decoding strategy
- Alleviating Hallucinations in Large Language Models through Multi-Model Contrastive Decoding and Dynamic Hallucination Detection
- IGD: Token Decisiveness Modeling via Information Gain in LLMs for Personalized Recommendation
- L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models
- Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models