Unverified50% confidenceFactExact time
TOFU (Task of Fictitious Unlearning) is a standard benchmark for evaluating machine unlearning, consisting of fictitious author question-answer pairs, used to test whether a model can forget a specified author while retaining the rest of its knowledge.
1
Sources
50%
Confidence
Long-term
Relevance
11/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe core of FuseAMC is a logistic regression meta-combiner that takes the concatenated class posterior probabilities of the two sub-models as input and is trained on a validation set disjoint from the test set.62% similarUnverifiedUnFlow 借鉴内容寻址(content-addressable)思想,通过对函数代码和参数组合进行哈希计算判断实验是否等价,从而实现自动去重61% similarVerifiedMachine Unlearning is an emerging research field focused on enabling AI systems to verifiably forget specific data.59% similarUnverifiedIn synthetic data review, 'residual reasoning traces' refer to the extraneous thinking process, draft-style analysis, or intermediate derivation text that the generating model attaches before outputting its final answer; 'persona leakage' refers to setting information that should be hidden being exposed in the dialogue, such as the model calling itself an AI assistant, mentioning the personas configuration, or directly repeating the system prompt content to the user.59% similarUnverifiedBefore having the model fill in entries, the representation of missing information (empty fields, explicit marking as 'unknown', model-generated guesses) must be clearly defined, otherwise 'completeness' becomes an incentive for the model to fabricate unfounded details.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1174466API
curl https://kongchang.com/api/v1/knowledge/claims/1174466MCP
get_claim(id=1174466)