claim
Exposure bias in large language models creates compounding errors where a small factual inaccuracy or semantic drift at a specific position changes the conditioning context for subsequent positions, leading the model to generate statistically likely continuations based on erroneous premises.
Authors
Sources
- Hallucination Causes: Why Language Models Fabricate Facts mbrenndoerfer.com via serper
Referenced by nodes (2)
- Large Language Models concept
- exposure bias concept