Unverified50% confidenceFactExact time
DeidSharp runs a 26B-parameter mixture-of-experts (MoE) LLM locally, layered with deterministic pattern matching and a clinical named entity recognition (NER) model, using multi-detector voting to improve recall.
1
Sources
50%
Confidence
Long-term
Relevance
11/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLLM-Blender 通过训练专用排序模型 PairRanker 来评估多个 LLM 的候选输出并融合最优结果70% similarUnverified'Evaluator-guided LLM co-design' is a viable path to discovering new algorithmic structures; LLMs can extract structural patterns from cross-domain knowledge that human experts might overlook, and the evaluator provides a reliable screening mechanism.68% similarUnverifiedDNO-Prct uses an iterative process: in each round, online sampling is performed on the policy model, an LLM scores the samples together with the teacher model's golden answers, large-margin preference pairs are selected, and finally a DPO-style contrastive update is performed.67% similarUnverifiedDue to the stochasticity of large model outputs, evaluation practices commonly employ methods such as model scoring (LLM-as-Judge), human annotation, or reference-based semantic similarity.67% similarUnverifiedThe "is this chunk relevant?" task that the LLM judge is prompted to imitate is essentially the scoring function of a cross-encoder; replacing the LLM judge with a specialized reranker is usually the easiest migration win to achieve, because the two have exactly the same output form and the reranker's scores are calibrated.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1154375API
curl https://kongchang.com/api/v1/knowledge/claims/1154375MCP
get_claim(id=1154375)