Alignment
Also: AI alignment
Work to make a model act as people intend. For example, it should follow rules and avoid harm. This is a goal, not a promise.
The fuller definition
Alignment concerns making AI behavior conform to intended goals, instructions, and constraints. The intended goals and ways of measuring them need to be specified.
Supply instructions and examples each time. Nothing in the model changes.
Fetch current documents and put them in context. Facts can change daily.
Train the parameters on examples. Changes behaviour and style; poor at keeping facts current.
Most legal tasks need the first two. Fine-tuning is a project, with data, evaluation, and maintenance, and it is the wrong tool for facts that change.
A concrete example
A system is trained and tested to avoid taking actions outside the permissions granted for a task.
The distinction that matters
Instruction following, factual accuracy, and safe action are related but distinct properties.
Related terms
Reinforcement learning from human feedback (RLHF)
Training that uses people's ratings of model answers. It helps steer the model toward replies people prefer.
Reliability & securityGuardrail
A rule or filter that stops an AI system from doing certain things.
Reliability & securityEvaluation (eval)
Testing an AI tool on a set of tasks to see how well it actually does.
Where it is taught
How models learn from examplesSource and further reading
Hugging Face · LLM courseThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.