HN Explorer

jneagu

↗ HN profile [ 51.3 ms ] full profile
Karma
3
Created
May 22, 2020 (6y ago)
Submissions
0
  1. Show HN: HalluMix – A Benchmark for Real-World LLM Hallucination Detection (huggingface.co)

    We built HalluMix to evaluate how well hallucination detectors perform in the kinds of messy, high-stakes environments where LLMs are actually deployed: long-form outputs, multi-document contexts, and domain-specific…

    4 points 0
  2. Cheating Automatic LLM Benchmarks (arxiv.org)
    3 points 0
  3. The promise and perils of synthetic data (techcrunch.com)
    3 points 0
  4. Show HN: Smell – A framework for aligning LLM evaluators to human feedback (quotientai.co)

    We've built SMELL (Subject-Matter Expert Language Liaison), a new framework that combines human expertise with LLMs to create feedback-informed, domain-specific LLM evaluators. One of the biggest issues with current…

    5 points 0
  5. Show HN: Quotient AI – Build better AI products fast (quotientai.co)
    1 points 1