈缓解情感支持对话中的无帮助性
Mitigating Unhelpfulness in Emotional Support Conversations with Multifaceted AI Feedback
AI总结：
针对情感支持模型可能生成适得其反回复的问题，提出模型无关框架 Muffin，通过多方面 AI 反馈评估与对比学习降低无帮助回复概率。
摘要：
情感支持对话系统旨在缓解用户的情绪困扰，并帮助他们应对自身挑战。为生成支持性回复，正如以往方法所确立的，必须考虑共情、支持策略和回复连贯性等多个因素。尽管如此，先前模型偶尔会生成无帮助的回复：这些回复本意是提供支持，却表现出适得其反的效果。根据心理学与传播学理论，仅在一个促成因素上表现不佳，就可能导致回复失去帮助作用。从模型训练角度看，由于这些模型在训练阶段未曾接触过无帮助回复，它们在推理时无法判断自己生成的 token 是否可能导致无帮助回复。为解决这一问题，我们提出了一个新颖的、与模型无关的框架，名为 mitigating unhelpfulness with multifaceted AI feedback for emotional support（Muffin）。具体而言，Muffin 使用多方面 AI 反馈模块，在综合考虑多个因素的情况下评估特定模型所生成回复的帮助性。随后，它利用对比学习，相较于有帮助回复，降低模型生成无帮助回复的可能性。实验结果表明，Muffin 有效缓解了无帮助回复的生成，同时略微提升了回复的流畅性和相关性。
英文摘要：
An emotional support conversation system aims to alleviate users' emotional distress and assist them in addressing their challenges. To generate supportive responses, it is critical to consider multiple factors such as empathy, support strategies, and response coherence, as established in prior methods. Nonetheless, previous models occasionally generate unhelpful responses, which intend to provide support but display counterproductive effects. According to psychology and communication theories, poor performance in just one contributing factor might cause a response to be unhelpful. From the model training perspective, since these models have not been exposed to unhelpful responses during their training phase, they are unable to distinguish if the tokens they generate might result in unhelpful responses during inference. To address this issue, we introduce a novel model-agnostic framework named mitigating unhelpfulness with multifaceted AI feedback for emotional support (Muffin). Specifically, Muffin employs a multifaceted AI feedback module to assess the helpfulness of responses generated by a specific model with consideration of multiple factors. Using contrastive learning, it then reduces the likelihood of the model generating unhelpful responses compared to the helpful ones. Experimental results demonstrate that Muffin effectively mitigates the generation of unhelpful responses while slightly increasing response fluency and relevance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
