causal
Training models to say I do not know
Accuracy improved by training models to decline answering when search snippets lack sufficient information, because LLMs are conditioned to always be helpful, and this cannot be solved with prompt engineering alone but required reprogramming and rewiring.
causalpending
Speaker
AravindEvidence Quote
“LLMs are conditioned to always be helpful, will always try to serve the user's query despite what it has access to”
Source
Aravind Srinivas - Building An Answer Engine - [Invest Like the Best, EP.363]— Invest Like the BestCreated: 11/14/2026, 5:47:28 AM
Your notes
Loading notes...