GenAI Field Guide

Reference

The evidence

Every "why" in this guide traces to one of these. Several 2025–2026 items are preprints or vendor reports: strong, but not peer-reviewed, and this guide says so where it leans on them.

≈3 min
Claim in this guide Source
The transformer, the architecture under every LLM Vaswani et al., "Attention Is All You Need," NeurIPS 2017
Examples in the prompt work (in-context learning) Brown et al., "Language Models are Few-Shot Learners," NeurIPS 2020
Stepwise reasoning improves accuracy (now built into "reasoning" models) Wei et al., "Chain-of-Thought Prompting," NeurIPS 2022
RAG Lewis et al., "Retrieval-Augmented Generation for Knowledge-Intensive NLP," NeurIPS 2020
Material in the middle of a long context is used less reliably Liu et al., "Lost in the Middle," TACL 2024
Effective context is often far shorter than advertised Modarressi et al., "NoLiMa: Long-Context Evaluation Beyond Literal Matching," 2025 (preprint)
Hallucination is structural; RAG reduces but does not eliminate it Ji et al., "Survey of Hallucination in Natural Language Generation," ACM Computing Surveys 2023, and numerous 2024–2025 RAG evaluations showing residual errors when retrieval returns wrong or partial chunks
Uncertainty can be measured by sampling and checking agreement Farquhar et al., "Detecting hallucinations in large language models using semantic entropy," Nature 2024
Models guess because guessing was rewarded Kalai et al., "Why Language Models Hallucinate," OpenAI, 2025 (vendor report)
Prompt injection is a real attack class Greshake et al., "Not what you've signed up for: Compromising real-world LLM-integrated applications with indirect prompt injection," AISec 2023

Where this guide is least sure