English(EN)Commit or Abstain? System One Decision Models, LLMs, and Missing Legal Authority
System One决策模型在法律、临床和多模态AI任务中展现出潜力
作者PulseAugur 编辑部·[5 个来源]·
研究人员正在探索“System One”决策模型的应用，该模型源自大型语言模型，但侧重于输出校准后的概率而非生成文本，用于专业任务。一篇论文研究了其在法律AI中用于验证主张的应用，发现与生成式LLM相比，当不存在正确权威时，这些模型可以弃权，从而显著减少不正确的引用。另一项研究展示了一个通用的“Clinical System One”模型，该模型能有效地从患者记录中提取信息，性能优于更大的模型，并实现了小型决策模型与生成式AI之间的分工。第三篇论文提出通过System One决策机制使用通用的视觉-语言模型作为多模态重排器，该方法在极少的调整下就展现出与专用重排器相当或更优的性能。
AI
arXiv:2610.29961v1 Announce Type: cross Abstract: Given the enormous number of claims to be checked, verifiable legal AI requires scalable, cost-effective models that answer the practical needs of law. System One decision models are built on large language models but, instead of …
Given the enormous number of claims to be checked, verifiable legal AI requires scalable, cost-effective models that answer the practical needs of law. System One decision models are built on large language models but, instead of generating text, return a calibrated probability f…
arXiv cs.AI
TIER_1English(EN)·Andrew Zhang, Trinh T. L. Vuong, Sophia J. Wagner, Dongmin Bang, Tong Ding, Yuchang Su, Mary Cipperman, Christina S. Chen, Judith Lefkes, Ramin Kahidi, Ming Y. Lu, Caiwei Tian, Tianhao Luo, Jingnan Ma, Rowland Pettit, Long Phi Le, Faisal Mahmood·
arXiv:2610.27099v1 Announce Type: new Abstract: Clinical care, health-system operations and biomedical discovery depend on extracting reliable answers from patient records, yet applying diverse clinical questions across entire populations remains computationally expensive. Here w…
Multimodal rerankers are usually dedicated models: a vision-language model (VLM) is trained on retrieval data to score the candidates of a query. Scoring options is not specific to reranking. System One decision models such as Jev map a state and a typed question to one probabili…
A general vision-language model can serve as a multimodal reranker via single-pass choice questions, matching or exceeding dedicated rerankers with minimal tuning.
