Unveiling Privacy Risks in LLM Agent Memory (2025 · 33 citations)
LLM agents often keep a long-term memory of earlier user queries paired with the solutions they produced, and they reuse these records as in-context examples.
Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective (2025 · 14 citations)
RAG systems often fail when the retrieved passages are misleading (for example, after PoisonedRAG-style injection of false answers) or only loosely related to the question. LLMs tend to trust such context over what they already know. The authors frame knowledge checking as four tasks:
Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach (2025 · 5 citations)
LLMs that receive retrieved passages, as in RAG, tend to trust that text too much. Misleading or off-topic passages can override knowledge the model already has. The authors define a "context-robust" LLM by four behaviours:

Co-authors here

12 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 26 times (of the 149,439 papers whose bibliographies we read); 7 citing papers with a page here →.

Updated 1 November 2026