会员服务
Transferring Extreme Subword Style Using Ngram Model-Based Logit Scaling
Arxiv
0+阅读 · 3月11日
Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents
Arxiv
0+阅读 · 3月11日
Reducing Large Language Model Safety Risks in Women's Health using Semantic Entropy
Arxiv
0+阅读 · 3月1日
Unifying Perplexing Behaviors in Modified BP Attributions through Alignment Perspective
Arxiv
0+阅读 · 3月14日
Adversarial Decoding: Generating Readable Documents for Adversarial Objectives
Arxiv
0+阅读 · 3月6日
Beyond Natural Language Perplexity: Detecting Dead Code Poisoning in Code Generation Datasets
Arxiv
0+阅读 · 2月28日
What is Wrong with Perplexity for Long-context Language Modeling?
Arxiv
0+阅读 · 3月4日
What is Wrong with Perplexity for Long-context Language Modeling?
Arxiv
0+阅读 · 3月2日
Fine-tuning can Help Detect Pretraining Data from Large Language Models
Arxiv
0+阅读 · 3月17日
DataMan: Data Manager for Pre-training Large Language Models
Arxiv
0+阅读 · 3月13日
Optimization-based Prompt Injection Attack to LLM-as-a-Judge
Arxiv
0+阅读 · 3月3日
Beyond Natural Language Perplexity: Detecting Dead Code Poisoning in Code Generation Datasets
Arxiv
0+阅读 · 2月27日
Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models
Arxiv
0+阅读 · 2月26日
DataMan: Data Manager for Pre-training Large Language Models
Arxiv
0+阅读 · 2月26日
Architectural Fusion Through Contextual Partitioning in Large Language Models: A Novel Approach to Parameterized Knowledge Integration
Arxiv
0+阅读 · 1月22日
参考链接
微信扫码咨询专知VIP会员
Top