Retired

Lynx

The LLM evaluation platform documented on this site is retired and no longer offered. Lynx is retired as a product. The research paper stays public on patronus.ai.

Patronus AI is a research lab developing training data and simulated environments for frontier AI. Its work spans reinforcement learning environments and digital world models for agents operating in software.

Detecting hallucinations in retrieval-augmented generation

Lynx is an open-source model for detecting hallucinations in retrieval-augmented generation, evaluated on HaluBench, a benchmark of 15,000 samples. The paper introduces both, with HaluBench sourced from various real-world domains.

Where to find the paper

Read it on arXiv (opens in a new tab) or as a PDF (opens in a new tab). The current home for Lynx is its research page on patronus.ai (opens in a new tab).

Lynx: An Open Source Hallucination Evaluation Model

Selvan Sunitha Ravi, Bartosz Mielczarek, Anand Kannappan, Douwe Kiela, Rebecca Qian. Jul 11, 2024.

Selvan Sunitha Ravi, Bartosz Mielczarek, Anand Kannappan, Douwe Kiela, Rebecca Qian. Lynx: An Open Source Hallucination Evaluation Model. arXiv:2407.08488, 2024.