Unverified50% confidenceBenchmarkExact time
Experiments on the TOFU and WMDP benchmarks show that UUE and UUE-L significantly outperform existing methods in unlearning effectiveness.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
11/16/2026
First Seen
Valid until: 2/14/2027
Sources
Related Entities
Related Claims
UnverifiedCurrent mainstream alignment techniques such as RLHF are often deeply coupled with improvements in model capability, making it technically difficult to fix alignment strictly without also improving capability.59% similarUnverifiedA large body of research has attempted to design smarter cache eviction strategies than LRU, such as deciding which cache entries to retain based on token importance, attention scores, or access frequency.59% similarUnverifiedWhen unlearning objectives designed for multi-step models are applied to few-step distilled (FSD) models, the unlearning effectiveness is significantly diminished.57% similarUnverifiedIn low-dimensional fine-tuning experiments on a math benchmark suite, LlMBO's fine-tuning gains matched or even exceeded those of GRPO, while using only a small fraction of the latter's compute and memory.56% similarUnverifiedExperimental results show that Warm-Start UCB outperforms all baseline methods under different memory budgets and history lengths.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1174465API
curl https://kongchang.com/api/v1/knowledge/claims/1174465MCP
get_claim(id=1174465)