Factual Knowledge in Language Models

This field studies which facts language models learn from training data, when they can retrieve them, and whether their answers match reliable evidence. Researchers use closed-book question-answering benchmarks such as SimpleQA and TruthfulQA, alongside multilingual, temporal, and long-tail tests; probing and causal tracing help investigate how knowledge is represented and accessed. Common interventions include retrieval-augmented generation, reinforcement learning, fine-tuning, and targeted knowledge editing. These methods can improve recall or update answers, but a central challenge is doing so without introducing hallucinations, losing other knowledge, or leaving gaps in unfamiliar languages, domains, and multi-step reasoning.