English(EN) Text-to-SPARQL Generation with Reinforcement Learning: A GRPO-based Approach on DBLP

强化学习提升零样本文本到SPARQL生成能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-14 04:00

研究人员探索了使用强化学习进行零样本文本到SPARQL生成，这是知识图谱问答的关键任务。他们将Group-Relative Policy Optimization (GRPO)应用于Qwen3-1.7B模型，利用执行反馈和答案级奖励进行训练，无需金标准查询标注。研究发现，基于结果的奖励显著提高了性能，优于零样本基线，表明在缺乏完全监督的情况下，强化学习是一种可行的策略。 AI

影响展示了一种无需完全监督即可进行知识图谱问答的可行强化学习方法。

排序理由学术论文，详细介绍了使用强化学习进行文本到SPARQL生成的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 23 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了使用强化学习进行文本到SPARQL生成的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Jann Pfeifer, Debayan Banerjee, Ricardo Usbeck · 2026-09-14 04:00

基于GRPO的文本到SPARQL生成方法：一种强化学习的DBLP应用

arXiv:2605.20066v2 Announce Type: replace Abstract: Knowledge graph question answering seeks to translate natural language questions into executable queries over knowledge graphs, but existing approaches often rely on large models or full supervision in the form of gold query ann…

本文如何被排名

报道来源 [1]

基于GRPO的文本到SPARQL生成方法：一种强化学习的DBLP应用

相关实体

相关话题