Qing Li
Publications
PolyUQuest: Verifiable Structure-Aware Web RAG over Heterogeneous Graphs
Existing retrieval-augmented generation (RAG) systems treat web pages as flat text, losing the structural and semantic signals encoded in HTML. We present PolyUQuest, a verifiable, structure-aware web RAG framework built on a heterogeneous graph that unifies hyperlink topology between pages, DOM hierarchy within pages, and entity-relation knowledge across pages. A two-tier router dispatches each query to one of three retrieval modes matched to its structural need, including direct block retrieval, cross-page graph traversal, and multi-hop entity reasoning. Every answer is fully verifiable, as each cited block carries its source page, heading path, and entity links so that users can trace any claim back to its structural evidence. We evaluate on the official websites of the Hong Kong Polytechnic University (PolyU), comprising 4,240 pages, 31,086 DOM blocks, 29,119 entities, and 37,680 relations, together with a multi-type evaluation benchmark. PolyUQuest outperforms existing RAG systems in answer correctness, coverage, and faithfulness, while consuming significantly fewer LLM tokens per query. The demonstration provides an interactive interface for inspecting cited answers, comparing retrieval traces across routing modes, and exploring evidence graph paths. PolyUQuest is being prepared for deployment as a student-facing QA service at PolyU.
From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs
Existing sparse attention and KV cache compression methods for long-context LLM inference typically apply fixed sparsity patterns or uniform budgets across all attention heads, overlooking the substantial variation in attention behavior among heads and contexts. We observe two distinct entropy patterns among attention heads: Rigid Heads, whose entropy stays near zero across input segments, and Dynamic Heads, whose entropy fluctuates significantly. Crucially, the distribution of these types is context-dependent and cannot be predetermined offline. We therefore propose EntropyInfer, a training-free framework that uses attention entropy to adaptively allocate compute at the granularity of individual heads and segments during prefilling. For decoding, we introduce a latent KV cache compression scheme that leverages generated output tokens, rather than prefill tokens alone, to identify and retain the most critical cache entries. Extensive experiments on Llama, Qwen and openPangu model series show that EntropyInfer consistently outperforms baselines including SnapKV, AdaKV, and CritiPrefill, achieving up to 2.39$\times$ end-to-end speedup beyond 100k tokens with minimal quality degradation compared to full attention. The code is released in https://github.com/SHA-4096/EntropyInfer.
Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions
Retrieval-augmented generation (RAG) significantly enhances large language models (LLMs) but introduces novel security risks through external knowledge access. While existing studies cover various RAG vulnerabilities, they often conflate inherent LLM risks with those specifically introduced by RAG. In this paper, we propose that secure RAG is fundamentally about the security of the external knowledge-access pipeline. We establish an operational boundary to separate inherent LLM flaws from RAG-introduced or RAG-amplified threats. Guided by this perspective, we abstract the RAG workflow into six stages and organize the literature around three trust boundaries and four primary security surfaces, including pre-retrieval knowledge corruption, retrieval-time access manipulation, downstream context exploitation, and knowledge exfiltration. By systematically reviewing the corresponding attacks, defenses, remediation mechanisms, and evaluation benchmarks, we reveal that current defenses remain largely reactive and fragmented. Finally, we discuss these gaps and highlight future directions toward layered, boundary-aware protection across the entire knowledge-access lifecycle.
GPU-Accelerated Algorithms for Graph Vector Search: Taxonomy, Empirical Study, and Research Directions
Approximate Nearest Neighbor Search (ANNS) underpins many large-scale data mining and machine learning applications, with efficient retrieval increasingly hinging on GPU acceleration as dataset sizes grow. Although graph-based approaches represent the state of the art in approximate nearest neighbor search, there is a lack of systematic understanding regarding their optimization for modern GPU architectures and their end-to-end effectiveness in practical scenarios. In this work, we present a comprehensive survey and experimental study of GPU-accelerated graph-based vector search algorithms. We establish a detailed taxonomy of GPU optimization strategies and clarify the mapping between algorithmic tasks and hardware execution units within GPUs. Through a thorough evaluation of six leading algorithms on eight large-scale benchmark datasets, we assess both graph index construction and query search performance. Our analysis reveals that distance computation remains the primary computational bottleneck, while data transfer between the host CPU and GPU emerges as the dominant factor influencing real-world latency at large scale. We also highlight key trade-offs in scalability and memory usage across different system designs. Our findings offer clear guidelines for designing scalable and robust GPU-powered approximate nearest neighbor search systems, and provide a comprehensive benchmark for the knowledge discovery and data mining community.