A continuaciónSiguiente guía
Transferir aprendizaje
Fundamentos
GUÍA DE FUNDAMENTOS
Few-shot methods aim to use a small labeled support set or a few demonstrations for a task.
Escuche esta guíaNarrado por IA · ~3 min
In-context prompting and metric-based learning achieve this through different procedures, and neither guarantees successful adaptation from any arbitrary examples.
Few-shot is used across methods that supply only a small number of task examples, often after substantial prior learning. In an N-way K-shot classification episode, N counts classes and K counts labeled support examples per class. That notation describes the task’s support data rather than the model’s total pretraining corpus. In-context few-shot prompting supplies demonstrations in the input of an already trained model. The cited language-model study evaluates this mode without task-specific gradient updates during the prompt; examples condition the prediction rather than rewrite weights. Fine-tuning on a small dataset is a different procedure even when both are called few-shot adaptation. Prior training can make representations or patterns useful for a new task, but a few examples do not guarantee that the model infers the intended labels or rules. Prototypical Networks studies a metric-based alternative. A learned embedding maps labeled support items into a space, and each class prototype is the mean of its support embeddings. A query is classified using distances to those prototypes. If one class has support vectors (0,0) and (2,0), its arithmetic-mean prototype is (1,0). The support items used to build the prototype and the query items used to assess classification have different roles. Training episodes in the paper keep those sampled sets separate. For in-context models, demonstration order can also affect results: Fantastically Ordered Prompts studies large variation among permutations in particular text-classification setups. Selecting a favorable order should not be confused with proof of generalization on an untouched evaluation set.
Providing labeled ticket examples in a prompt before a new ticket query.
Demonstrating an output format with a few input-output pairs.
Computing a class prototype from labeled support embeddings.
Comparing prompt orders on a separate evaluation set without changing the examples.
Few-shot evaluations can compare representative support examples, ordering, retrieval of demonstrations, and learned distance functions under clearly separated data roles. More demonstrations may supply useful information but can also change prompt length or introduce misleading patterns. Experiments should record whether weights were updated and whether labels from the final query set influenced selection. Different domains can require different prior representations or examples. Testing the intended task and untouched queries gives a more meaningful result than assuming a small labeled set automatically enables instant adaptation or reproduces human learning.
Boletín gratuito
Tres noticias verificadas sobre IA cada mañana de lunes a viernes, explicadas con claridad. Gratis para siempre y sin anuncios.
Un correo cada día laborable. Date de baja con un clic. Nunca vendemos ni compartimos tu dirección.
Ponte a prueba
Corrección inmediata en cada respuesta y un certificado para compartir, con un ID verificable, cuando apruebas un curso.
Apoya la educación gratuita sobre IA. AI Understanding es una organización sin fines de lucro 501(c)(3): sin anuncios ni muros de pago, nunca. Hacer una donación
Few-shot methods aim to use a small labeled support set or a few demonstrations for a task. In-context prompting and metric-based learning achieve this through different procedures, and neither guarantees successful adaptation from any arbitrary examples.
N counts the classes; K counts examples for each class in the specified support set.
El aprendizaje en contexto no realiza actualizaciones de gradiente; Los ejemplos del mensaje simplemente guían las predicciones del siguiente token del modelo.
Zero-shot solo ofrece instrucciones sin ejemplos, mientras que pocos-shot incluye un puñado de demostraciones.
The benefit depends on the prior model, task, and examples; success must be measured.
Las redes prototípicas forman un prototipo (incrustación promedio) por clase y clasifican nuevos puntos según el prototipo más cercano en el espacio aprendido.
sigue aprendiendo
Más guías seleccionadas para este tema.
A continuaciónSiguiente guía
Transferir aprendizaje
Fundamentos