Unverified50% confidenceBenchmarkExact time
UC Berkeley 研究团队在 ToolBench 基准上发现，模型在复杂工具调用链中的幻觉率可达 15-30%
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/23/2026
First Seen
Valid until: 11/21/2026
Sources
Related Entities
Related Claims
Unverified哈佛大学Judson Brewer团队研究发现，经验丰富的冥想者与进入心流的创作者在神经影像上呈现高度相似的默认模式网络抑制模式61% similarUnverifiedThe idea of expectation-based localization (integral regression) was first proposed by Jian Sun's team at SenseTime in the task of human pose estimation.59% similarUnverifiedAnthropic researchers discovered a global workspace structure similar to that of the human brain inside the Claude large model using mechanistic interpretability methods.58% similarUnverified链式思考（CoT）由Wei等人于2022年提出，研究发现CoT能力在模型参数超过约100B时才显著涌现56% similarUnverified理解的错觉（解释深度的错觉）现象最早由认知科学家Rozenblit和Keil在2002年的研究中系统描述56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/792032API
curl https://kongchang.com/api/v1/knowledge/claims/792032MCP
get_claim(id=792032)