Towards Practical Tool Usage for Continually Learning LLMs

arXiv:2404.09339v1 Announce Type: cross
Abstract: Large language models (LLMs) show an innate skill for solving language based tasks. But insights have suggested an inability to adjust for information or task-solving skills becoming outdated, as their knowledge, stored directly within their parameters, remains static in time. Tool use helps by offloading work to systems that the LLM can access through an interface, but LLMs that use them still must adapt to nonstationary environments for prolonged use, as new tools can emerge …

abstract arxiv cs.ai cs.cl cs.lg information insights knowledge language language models large language large language models llms parameters practical show skills tasks tool type usage work