会员服务
Awal -- Community-Powered Language Technology for Tamazight
Arxiv
0+阅读 · 10月31日
LLM-Centric RAG with Multi-Granular Indexing and Confidence Constraints
Arxiv
0+阅读 · 10月30日
Systematic Absence of Low-Confidence Nighttime Fire Detections in VIIRS Active Fire Product: Evidence of Undocumented Algorithmic Filtering
Arxiv
0+阅读 · 10月28日
LLMs are Overconfident: Evaluating Confidence Interval Calibration with FermiEval
Arxiv
0+阅读 · 10月30日
FOCUS: Efficient Keyframe Selection for Long Video Understanding
Arxiv
0+阅读 · 10月31日
HyperClick: Advancing Reliable GUI Grounding via Uncertainty Calibration
Arxiv
0+阅读 · 10月31日
Kernel conditional tests from learning-theoretic bounds
Arxiv
0+阅读 · 10月31日
Personalized AI Scaffolds Synergistic Multi-Turn Collaboration in Creative Work
Personalized AI Scaffolds Synergistic Multi-Turn Collaboration in Creative Work
Arxiv
0+阅读 · 10月31日
Human-AI Complementarity: A Goal for Amplified Oversight
Arxiv
0+阅读 · 10月30日
Transferring Causal Effects using Proxies
Arxiv
0+阅读 · 10月29日
FESTA: Functionally Equivalent Sampling for Trust Assessment of Multimodal LLMs
Arxiv
0+阅读 · 10月30日
Metacognition and Confidence Dynamics in Advice Taking from Generative AI
Arxiv
0+阅读 · 10月30日
The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems
Arxiv
0+阅读 · 10月30日
To Rely or Not to Rely? Evaluating Interventions for Appropriate Reliance on Large Language Models
Arxiv
0+阅读 · 10月29日
Scalable Utility-Aware Multiclass Calibration
Arxiv
0+阅读 · 10月29日
参考链接
微信扫码咨询专知VIP会员
Top