33 lines
1.2 KiB
Markdown
33 lines
1.2 KiB
Markdown
# Hallucination
|
|
|
|
## Definition
|
|
The phenomenon where an LLM generates information that appears plausible but is actually false, fabricated, or not grounded in its input or training data. The model "makes things up" with confidence, presenting fiction as fact.
|
|
|
|
## Key Statistics
|
|
- If a single model hallucinates 20% of the time
|
|
- 3 models hallucinating the exact same lie: 0.8% (0.2³ = 0.008)
|
|
- This mathematical property is the foundation of Consensus voting
|
|
|
|
## Causes
|
|
- Stochastic nature of LLM token generation
|
|
- Training data includes conflicting or incorrect information
|
|
- Model may lack specific knowledge but generates plausible substitutes
|
|
- Prompting that asks for creative or speculative content
|
|
|
|
## Impact on Multi-Agent Systems
|
|
- Errors propagate through agent topologies
|
|
- Can make entire system unreliable if not contained
|
|
- Multiple architectures address this: Consensus, Validator, etc.
|
|
|
|
## Mitigation
|
|
- [[Multi-Agent Consensus]] — majority voting cancels noise
|
|
- [[Validator]] checkpoints to catch errors
|
|
- Deterministic code validation where possible
|
|
- Don't anthropomorphize — force correctness architecturally
|
|
|
|
## Related Concepts
|
|
- [[Sycophancy]]
|
|
- [[Context Drift]]
|
|
- [[Multi-Agent Consensus]]
|
|
- [[Validator]]
|
|
- [[LLM Reliability Engineering]] |