09-17 [论文笔记] Hallucination Detection in LLMs with Topological Divergence on Attention Graphs (2026.07, ACL 2026)
09-05 [论文笔记] A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions (2024.11, ACM TOIS 2026)
07-18 [论文笔记] Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders (2026.02, ICLR 2026)
06-29 [论文笔记] Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models (2026.05)
06-29 [论文笔记] ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability (2025.01, ICLR 2025)
06-15 [论文笔记] Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking (2025.09, ACL 2025)
06-08 [论文笔记] VERA: Identifying and Leveraging Visual Evidence Retrieval Heads in Long-Context Understanding (2026.02)
06-08 [论文笔记] Retrieval Head Mechanistically Explains Long-Context Factuality (2024.04, ICLR 2025 Oral)
04-22 [论文笔记] FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling (2026.03)
04-22 [论文笔记] FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision (2024.07)