Unverified50% confidenceOpinionExact time
In zero-shot scenarios, when labeled data is lacking, decision models like Jev still have value.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/29/2026
First Seen
Valid until: 1/27/2027
Sources
Related Entities
Related Claims
VerifiedZero retention does not equal zero learning—the fact that data is not stored does not mean that patterns and information extracted from it will not influence the model in some form72% similarUnverifiedJev does not generate content; it only returns selections, scores, and probabilities for programs to make decisions.71% similarUnverifiedReplacing the forget set labels with zero causes the model to learn to predict those samples as class 0, and modifying labels is a different thing from eliminating the influence of samples.68% similarUnverifiedJev officially claims to output probabilities over a constrained option set, perform no autoregressive generation, be incapable of producing illegal categories, and support label definition at inference time.66% similarUnverifiedThe charts and data tables shown in the article are all from the base model with no LoRA adapters attached, i.e., purely zero-shot results.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1111875API
curl https://kongchang.com/api/v1/knowledge/claims/1111875MCP
get_claim(id=1111875)