Unverified50% confidenceFactExact time
The hidden state steering experiments provide causal evidence that psycholinguistic factors such as commonness and distinctiveness are encoded inside the models, rather than being merely correlational observations.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
Unverified分词特征差异发生在推理链路底层，难以通过提示工程掩盖，可作为模型识别手段74% similarUnverifiedWhenever a model is intervened upon based on chain-of-thought observations, implicit pressure is applied that causes the model to hide its chain of thought.74% similarUnverifiedThe researchers conducted hidden state steering experiments on six models of 7-9B parameters, and shifting hidden states along the direction corresponding to each factor changed the models' judgments as expected.74% similarUnverifiedThe core method of the experiment is to fine-tune a small causal language model on a corpus that lies everywhere, and then observe how its confidence changes.74% similarUnverified单一 prompt 要求模型同时完成数据采集、模式发现、批判验证和结论收敛，往往导致幻觉叠加73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1079539API
curl https://kongchang.com/api/v1/knowledge/claims/1079539MCP
get_claim(id=1079539)