Large language model (LLM) systems increasingly rely on techniques such as prefill-decode disaggregation, KV-cache offloading, and computation-communication overlap. These optimizations often treat GPU interconnects as best-effort substrates, overlooking contention across shared PCIe, NVLink, and RDMA fabrics. We chara...
Dan-Yang Chen, Yu-Feng Gu, Yibo Huang et al.· Proceedings of the 17th ACM...· 1 citation
Retrieval-augmented generation (RAG) grounds large language models in external sources, but retrieved passages often name the right entities without providing the facts needed to answer. Even when instructed to abstain, 12 generators answer 40.0-99.3% of insufficient-evidence questions. Training generators to abstain t...
This work proposes a controlled inject-and-remove cycle: deliberately inject a weaker backdoor and then unlearn it, which weakens detector-visible signatures and fools the backdoor detectors with an illusion of purification while preserving the malicious retrieval behavior.
Large language models (LLMs) increasingly rely on external sources when answering questions that require proprietary information or up-to-date live web content, through both traditional single-shot retrieval-augmented generation (RAG) and multi-turn agentic RAG. Yet today's web infrastructure is still built for human c...
Retrieval-augmented generation (RAG) depends on dense retrieval: each document is stored as a learned vector, and a query is answered by finding its nearest neighbors in that vector space. Keeping one full-precision vector per document is the dominant index cost at corpus scale, so retrieval systems replace each vector...
Closed source agent skills may encode proprietary instructions, scripts, constants, and data. Providers may offer their capabilities as services while keeping the underlying packages hidden. Prior work focuses on prompt injection attacks that directly disclose these artifacts, and existing defenses accordingly aim to p...
This shortlist short-circuits full-corpus cryptographic search without sacrificing retrieval quality: with 200-500 candidates, it closely matches full-corpus retrieval across five zero-shot corpora spanning 25K to 5.4M documents.
Pei-Chun Hua, Dan-Yang Chen, Ju-Nan Zhang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
