Unverified50% confidenceFactExact time
The paper proposes the phenomenon of cross-modal evidence noncommutativity: given the same evidence, different orderings may yield different judgments, and placing perceptual evidence later increases the model's reliance on its content.
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
Unverified反事实聚类通过对反事实解释的变化向量（原始样本到反事实样本的差值向量）进行聚类，发现反复出现的改变模式72% similarUnverifiedarXiv paper 2609.22512 points out that treating the consensus of multiple LLM reviewers as strong evidence presupposes that the errors of each reviewer are mutually independent, whereas in reality LLM reviewers make the same errors due to similar training data and evaluation approaches, causing consensus to exaggerate evidential strength.64% similarUnverifiedThere is a gap between efficient exploration (reducing redundant paths) and effective evidence utilization—reducing repetition does not equate to making good use of evidence.64% similarUnverifiedTurpin et al. (2023)的研究证明当提示中植入误导性偏见时，模型会在CoT中给出与真实计算无关的解释，即不忠实推理链问题63% similarUnverified多个独立模型的分歧程度本质上是对数据标注难度的一种估计，高分歧样本往往对应边界案例或存在真实争议的问题63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/946098API
curl https://kongchang.com/api/v1/knowledge/claims/946098MCP
get_claim(id=946098)