From Tokens To Agents: A Researcher's Guide To Understanding Large Language Models
It provides a non-technical guide for researchers to assess LLM applicability, but is incremental as it synthesizes existing knowledge into a framework.
The chapter tackles the problem of researchers needing to understand large language models (LLMs) to use them effectively in their work, by breaking down six essential components and developing a framework for critical reasoning, illustrated with a case study on simulating social media dynamics.
Researchers face a critical choice: how to use -- or not use -- large language models in their work. Using them well requires understanding the mechanisms that shape what LLMs can and cannot do. This chapter makes LLMs comprehensible without requiring technical expertise, breaking down six essential components: pre-training data, tokenization and embeddings, transformer architecture, probabilistic generation, alignment, and agentic capabilities. Each component is analyzed through both technical foundations and research implications, identifying specific affordances and limitations. Rather than prescriptive guidance, the chapter develops a framework for reasoning critically about whether and how LLMs fit specific research needs, finally illustrated through an extended case study on simulating social media dynamics with LLM-based agents.