English(EN) HarnessSQL Uses DeepSeek Harness to Lift an 8B Model to 45.2% on Spider 2.0-SQLite

港科大 HarnessSQL 将 8B 模型在 Spider 基准测试上提升至 45.2%

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-03 02:08

香港科技大学的研究人员开发了 HarnessSQL 系统，该系统在 DeepSeek Harness 框架内训练较小的语言模型。该方法成功地将一个 80 亿参数模型的在 Spider 2.0-SQLite 基准测试上的性能从 15.5% 提升到 45.2%，超过了得分约为 16% 的更大模型。该技术专注于有效提升小型模型在文本到 SQL 任务上的能力。 AI

影响展示了一种在文本到 SQL 等复杂任务上提高小型语言模型性能的有效方法。

排序理由大学实验室在特定基准测试上取得的研究里程碑。 [lever_c_demoted from research: ic=1 ai=1.0]

在 Pandaily 阅读 →

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

港科大 HarnessSQL 将 8B 模型在 Spider 基准测试上提升至 45.2%

本文如何被排名

Signal score: 7 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 大学实验室在特定基准测试上取得的研究里程碑。 [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: model release, product; 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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

Pandaily TIER_1 English(EN) · [email protected] (Pandaily) · 2026-11-03 02:08

HarnessSQL Uses DeepSeek Harness to Lift an 8B Model to 45.2% on Spider 2.0-SQLite

HKUST's HarnessSQL trains small models inside DeepSeek Harness, lifting an 8B model from 15.5% to 45.2% on Spider 2.0-SQLite and past 32B baselines that score about 16%.

本文如何被排名

报道来源 [1]

HarnessSQL Uses DeepSeek Harness to Lift an 8B Model to 45.2% on Spider 2.0-SQLite

相关实体

相关话题