Sbert
PulseAugur coverage of Sbert — every cluster mentioning Sbert across labs, papers, and developer communities, ranked by signal.
2 天有情绪数据
-
LLM Agent 工具调用流量检测框架采用图神经网络
研究人员开发了一个新颖的框架，用于检测大型语言模型 (LLM) Agent 的工具调用流量中的攻击。该系统将 Agent 会话表示为图，并结合工具参数和响应的句子嵌入特征来将流量分类为良性或恶意。研究发现，内容级特征对于有效检测至关重要，其性能显著优于仅使用元数据的方法，并指出了一个可能夸大性能指标的常见评估陷阱。
-
Developer builds VORTEXRAG to fix RAG failures
A developer spent six months debugging a Retrieval-Augmented Generation (RAG) system for document Q&A, identifying two key failure modes: semantic drift in query reformulation and context poisoning by irrelevant but sim…
-
ONNX framework speeds up Sentence-BERT inference
This article explores how the ONNX framework can accelerate inference times for Sentence-BERT (SBERT) models, which are commonly used for generating sentence embeddings. The author demonstrates this by converting the `a…
-
Sentra-Guard system achieves 99.96% detection rate against adversarial LLM prompts
Researchers have developed Sentra-Guard, a real-time system designed to defend against adversarial prompts targeting large language models. The system employs a hybrid approach combining semantic embeddings with transfo…