少样本与免训练的评论生成：基于对话式提示
Few-Shot and Training-Free Review Generation via Conversational Prompting
AI总结：
针对少样本和免训练场景下的个性化评论生成，提出对话式提示方法，通过将用户评论重构为多轮对话，显著提升生成评论与目标用户风格的一致性。
摘要：
个性化评论生成有助于企业理解用户偏好，然而大多数现有方法假设目标用户拥有大量的评论历史，或需要额外的模型训练。现实世界中的应用常常面临少样本和免训练的情境，即仅有少量用户评论可用且微调不可行。众所周知，大型语言模型（LLMs）能够应对此类低资源场景，但其效果依赖于提示工程。在本文中，我们提出了对话式提示（Conversational Prompting），一种将用户评论重构为多轮对话的轻量级方法。其简单变体——简单对话式提示（SCP）仅依赖用户自身的评论，而对比变体——对比对话式提示（CCP）则插入其他用户或LLMs的评论作为错误回复，并要求模型对其进行纠正，从而鼓励模型以用户的风格生成文本。在八个产品领域和五个LLMs上的实验表明，基于文本指标（如ROUGE-L和BERTScore）以及应用导向任务（如用户身份匹配和情感分析），传统的非对话式提示生成的评论往往与随机用户所写的评论相似。相比之下，SCP和CCP生成的评论都更接近目标用户的评论，即使每个用户仅有两条评论。当存在高质量负例时，CCP带来进一步改进，而SCP在无法收集此类数据时仍具竞争力。这些结果表明，对话式提示为少样本和免训练约束下的评论生成提供了一种实用解决方案。
英文摘要：
Personalized review generation helps businesses understand user preferences, yet most existing approaches assume extensive review histories of the target user or require additional model training. Real-world applications often face few-shot and training-free situations, where only a few user reviews are available and fine-tuning is infeasible. It is well known that large language models (LLMs) can address such low-resource settings, but their effectiveness depends on prompt engineering. In this paper, we propose Conversational Prompting, a lightweight method that reformulates user reviews as multi-turn conversations. Its simple variant, Simple Conversational Prompting (SCP), relies solely on the user's own reviews, while the contrastive variant, Contrastive Conversational Prompting (CCP), inserts reviews from other users or LLMs as incorrect replies and then asks the model to correct them, encouraging the model to produce text in the user's style. Experiments on eight product domains and five LLMs showed that the conventional non-conversational prompt often produced reviews similar to those written by random users, based on text-based metrics such as ROUGE-L and BERTScore, and application-oriented tasks like user identity matching and sentiment analysis. In contrast, both SCP and CCP produced reviews much closer to those of the target user, even when each user had only two reviews. CCP brings further improvements when high-quality negative examples are available, whereas SCP remains competitive when such data cannot be collected. These results suggest that conversational prompting offers a practical solution for review generation under few-shot and training-free constraints.
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。
