↓Skip to main content

🏢 Rice University

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
·3774 words·18 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Large Language Models 🏢 Rice University
LLMs survey: Model, output, and prompt-based strategies for efficient reasoning, mitigating ‘overthinking’ for faster, cheaper, and real-world applications.
Rethinking Diverse Human Preference Learning through Principal Component Analysis
·2799 words·14 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Large Language Models 🏢 Rice University
Decomposed Reward Models (DRMs) extract diverse human preferences from binary comparisons using PCA, enabling flexible and interpretable LLM alignment.