Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization

arXiv:2404.11531v1 Announce Type: new
Abstract: Fusing knowledge from multiple Large Language Models (LLMs) can combine their diverse strengths to achieve improved performance on a given task. However, current fusion approaches either rely on learning-based fusers that do not generalize to new LLMs, or do not take into account how well each LLM understands the input. In this work, we study LLM fusion at test-time, which enables leveraging knowledge from arbitrary user-specified LLMs during inference. We introduce Pack of LLMs (PackLLM), …

abstract arxiv cs.cl current diverse fusion however knowledge language language models large language large language models llms multiple optimization performance perplexity test type via