会员服务
The Professor: Multi-Teacher Unsupervised Prompt Distillation for Vision-Language Models
Arxiv
0+阅读 · 6月22日
VeryTrace: Verifying Reasoning Traces through Compilable Formalism and Structured Verification
Arxiv
0+阅读 · 6月23日
On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners
Arxiv
0+阅读 · 6月22日
MAS-PromptBench: When Does Prompt Optimization Improve Multi-Agent LLM Systems?
Arxiv
0+阅读 · 6月22日
MedP-CLIP: Medical CLIP with Region-Aware Prompt Integration
Arxiv
0+阅读 · 6月23日
LLMs Prompted for Legal Context Object More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context
LLMs Prompted for Legal Context Object More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context
Arxiv
0+阅读 · 6月23日
Pigeonholing: Bad prompts hurt models to collapse and make mistakes
Arxiv
0+阅读 · 6月23日
Collecting Prosody in the Wild: A Content-Controlled, Privacy-First Smartphone Protocol and Empirical Evaluation
Arxiv
0+阅读 · 6月22日
Stabilizing Black-Box Prompt Optimization with Textual Regularization and Signal Aggregation
Arxiv
0+阅读 · 6月23日
AdversaBench: Automated LLM Red-Teaming with Multi-Judge Confirmation and Cross-Model Transferability
AdversaBench: Automated LLM Red-Teaming with Multi-Judge Confirmation and Cross-Model Transferability
Arxiv
0+阅读 · 6月23日
Bridging Mechanistic Interpretability and Prompt Engineering with Gradient Ascent for Interpretable Persona Control
Arxiv
0+阅读 · 6月23日
On the Stability of Prompt Ranking in Large Language Model Evaluation
Arxiv
0+阅读 · 6月23日
When Helpfulness Overrides Causal Caution: Context-Dependent Suppression and Recovery in LLMs
Arxiv
0+阅读 · 6月23日
Project Ariadne: Prompt-Conditioned Route Generation for Synthesis Planning
Arxiv
0+阅读 · 6月23日
PCB-QA: Evaluating LLMs over the First Printed Circuit Board Design Question-Answer Dataset
Arxiv
0+阅读 · 6月10日
参考链接
微信扫码咨询专知VIP会员
Top