Closed ChenghaoMou closed 7 months ago
Yes, they are similar. Actually, our initial paper was presented around five months ago Factcheck-GPT: End-to-End Fine-Grained Document-Level Fact-Checking and Correction of LLM Output. Unfortunately, our paper isn't noticed by the Google and Stanford team, which you may see this discussion as an example: https://x.com/gregd_nlp/status/1773453723655696431 Compared with our initial version, we have mainly focused on its efficiency, with a 10X faster checking process without decreasing accuracy.
Thanks for all the details!
One weird detail I noticed is that in that Google paper, they are also using SERPER, a third party tool, for their OWN search API 🤷
In our implementation of SAFE, we use gpt-3.5-turbo-0125 as the language model and Serper (available at https://serper.dev/) as the Google Search API.
This project seems eerily similar to a recent paper: LONG-FORM FACTUALITY IN LARGE LANGUAGE MODELS. Is this a pure coincidence?