会员服务
Beyond Logprobs: A Multi-Signal Confidence Engine for LLM-Based Document Field Extraction
Arxiv
0+阅读 · 6月23日
A Benchmark for Hallucination Detection in VLMs for Gastrointestinal Endoscopy
Arxiv
0+阅读 · 6月23日
Anticipating the Optimism Gap: Predicting Distribution-Shift Degradation of RF-Impairment Detectors from In-Distribution Statistics
Arxiv
0+阅读 · 6月23日
DevoTG: Temporal Graph Neural Networks for Modeling C. elegans Developmental Connectomics
Arxiv
0+阅读 · 6月20日
Anticipating the Optimism Gap: Predicting Distribution-Shift Degradation of RF-Impairment Detectors from In-Distribution Statistics
Arxiv
0+阅读 · 6月20日
Amplify, Don't Create: Temporal Accumulation for Slow-Burn Prompt Injection
Arxiv
0+阅读 · 6月17日
Topological summaries of fingerprint ridge patterns carry identity information
Arxiv
0+阅读 · 6月20日
Five Queries Are Enough: Query-Efficient and Surrogate-Free Membership Inference Attacks on RAG via Entailment
Arxiv
0+阅读 · 6月21日
Catching Lies Without Sending the Video: Privacy-Preserving Multimodal Deception Detection
Arxiv
0+阅读 · 6月21日
When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents
Arxiv
0+阅读 · 6月22日
AI-Augmented Thyroid Scintigraphy for Robust Classification of Disease
Arxiv
0+阅读 · 6月19日
One Probe Won't Catch Them All: Towards Targeted Deception Detection
Arxiv
0+阅读 · 6月18日
Scoring Backends Matter More Than Pooling: A Systematic Study of Training-Free Anomalous Sound Detection under Domain Shift
Arxiv
0+阅读 · 6月17日
An Estimand-Focused Approach for AUC Generalization and Cross-Study Benchmarking
Arxiv
0+阅读 · 6月16日
When AUC Misleads: Polarization-Aware Evaluation of Deepfake Detectors under Domain Shift
Arxiv
0+阅读 · 6月17日
参考链接
微信扫码咨询专知VIP会员
Top