Results for "data → model"

Using production outcomes to improve models.

Model relies on irrelevant signals.

Model behaves well during training but not deployment.

Coordinating models, tools, and logic.

Fast approximation of costly simulations.

Logging hyperparameters, code versions, data snapshots, and results to reproduce and compare experiments.

Estimating parameters by maximizing likelihood of observed data.

Centralized repository for curated features.

Attention between different modalities.

Scaling law optimizing compute vs data.

Predicts masked tokens in a sequence, enabling bidirectional context; often used for embeddings rather than generation.

A high-priority instruction layer setting overarching behavior constraints for a chat model.

Studying internal mechanisms or input influence on outputs (e.g., saliency maps, SHAP, attention analysis).

System for running consistent evaluations across tasks, versions, prompts, and model settings.

Hidden behavior activated by specific triggers, causing targeted mispredictions or undesired outputs.

Embedding signals to prove model ownership.

Maps audio signals to linguistic units.

Cost of model training.

Models whose weights are publicly available.

One example included to guide output.

Asking model to review and improve output.

Learned model of environment dynamics.

Credit models with interpretable logic.

Learning a function from input-output pairs (labeled data), optimizing performance on predicting outputs for unseen inputs.

Reusing knowledge from a source task/domain to improve learning on a target task/domain, typically via pretrained models.

Techniques that discourage overly complex solutions to improve generalization (reduce overfitting).

A conceptual framework describing error as the sum of systematic error (bias) and sensitivity to data (variance).

One complete traversal of the training dataset during training.

Converting text into discrete units (tokens) for modeling; subword tokenizers balance vocabulary size and coverage.

Letting an LLM call external functions/APIs to fetch data, compute, or take actions, improving reliability.