Terms starting with D

24 of 250 glossary terms. Each entry links to its own page with why it matters and where it fits.

Definitions here are written for engineers, not grammarians: what the term means, why it matters when it comes up, and where it sits in the curriculum — most term pages name the lessons that lean on the concept, so you can jump from a definition straight to the teaching. Use the letter bar below to move through the alphabet, or press the slash key to search the whole corpus directly.

Every entry carries three things besides the definition: the plain aliases it travels under (listed as “also”), a category tag for which stretch of the curriculum it belongs to, and the cross-references that place it next to its neighbors — the terms you would meet in the same lesson. A term earns a page here only when a lesson in the curriculum actually uses it, so the corpus stays the shape of the material instead of the shape of a dictionary.

One honest way to use this page: read down the list of entries below and note every term you could not define in a sentence if a colleague asked. That list — not the whole letter — is your revision list, and each entry links to the reading that closes the gap.

DPO (Direct Preference Optimization)
Math & training
A preference-optimization objective that trains a policy directly from preferred and rejected response pairs relative to a reference policy. It avoids running an explicit reward model and reinforcement-learning loop during this stage.
Data Augmentation
Math & training
Creating modified examples, such as transformed images, perturbed audio, or paraphrased text, to increase training diversity without collecting entirely new source data. It can reduce overfitting when the transformation preserves the task signal.
Data Classification
Security & governance
Assigning data to documented sensitivity or impact classes so handling, access, retention, sharing, and incident rules follow the consequences of disclosure or loss.
Data Deduplication
Data & representations
Detecting and removing exact and near-duplicate examples within or across datasets.
Data Exfiltration
Security & governance
Unauthorized transfer of protected data from a system or trust zone to a person, tool, service, or storage location that is not permitted to receive it.
Data Leakage
Data & representations
Unintended use of information during training or feature construction that would not be available at the real prediction point or belongs to a held-out evaluation boundary.
Data Lineage
Security & governance
A record of how a data artifact was derived across sources, transformations, joins, filters, versions, and downstream uses.
Data Minimization
Security & governance
For personal data, limiting what is collected, processed, exposed, and retained to what is necessary for a specified purpose. Teams can apply the same discipline to sensitive non-personal data as an engineering control.
Data Provenance
Data & representations
Traceable information about where data originated, who or what transformed it, which versions were used, and how derived artifacts relate to their sources.
Dataset Split
Data & representations
A documented partition of examples into separate subsets for fitting, development decisions, and final evaluation.
Datasheet for Datasets
Security & governance
Structured documentation of a dataset's motivation, composition, collection process, preprocessing, uses, distribution, maintenance, and known limitations.
Deadline Propagation
Reliability & operations
Passing the remaining end-to-end time budget to downstream calls so each dependency knows how long the original request can still usefully wait.
Decode Phase
Infrastructure & serving
The iterative stage of autoregressive inference that generates new tokens one step at a time after the input prefix has been processed.
Decoder
Models & inference
A component that maps a representation into an output. In an encoder-decoder transformer, the decoder uses masked self-attention and cross-attention to generate outputs. Decoder-only language models instead generate from a single causal stack.
Decoding Strategy
Models & inference
The algorithm that converts a model's sequence of next-token scores into selected tokens and a completed output.
Defense in Depth
Security & governance
Using independent preventive, detective, and corrective controls at several system boundaries so one failed control does not determine the outcome.
Delegation
Agents & tools
Assigning a bounded subtask to another person or agent together with the needed context, authority, output contract, and return conditions.
Dense Retrieval
Retrieval & generation
First-stage retrieval that embeds queries and candidates into vector representations and ranks candidates by a similarity function.
Diffusion Model
Models & inference
A generative model trained around a progressive noising process and a learned reverse process. Sampling usually begins from noise and applies repeated denoising steps, sometimes in a learned latent space.
Disaggregated Serving
Infrastructure & serving
A serving architecture that runs prefill and decode work in separately provisioned worker pools and transfers the required attention state between them.
Distribution Shift
Evaluation & safety
A difference between the data distribution used to build or evaluate a system and the distribution it encounters after deployment.
Dropout
Math & training
During training, randomly setting a fraction of activations to zero encourages the network not to rely on one activation path. It is normally disabled for standard inference, although Monte Carlo dropout deliberately keeps it active to estimate uncertainty.
Durable Execution
Agents & tools
Running a workflow so its state and completed steps survive process crashes, restarts, or long waits without redoing confirmed side effects.
Dynamic Batching
Infrastructure & serving
A runtime policy that forms inference batches from queued requests according to compatible shapes, maximum size, priority, and allowed queue delay.