ДаліНаступний посібник
Налаштування префіксів
ШІ мови
Мова AI GUIDE
Instruction tuning is supervised training on task instructions paired with example responses.
Послухайте цей посібникШІ-розказаний · ~3 min
It aims to improve instruction following beyond a pretrained model's original behavior, while success on unseen tasks still requires evaluation.
A pretrained language model learns patterns from its training data, but continuing a text pattern is different from reliably following a user's requested task. A base model might respond to a question with an answer or continue a sequence of questions; its behavior is not uniformly one or the other. Instruction tuning uses supervised examples that pair instructions with target responses. Model parameters are updated so that the predicted response better matches the training target. Tasks can include translation, summarization, classification, and question answering. Research such as FLAN, T0, and FLAN-T5 studies mixtures of prompted tasks and evaluates whether the trained model handles tasks beyond those used in training. Results depend on the data, model, and evaluation; diversity is useful evidence to investigate rather than proof that every new instruction will be followed. Instruction tuning also differs from later preference optimization. In the InstructGPT recipe, supervised fine-tuning is followed by reward-model training from comparisons and a reinforcement-learning stage. That is a particular published recipe, not a requirement that every assistant use identical stages. The LIMA experiment illustrates another configuration: a 65B model was supervised fine-tuned on 1,000 carefully curated prompts and responses without reinforcement learning or human preference modeling. Its reported results motivate attention to data quality, but do not establish that 1,000 examples are sufficient for every model and task. A practical evaluation should distinguish reproducing training responses from following held-out instructions, and should state which training stages were actually used.
Comparing a pretrained model with its instruction-tuned version on held-out tasks.
Studying FLAN and FLAN-T5 research on learning from a mixture of instructed tasks.
Separating InstructGPT's supervised response training from its later preference-based stages.
Reviewing instruction-response examples before using them for supervised fine-tuning.
Research can compare instruction datasets, response quality, task coverage, and training procedures under explicit evaluation conditions. Small curated datasets and larger mixtures answer different experimental questions, so their findings should not be generalized without checking the target task. Reports should identify the base model, examples, supervised objective, optional preference stages, and held-out evaluation. Instruction following also needs separate checks for factual accuracy and application suitability; a model can follow the requested format while still generating an incorrect answer.
Безплатний розсилок
Три перевірені історії про ШІ щоробочого ранку, написані простою мовою. Безплатно назавжди, без реклами.
Один лист щотижня з понеділка по п'ятницю. Відписатися в один клік. Ми ніколи не продаємо та не передаємо вашу адресу.
Перевір себе
Миттєва зворотна связь на кожну відповідь та сертифікат із перевіреним ідентифікатором, яким можна поділитися, після проходження курсу.
Підтримайте безплатну освіту у сфері ШІ. AI Understanding — це некомерційна організація 501(c)(3) — без реклами, без платних стін, назавжди. Зробіть пожертву
Instruction tuning is supervised training on task instructions paired with example responses. It aims to improve instruction following beyond a pretrained model's original behavior, while success on unseen tasks still requires evaluation.
The distinction concerns target-response supervised learning versus the paper's later preference-based training stages.
Task diversity can support generalization, but performance should be measured on inputs outside the training examples.
Моделі спочатку готуються до необробленого тексту, потім налаштовуються інструкції для виконання завдань і часто вдосконалюються за допомогою RLHF для тонусу та безпеки.
The reported LIMA configuration motivates data-quality research without creating a universal sample-count rule.
The original paper describes standard supervised fine-tuning without those preference-based stages.
Продовжуйте вчитися
Інші посібники, вибрані для цієї теми
ДаліНаступний посібник
Налаштування префіксів
ШІ мови