疗法会话中LLM不参与临床决策，而是由含禁忌症的状态机驱动证据微实践，确保安全与深度。
Article URL: https://www.hamo.ai/blog/taking-the-clinical-decision-out-of-the-llm/ Comments URL: https://news.ycombinator.com/item?id=48916167 Points:…
LLM化身验证器，用证据链提升多跳推理的准确性与可信度
arXiv:2604.01993v2 Announce Type: replace-cross Abstract: Multi-hop QA benchmarks often reward Large Language Models (LLMs) for spurious correctness, …
颠覆认知：AI科学家的能力瓶颈不在模型，而在证据质量——药物估值的深层剖析
arXiv:2606.09556v1 Announce Type: new Abstract: AI Scientist agents are often evaluated as if capability were mainly a function of model quality, prom…
用LLM智能体实现高效、证据驱动的移动性预测，为轨迹建模提供新思路。
arXiv:2606.05130v1 Announce Type: cross Abstract: Individual-level mobility prediction is central to urban simulation, transportation planning, and po…
一种注册绑定的LLM管道，为热带植物、水生动物及异宠的性状提取提供可溯源证据，方法论严谨且跨物种适用。
arXiv:2606.00994v1 Announce Type: new Abstract: We describe a registry-bound large-language-model extraction pipeline producing evidence-grounded stru…
提出「证据驱动」评估新范式，让LLM法官告别模糊打分，生成可追溯的评分依据。
arXiv:2601.08654v2 Announce Type: replace-cross Abstract: Rubric-based text evaluation increasingly uses large language models (LLMs) as scalable judg…