返回全部动态
TAPR:利用任务感知提示重写器提升大语言模型性能
原标题:TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter
AI 摘要
arXiv 上发布了一篇题为 TAPR 的论文,提出了一种任务感知的提示重写器,利用强化学习(GRPO)和 LLM 作为评判者来优化用户提示,以提升下游大语言模型的性能。实验表明,在问答、摘要和算术推理等任务上,该方法能生成更清晰、更具指导性的提示,并在 Natural Questions 和 GSM8K 基准上取得更高准确率。
以上摘要由 AI 生成,可能存在误差。事实请以原文为准。
正文节选
Computer Science > Artificial Intelligence Title:TAPR: Enhancing LLM Performance with a Task-Aware Prompt Rewriter View PDF HTML (experimental) Abstract:Large Language Models (LLMs) often require carefully crafted prompts to unlock their full potential, which can be a barrier for non-expert users. This work addresses the challenge by introducing a Task-Aware Prompt Rewriter (TAPR), a model that reformulates user prompts into task-optimized prompts with the explicit goal of improving
发布时间:2026-08-03 12:00
抓取时间:2026-08-03 15:32
来源机构:arXiv