x.comthreadRahul Sain (@RahulSain714) on X
Innodata open-sourced a toolkit and 14 accompanying datasets for benchmarking factuality and hallucination rates in LLMs, tested against models including Llama2 and Mistral. The toolkit is aimed at identifying input conditions that trigger problematic or hallucinated outputs, giving practitioners a reproducible way to probe model reliability.
TL;DR Innodata open-sources a toolkit and 14 datasets for benchmarking LLM factuality and hallucinations on models like Llama2 and Mistral.
Organisations named here
- Innodata
- Mistral
Technologies named here
- Llama2
- Innodata open-source toolkit
- Mistral
Related in evals
