REVIEW 4 cited by
SCALM: Towards Semantic Caching for Automated Chat Services with Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large Language Models (LLMs) have become increasingly popular, transforming a wide range of applications across various domains. However, the real-world effectiveness of their query cache systems has not been thoroughly investigated. In this work, we for the first time conducted an analysis on real-world human-to-LLM interaction data, identifying key challenges in existing caching solutions for LLM-based chat services. Our findings reveal that current caching methods fail to leverage semantic connections, leading to inefficient cache performance and extra token costs. To address these issues, we propose SCALM, a new cache architecture that emphasizes semantic analysis and identifies significant cache entries and patterns. We also detail the implementations of the corresponding cache storage and eviction strategies. Our evaluations show that SCALM increases cache hit ratios and reduces operational costs for LLMChat services. Compared with other state-of-the-art solutions in GPTCache, SCALM shows, on average, a relative increase of 63% in cache hit ratio and a relative improvement of 77% in tokens savings.
Forward citations
Cited by 4 Pith papers
-
Risk-Constrained Freshness-Aware Semantic Caching for Open-Web Retrieval-Augmented LLMs
A risk-gated three-tier semantic cache reuses open-web RAG results only when estimated staleness probability stays under per-tier budgets, cutting search cost while limiting stale answers.
-
Rethinking Caching for LLM Serving Systems: Beyond Traditional Heuristics
SISO caches representative centroid embeddings of similar queries and adjusts its similarity threshold under load, improving semantic cache hit ratios for LLM serving by up to 1.71x with a small accuracy cost.
-
Semantic Caching for Improving Web Affordability
Semantic image caching guided by large language models can cut web data transfer by roughly 10% beyond exact caching in simulations on 50 news sites.
-
An Ensemble Embedding Approach for Improving Semantic Caching Performance in LLM-based Systems
A small trained meta-encoder that combines two embedding models improves duplicate-query detection on QQP, but the evaluation is a classification benchmark rather than a real caching workload.
Discussion (0). Continue with ORCID to comment.