Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks, but their long chain-of-thought trajectories incur substantial inference latency and computational cost. Small-large model collaborative reasoning mitigates this issue by offloading part of the reasoning steps to a small language model...
Yi-Bin Wang, Xiyu Liu, Xiao-Ying Jiang et al.· Proceedings of the 35th ACM...· 0 citations
CriticRouter is a verifier-free step-wise routing framework that reduces redundancy based on structural criticality as a routing signal, and achieves comparable accuracy to standard LLM reasoning while significantly reducing latency, demonstrating a better utility-efficiency trade-off.
Yi-Bin Wang, Xiyu Liu, Xiao-Ying Jiang et al.· Proceedings of the 35th ACM...· 0 citations
Hallucinations in knowledge-intensive tasks are frequent in Large Language Models (LLM). This is alleviated by Retrieval-Augmented Generation (RAG) and multi-agent systems, which include external knowledge and tools. Nevertheless, the consistency of retrieved evidence and the tracing of the pipeline in multifaceted int...
Xiyu Liu· ITM Web of Conferences· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.