Oriel — AI & technology worth noticing, every day.

An Introduction to Large Language Models for Scientists and Professionals

Paper · https://arxiv.org/abs/2610.37684

arXiv:2610.37684v1 Announce Type: new Abstract: Large Language Models (LLMs) have rapidly become important tools for science, education, medicine, and professional work. Despite their apparent simplicity from the user's perspective, effective and responsible use requires an understanding of how these systems work, what their limitations are, and how their outputs should be evaluated. I wrote this document as a basis for my lecture on LLM in the master in artificial intelligence in medicine at the university of Turin, Italy. This book provides a practical and accessible introduction to LLMs for scientists and professionals. It explains the fundamental ideas behind tokenisation, embeddings, training, inference, context windows, prompting, and instruction hierarchies, while deliberately avoiding mathematical detail. Particular attention is given to the limitations of LLM-generated answers, including hallucinations, uncertainty, reproducibility, bias, and the need for systematic verification and human oversight. The book also discusses privacy, governance, security, and the responsible handling of personal and sensitive information. More advanced topics include Retrieval-Augmented Generation (RAG), retrieval quality, chunking, embeddings, vector search, agents, tools, and workflows. A substantial practical exercise guides the reader through running a local LLM with Ollama and Open WebUI and using it to interact with a collection of scientific papers. The exercise emphasizes evidence retrieval, source verification, uncertainty, disagreement between studies, and the distinction between plausible language and scientifically supported conclusions. No programming knowledge is required.

First seen by Oriel on .

AI summary

This practical, non-mathematical introduction teaches scientists and professionals how LLMs work, where they fail, and how to use and evaluate them responsibly.

  • It covers tokenisation, embeddings, training, inference, context windows, prompting, and instruction hierarchies without requiring programming knowledge.
  • It addresses hallucinations, uncertainty, reproducibility, bias, privacy, governance, security, verification, and human oversight.
  • Advanced topics include Retrieval-Augmented Generation (RAG), retrieval quality, chunking, vector search, agents, tools, and workflows.
  • A practical exercise uses Ollama and Open WebUI to query scientific papers, emphasizing evidence retrieval, source verification, and disagreement between studies.

#large language models #rag #llm agents #responsible ai

Generated by gpt-5.6-sol. Check the original for details.

Aliases

SourceExternal IDURL
arXiv AI Papersoai:arXiv.org:2610.37684v1https://arxiv.org/abs/2610.37684 Read discussion