ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models

Summary: ContextCache: a context-aware semantic cache for multi-turn LLM dialogues that first retrieves vector-based candidates for the current query, then refines matches by self-attention over current and historical dialogue representations. Improves precision/recall over per-query caches on real conversations and delivers ~10× lower latency for cached responses, cutting LLM compute costs. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID: 14352
Venue: VLDB
Year: 2025
Pagerank: -
Overall Rank: 13,340 | 8.48%
DOI: 10.14778/3750601.3750679

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Jianxin Yan (Zhejiang University)
2. Wangze Ni (Zhejiang University)
3. Lei Chen (Hong Kong University of Science and Technology)
4. Xuemin Lin (Shanghai Jiao Tong University)
5. Peng Cheng (Tongji University)
6. Zhan Qin (Zhejiang University)
7. Kui Ren (Zhejiang University)

BibTeX Citation

@article{yan_vldb25,
        title = {{ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models}},
        author = {Yan, Jianxin and Ni, Wangze and Chen, Lei and Lin, Xuemin and Cheng, Peng and Qin, Zhan and Ren, Kui},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {12},
        pages = {5391--5394},
        doi = {10.14778/3750601.3750679},
        url = {https://doi.org/10.14778/3750601.3750679},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 0 of 0 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	7,332	Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQL	2025	VLDB
2	13,291	OrbitFlow: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration	2026	VLDB
3	10,459	From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation	2026	SIGMOD
4	10,663	Dialogue Benchmark Generation from Knowledge Graphs with Cost-Effective Retrieval-Augmented LLMs	2025	SIGMOD
5	6,432	RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference	2026	VLDB
6	10,290	Skyline Retrieval meets Set-Cover Chunk Merging: A Cost-Effective RAG-Sketch for Long-Context LLM QA	2026	SIGMOD
7	10,357	DepCache: A KV Cache Management Framework for GraphRAG with Dependency Attention	2026	SIGMOD
8	10,259	KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference	2026	SIGMOD
9	4,430	PQCache: Product Quantization-based KVCache for Long Context LLM Inference	2025	SIGMOD
10	2,816	Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation	2025	SIGMOD