Feedback Distillation: A New Training Method for Improving LLM Reasoning in Theorem Proving
Post-training for reasoning models typically combines supervised fine-tuning with reinforcement learning from verifiable rewards, most commonly with GRPO. However, this algorithm suffers from sparse…
Read the full articleYou might also wanna read
DOPD: A Dual On-policy Distillation Method to Address Privilege Illusion in LLM and VLM Training
On-policy distillation (OPD) offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals. T
arxiv.org·17d ago
Can We Trust LLM's Logic? Quantifying Uncertainty, Coherence, and Robustness via a Graph-Based Framework
arXiv:2607.08017v1 Announce Type: new Abstract: Large-Language Models (LLMs) can be prone to flawed and unfaithful reasoning that decoding s
Proxy-KD: A Novel Method for Knowledge Distillation from Black-Box Large Language Models
Given the exceptional performance of proprietary large language models (LLMs) like GPT-4, recent research has increasingly focused on boosti
arxiv.org·18d ago
SPIRAL: A Reinforcement Learning Framework for Multi-Primitive Language Model Reasoning
Language model reasoning can be substantially improved at test time via scaffolds that scale inference compute across different primitives -
arxiv.org·20d agoJust Keep Prompting: Evaluating Repetitive Socratic Prompting in VLMs
arXiv:2607.14099v1 Announce Type: cross Abstract: Deploying Vision-Language Models (VLMs) in real-world settings requires not only strong vi
Comprehensive Survey of Reasoning Failures in Large Language Models
Large Language Models (LLMs) have exhibited remarkable reasoning capabilities, achieving impressive results across a wide range of tasks. De
arxiv.org·4mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.