Unverified50% confidenceBenchmarkExact time
The research conducted experiments on four datasets and five open-weight LLMs.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThis study models the data selection problem as a high-dimensional regression scenario with multiple heterogeneous data sources, and employs a weighted ridge regression estimator to fuse these sources.69% similarUnverifiedThe paper examined the impact of 4 context types on LLM reasoning results, finding that the form and scope of provided context significantly alters reasoning performance.66% similarUnverifiedLLM的每次调用可以被建模为伯努利试验，N次独立调用的通过次数服从二项分布B(N, p)66% similarUnverifiedThe key insight of this study is that when the likelihood function derived from the data model is known and differentiable, guided diffusion modeling can be used to sample the predictive distribution.66% similarUnverifiedLLM评测方法经历了从BLEU/ROUGE词汇重叠指标，到MMLU、HumanEval等离线静态基准，再到面向生产环境的实时动态评测的演变66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001304API
curl https://kongchang.com/api/v1/knowledge/claims/1001304MCP
get_claim(id=1001304)