arXiv AI
SKIP: a Self-knowledge-guided Step-wise Preference Learning Framework for Concise Reasoning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 25
ChainPrune: Evaluating and Reducing Redundancy in Long Chain-of-Thought Reasoning
arXiv:2608.21860v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) reasoning has significantly enhanced the multi-step problem-solving capabilities of large language models (LLMs) by introducin...
arXiv AI
Jul 28
Learning When to Reason for Text-to-SQL via SFT and DPO
arXiv:2607. 22622v1 Announce Type: cross Abstract: Recent Text-to-SQL methods rely heavily on reasoning-centric paradigms such as Chain-of-Thought (CoT), achieving substantial gains on complex benchmarks at the cost of high inference-time overhead.
arXiv Machine Learning
Aug 3
TELLER: Dual-Path Iterative Preference Optimization for Table Entity Linking
arXiv:2607. 28680v1 Announce Type: cross Abstract: Entity linking in tables matches short and ambiguous cell mentions to their corresponding knowledge-base entities.
arXiv AI
Aug 12
Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging
arXiv:2608. 10447v1 Announce Type: cross Abstract: Large language model-based recommender systems are increasingly adopting slow-thinking models that generate step-by-step reasoning before making predictions, often achieving higher accuracy than fast-thinking models that predict directly.
Hugging Face Trending Papers
Aug 11
Towards Efficient Reasoning in LLM-Based Recommender Systems via Model Merging
Large language model-based recommender systems are increasingly adopting slow-thinking models that generate step-by-step reasoning before making predictions, often achieving higher accuracy than fast-thinking models that predict directly. However, their reasoning traces are often unnecessarily verbose, increasing inference costs without commensurate accuracy gains.
arXiv AI
Jul 13
HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs
arXiv:2604. 20140v2 Announce Type: replace Abstract: Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks.