用小型语言模型辅助大规模人机交互文献筛选，提升效率且发现遗漏论文。
Charting the Growth of Social-Physical HRI (spHRI): A Systematic Review Pipeline Augmented by Small Language Models
- 采用参数小于15亿的小型语言模型，本地运行加速论文标题摘要筛查。
- 集成模型发现39篇被人工漏筛的论文，占最终数据集的10.29%。
- 适合需要高效开展大规模系统综述的研究者或团队使用。
社交物理人机交互（spHRI）在机器人学、人机交互及触觉等领域迅速发展，但术语碎片化与方法不一致导致系统性综述困难。为支持可扩展的综述实践，我们评估了小型语言模型（SLMs；<1.5B参数）在大型spHRI系统综述中用于标题与摘要筛选的效果。尽管无SLM能达到人类评审员的性能，但其可在本地运行，筛查速度比人工快数个数量级。联合使用的SLM集成模型识别出39篇人工遗漏的论文，占最终相关数据集的10.29%。结果表明，SLMs可增强而非替代专家评审员，使大规模文献综述更具可访问性与可持续性。
原文摘要 · Abstract (English)
Social-physical human-robot interaction (spHRI) has grown rapidly across robotics, human-computer interaction, human-robot interaction, and haptics. Yet, fragmented terminology and inconsistent methodologies make systematic synthesis difficult. To support scalable review practices, we evaluated the extent to which small language models (SLMs; < 1.5B parameters) can assist with title and abstract screening for a large spHRI systematic review. While no SLMs matched human reviewers' performance, the models operated locally and screened papers orders of magnitude faster. The combined SLM ensemble identified 39 papers reviewers missed, representing 10.29% of the final relevant dataset. These results demonstrate that SLMs can augment, rather than replace, expert reviewers and make large-scale literature reviews accessible and sustainable.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。