AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
Common Sense Reasoning in NLP with Vered Shwartz - #461
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Do Languad Models Exhibit Reporting Bias?
The training corpus of the language model does depend on how it is trained. We did see some differences between models trained on micipedia and models strained on the web. The way that i was using language models to generate it is a bit debatable, because there's an issuethes which has been discussed in several papers. It might just mean that haven't found the correct phrasing to extract this knowledge. And t the effect that it's not consistent is also a problem because it means that in some cases you're youare going to generate the wrong answer.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode