Yonatan Bisk
@ybisk.me
Assistant Professor confused by the concept of consciousness but talkingtorobots.com in the meantime
3. How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models
^^ includes @skgabrie.bsky.social who is just starting up her lab at UCLA!
^^ includes @skgabrie.bsky.social who is just starting up her lab at UCLA!
November 10, 2024 at 6:34 PM
3. How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models
^^ includes @skgabrie.bsky.social who is just starting up her lab at UCLA!
^^ includes @skgabrie.bsky.social who is just starting up her lab at UCLA!
#EMNLP2024
1. Tools Fail: Detecting Silent Errors in Faulty Tools
Are you using tools with your LLMs? Are you assuming your tools are perfect? Assuming the LLM can just handle any errors for you? 😬
Danger… 🚨 Models trust tools over their own “knowledge” even for simple and well trained cases.
1. Tools Fail: Detecting Silent Errors in Faulty Tools
Are you using tools with your LLMs? Are you assuming your tools are perfect? Assuming the LLM can just handle any errors for you? 😬
Danger… 🚨 Models trust tools over their own “knowledge” even for simple and well trained cases.
November 10, 2024 at 6:34 PM
#EMNLP2024
1. Tools Fail: Detecting Silent Errors in Faulty Tools
Are you using tools with your LLMs? Are you assuming your tools are perfect? Assuming the LLM can just handle any errors for you? 😬
Danger… 🚨 Models trust tools over their own “knowledge” even for simple and well trained cases.
1. Tools Fail: Detecting Silent Errors in Faulty Tools
Are you using tools with your LLMs? Are you assuming your tools are perfect? Assuming the LLM can just handle any errors for you? 😬
Danger… 🚨 Models trust tools over their own “knowledge” even for simple and well trained cases.
