从 Sierra 到 Jekka：AI 的边界、大规模实践与终点
"幻觉问题" 相关文章
Multi-Modal Fact-Verification Framework for Reducing Hallucinations in Large Language Models
Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context
Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context
MedTrust-RAG: Evidence Verification and Trust Alignment for Biomedical Question Answering
Credal Transformer: A Principled Approach for Quantifying and Mitigating Hallucinations in Large Language Models
CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement
Mitigating Hallucination in Multimodal Reasoning via Functional Attention Control
Multi-Source Knowledge Pruning for Retrieval-Augmented Generation: A Benchmark and Empirical Study
Hallucination is Inevitable for LLMs with the Open World Assumption
Hallucination is Inevitable for LLMs with the Open World Assumption
MaskCD: Mitigating LVLM Hallucinations by Image Head Masked Contrastive Decoding
Toward Causal-Visual Programming: Enhancing Agentic Reasoning in Low-Code Environments
DeFacto：用强化学习治愈AI幻觉，让多模态模型“有据可查”
Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality
百亿向量，毫秒响应：清华研发团队向量数据库 VexDB 首发，攻克模型幻觉难题
PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality
Making LLMs more accurate by using all of their layers
漫谈 MCP 构建之概念篇
Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
