← 최신 프로덕트

LettuceDetect

Lightweight hallucination detector for RAG pipelines. Span-level grounding verification for RAG, code, and tool-grounded AI outputs. Hallucinations are still a major blocker for deploying reliable retrieval-augmented generation (RAG) systems, especially in complex domains like medical or legal.

오픈소스

619 스타 · GitHub외부 사이트

github.com 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. Open-source model and scorecard for measuring hallucinations in LLMs

    vectara.com

    This morning, we released a new Apache 2.0 licensed model on HuggingFace for detecting hallucinations in retrieval augmented generation (RAG) systems.

    Hacker News65점

  2. Halgorithem

    github.com

    Catching AI Hallucinations Using Trees, No AI in Pipeline

    Hacker News5점

  3. Traceloop (YC W23)

    traceloop.com

    Detecting LLM Hallucinations with OpenTelemetry

    Hacker News101점

  4. Nomadic

    news.ycombinator.com

    Minimize RAG Hallucinations with 1 Hyperparameter Experiment

    Hacker News95점

  5. Demystifying Advanced RAG Pipelines

    github.com

    An LLM-powered advanced RAG pipeline built from scratch

    Hacker News131점