Get the latest tech news

Practical Prolog Planner Prompting

Using Large Language Models to generate Prolog planners State of the art in LLM-generated planners Parts of the public discussion about LLMs revolves around unachievably high goals such as "General AI", but LLMs are just statistical language models after all and excel in language translation and summarization tasks foremost. And while LLMs can be trained to do almost anything including optimization and other math and reasoning tasks, it's exceedingly clear results are determined by the used training data sets, and remain highly volatile and unpredictable for problems outside that set, a fact well known acknowledged in papers such as aiw and posp.

Logistics optimization is an established field of planning after all, and progress may evolve in incremental steps using experimentation and regular software engineering practices, which Prolog as a standardized programming language is ideally suited for of course. PMLR 235 2024 aiw Nezhurina, M., Cipolina-Kun, L., Cherti, M., Jitsev, J. Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models NeurIPS Scientific Methods for Understanding Deep Learning Workshop (SciDL) 2024 tnltopgwl Xie, Y., Yu, C., Zhu, T., Bau, J., Gong, Z., Soh, H. Translating Natural Language to Planning Goals using LLMs dwr Nau, D., Ghallab, M., Traverso, P. (2004) Automated Planning: Theory & Practice. San Francisco, CA, USA Morgan Kaufmann Publishers Inc osllpds Paul, G., Röger, G., Keller, T., Helmert, M., Optimal Solutions to Large Logistics Planning Domain Problems Vol.

Get the Android app