Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack — mentioned by pesenti

Thu, 07 May 2020 14:10:48 GMT

The team put a lot of effort on dialog safety. You can find more info here: https://parl.ai/projects/dialogue_safety/ and the paper here: https://arxiv.org/abs/1908.06083. Still, unlike Tay, we purposely did not create a service for it and do not advise creating one. This is for research purpose only and more effort needs to be made on safety before it can me more broadly consumed.

Paper and discussion history. A mention is not an endorsement.

Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack · HackerPapers discussions

Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack — mentioned by pesenti