Perplexity Decider 在 Vals AI 金融 ClaimBench 上达帕累托最优
Perplexity Decider pareto-optimal on Financial ClaimBench of Vals AI https://t.co/uBac0vOK15
AI 导读
Vals AI 发布面向决策模型的新基准 ClaimBench，测试模型能否判断一份金融文档是支持、反驳还是未涉及某项主张，共评估 15 个模型、1,960 条主张与 10-K 摘录配对，Decider V1.2 在决策模型中领先。Aravind Srinivas 转发称，Perplexity Decider 在该基准上达到帕累托最优。
查看原帖Today we’re releasing ClaimBench, our new benchmark targeted towards decision models. It tests whether a model can tell if a financial document supports, contradicts, or doesn’t address a claim. We evaluated 15 models on 1,960 claims paired with 10-K excerpts, with Decider V1.2 leading the pack of decision models.
正文
当前显示原文，中文全文译文尚未就绪。
Perplexity Decider pareto-optimal on Financial ClaimBench of Vals AI https://t.co/uBac0vOK15