SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
"连贯性" 相关文章
SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
Hybrid Dialogue State Tracking for Persian Chatbots: A Language Model-Based Approach
ID-RAG: Identity Retrieval-Augmented Generation for Long-Horizon Persona Coherence in Generative Agents
Evaluation & Hallucination Detection for Abstractive Summaries
This AI Paper from Amazon and Michigan State University Introduces a Novel AI Approach to Improving Long-Term Coherence in Language Models
10行代码让大模型数学提升20%，“野路子”研究谷歌也测上了，主要作者全靠自学成才
