会员服务
Fixed Budget is No Harder Than Fixed Confidence in Best-Arm Identification up to Logarithmic Factors
Arxiv
0+阅读 · 2月18日
Eigenmood Space: Uncertainty-Aware Spectral Graph Analysis of Psychological Patterns in Classical Persian Poetry
Arxiv
0+阅读 · 2月18日
Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation
Arxiv
0+阅读 · 2月18日
RAPID: Risk of Attribute Prediction-Induced Disclosure in Synthetic Microdata
Arxiv
0+阅读 · 2月9日
Unveiling the "Fairness Seesaw": Discovering and Mitigating Gender and Race Bias in Vision-Language Models
Arxiv
0+阅读 · 2月11日
On Calibration of Large Language Models: From Response To Capability
Arxiv
0+阅读 · 2月14日
Evaluating and Calibrating LLM Confidence on Questions with Multiple Correct Answers
Arxiv
0+阅读 · 2月8日
Evolving Multi-Channel Confidence-Aware Activation Functions for Missing Data with Channel Propagation
Arxiv
0+阅读 · 2月14日
No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes
Arxiv
0+阅读 · 2月9日
Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models
Arxiv
0+阅读 · 2月11日
Advancing Block Diffusion Language Models for Test-Time Scaling
Arxiv
0+阅读 · 2月10日
Advancing Block Diffusion Language Models for Test-Time Scaling
Arxiv
0+阅读 · 2月11日
When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation
Arxiv
0+阅读 · 2月13日
When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation
Arxiv
0+阅读 · 2月12日
AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection
Arxiv
0+阅读 · 2月12日
参考链接
微信扫码咨询专知VIP会员
Top