会员服务
Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot
Arxiv
0+阅读 · 1月8日
Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?
Arxiv
0+阅读 · 1月8日
Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
Arxiv
0+阅读 · 1月8日
ConMax: Confidence-Maximizing Compression for Efficient Chain-of-Thought Reasoning
Arxiv
0+阅读 · 1月8日
Chain-of-Thought as a Lens: Evaluating Structured Reasoning Alignment between Human Preferences and Large Language Models
Arxiv
0+阅读 · 1月7日
LaST$_{0}$: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model
Arxiv
0+阅读 · 1月8日
MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation
Arxiv
0+阅读 · 1月7日
CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval
Arxiv
0+阅读 · 1月7日
Chain-of-Sanitized-Thoughts: Plugging PII Leakage in CoT of Large Reasoning Models
Arxiv
0+阅读 · 1月8日
Investigating CoT Monitorability in Large Reasoning Models
Arxiv
0+阅读 · 1月7日
VISTA: Mitigating Semantic Inertia in Video-LLMs via Training-Free Dynamic Chain-of-Thought Routing
Arxiv
0+阅读 · 1月7日
FLEx: Language Modeling with Few-shot Language Explanations
Arxiv
0+阅读 · 1月7日
Post-Training Quantization of OpenPangu Models for Efficient Deployment on Atlas A2
Arxiv
0+阅读 · 1月8日
SCoTER: Structured Chain-of-Thought Transfer for Enhanced Recommendation
Arxiv
0+阅读 · 1月8日
EntroCoT: Enhancing Chain-of-Thought via Adaptive Entropy-Guided Segmentation
Arxiv
0+阅读 · 1月7日
参考链接
微信扫码咨询专知VIP会员
Top