Introduces NCU metric using token log-probabilities and finds small language models match or outperform larger ones in strict factual RAG extraction, while commercial APIs show high prior dominance and negative transfer.
A survey on collaborative mechanisms between large and small lan- guage models.arXiv preprint arXiv:2505.07460
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Large Language Models (LLMs) deliver powerful AI capabilities but face deployment challenges due to high resource costs and latency, whereas Small Language Models (SLMs) offer efficiency and deployability at the cost of reduced performance. Collaboration between LLMs and SLMs emerges as a crucial paradigm to synergistically balance these trade-offs, enabling advanced AI applications, especially on resource-constrained edge devices. This survey provides a comprehensive overview of LLM-SLM collaboration, detailing various interaction mechanisms (pipeline, routing, auxiliary, distillation, fusion), key enabling technologies, and diverse application scenarios driven by on-device needs like low latency, privacy, personalization, and offline operation. While highlighting the significant potential for creating more efficient, adaptable, and accessible AI, we also discuss persistent challenges including system overhead, inter-model consistency, robust task allocation, evaluation complexity, and security/privacy concerns. Future directions point towards more intelligent adaptive frameworks, deeper model fusion, and expansion into multimodal and embodied AI, positioning LLM-SLM collaboration as a key driver for the next generation of practical and ubiquitous artificial intelligence.
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
RailVQA-bench supplies 21,168 QA pairs for ATO visual cognition while RailVQA-CoM combines large-model reasoning with small-model efficiency via transparent modules and temporal sampling.
HyPE integrates DRL mobility prediction, LLM-based UAV trajectory and inference assignment, and greedy heuristics for service placement and routing to jointly optimize latency, output fidelity, and personalization continuity in UAV-assisted 6G networks.
Triage routes coding tasks to cost-effective LLM tiers based on code quality metrics to maintain verification quality at lower cost.
The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle with equally sophisticated long outputs.
A systematic survey of LLM ensemble methods organized into a taxonomy of ensemble-before-inference, ensemble-during-inference, and ensemble-after-inference stages, with review of benchmarks, applications, and future directions.
citing papers explorer
-
Quantifying Prior Dominance in RAG Systems
Introduces NCU metric using token log-probabilities and finds small language models match or outperform larger ones in strict factual RAG extraction, while commercial APIs show high prior dominance and negative transfer.
-
RailVQA: A Benchmark and Framework for Efficient Interpretable Visual Cognition in Automatic Train Operation
RailVQA-bench supplies 21,168 QA pairs for ATO visual cognition while RailVQA-CoM combines large-model reasoning with small-model efficiency via transparent modules and temporal sampling.
-
Quality-Aware Personalized AI Service Provisioning in UAV-Assisted 6G Networks
HyPE integrates DRL mobility prediction, LLM-based UAV trajectory and inference assignment, and greedy heuristics for service placement and routing to jointly optimize latency, output fidelity, and personalization continuity in UAV-assisted 6G networks.
-
Triage: Routing Software Engineering Tasks to Cost-Effective LLM Tiers via Code Quality Signals
Triage routes coding tasks to cost-effective LLM tiers based on code quality metrics to maintain verification quality at lower cost.
-
A Survey of Context Engineering for Large Language Models
The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle with equally sophisticated long outputs.
-
Harnessing Multiple Large Language Models: A Survey on LLM Ensemble
A systematic survey of LLM ensemble methods organized into a taxonomy of ensemble-before-inference, ensemble-during-inference, and ensemble-after-inference stages, with review of benchmarks, applications, and future directions.