by karteeksai1
Uses Laya to assess RAG answer grounding and route responses to deliver, retry, or refuse
RAG pipeline with a hallucination guard: an open-source decision model (Laya) scores each LLM answer for grounding against retrieved context and decides to deliver, retry retrieval, or refuse. Built on Pinecone and SQuAD 2.0, and benchmarked against no guard and an LLM-as-judge.
Platforms
Related projects
laya
NandhaKishorM
Runs multilingual typed-decision models and provides routing, serving, and integration options
laya-mlx
mizorewww
Runs Laya typed-decision models locally on Apple Silicon using MLX
laya
convaiinnovations
A multilingual-ready System 1 model that returns calibrated typed decisions over text in one pass
laya-coreml
mizorewww
Runs Laya typed-decision models locally on Apple Silicon using Core ML and the Neural Engine
laya-multilingual
convaiinnovations
A multilingual System 1 model that returns calibrated typed decisions over text in one pass
openJev-verdict-2.0
Heman10x-NGU
Develops and benchmarks a non-autoregressive typed-decision model against Jev and Laya