"When to Speak, When to Abstain: Contrastive Decoding with Abstention"

Teaching LLMs the art of knowing their knowledge boundaries

LLMs struggle with reliability when they lack knowledge, leading to hallucinations. This paper introduces Contrastive Decoding with Abstention (CDA), enabling models to either generate accurate responses or abstain when uncertain.

https://arxiv.org/abs/2412.12527

🔧 Solution in this Paper:

→ Contrastive Decoding with Abstention (CDA) evaluates knowledge relevance for each query through uncertainty calibration, determining which knowledge source to prioritize

→ The method uses momentum-based weight adjustments to prevent sudden attention shifts during generation

→ CDA incorporates an abstention distribution when no relevant knowledge is available

→ The system dynamically balances between parametric knowledge (learned during training) and contextual knowledge (external information)

-----

💡 Key Insights:

→ Models need explicit mechanisms to recognize knowledge gaps

→ Uncertainty calibration is crucial for reliable knowledge assessment

→ Momentum helps prevent attention shifts that cause hallucinations

→ Training-free decoding methods can effectively improve model reliability

-----

📊 Results:

→ Tested on 4 LLMs including Llama3 8B and Mistral 7B

→ Achieved 72.84% F1 score on answerable queries

→ Demonstrated 55.63% F1 score on abstention cases

→ Showed consistent performance improvements across all tested models