HOME/TECHNIQUE/Model Adaptation/Supervised fine-tuning

TECHNIQUE

Supervised fine-tuning

Model Adaptation

4APPLICATIONS
6OBSERVED OPERATORS
01

State of Practice

CROSS-VALIDATED — 8 OPERATORS

Supervised fine-tuning is being used as a product-specific adaptation layer: operators fine-tune on domain/task data, then wrap the model in retrieval, ranking, evaluation, HITL, or serving infrastructure.

Observed Practices

Fine-tune models on task- or domain-specific data for a concrete product workflow, rather than presenting the base model as sufficient.

8 of 8 deployed/pilot operators in the pool; announced operators not counted.
LinkedInCriteoUberPinterestPodiumAtlassianMetaCanva

Use fine-tuning inside retrieval, ranking, recommendation, or selection loops, where the model scores or represents candidates rather than only generating text.

5 of 8 deployed/pilot operators in the pool; LinkedIn is counted once despite multiple teardowns.
LinkedInCriteoPinterestAtlassianMeta

Pair fine-tuning with efficiency or operability tactics such as LoRA, lightweight continuous fine-tuning, in-house inference, compact models, or distillation.

5 of 8 deployed/pilot operators in the pool; announced operators not counted.
LinkedInCriteoPinterestPodiumCanva

Build evaluation, monitoring, safety, or human-review gates around the fine-tuned model before or during production use.

8 of 8 deployed/pilot operators in the pool; announced operators not counted.
LinkedInCriteoUberPinterestPodiumAtlassianMetaCanva

Where Operators Converge

Every deployed/pilot operator applies supervised fine-tuning to a bounded product task: job/feed matching, ad prediction, invoice/document extraction, journey relevance, agent conversation control, enterprise search, root-cause ranking, or design-object detection.

Every deployed/pilot operator wraps the fine-tuned model in surrounding production machinery rather than relying on fine-tuning alone: retrieval/ranking stages, OCR/document pipelines, clustering, tool calling, observability, evaluation, HITL, or model-serving infrastructure.

Where Operators Diverge

Operators fine-tune different model families for different production roles.

APPROACH 01

Fine-tuned LLMs or language models for extraction, ranking, agent behavior, or domain adaptation.

LinkedInUberPinterestPodiumMeta

APPROACH 02

Fine-tuned embedding or representation models for search/recommendation retrieval quality.

LinkedInAtlassian

APPROACH 03

Fine-tuned non-LLM deep models for structured-data prediction or vision detection.

CriteoCanva

Training supervision sources differ substantially.

APPROACH 01

Production behavior or historical operational records become fine-tuning data.

CriteoLinkedInPodiumMeta

APPROACH 02

Human annotations, reviewer validation, or in-house labeling are used to create or correct supervised data.

LinkedInUberCanva

APPROACH 03

Synthetic or teacher-generated labels/data are used to scale supervision.

PinterestAtlassian

Fine-tuning update style differs by operating constraint.

APPROACH 01

Continuous or frequent fine-tuning/retraining to keep models fresh.

Criteo

APPROACH 02

Multi-stage domain adaptation or alignment pipelines.

LinkedInMeta

APPROACH 03

Task-centric fine-tuning of an existing model for one bounded product capability.

UberPinterestPodiumAtlassianCanva

Watch Items

Compute, latency, and cost pressure are repeatedly called out as production constraints around fine-tuned models.

Reliable labels and evaluations remain hard: operators report costly/inconsistent human evaluation, missing reference labels, and effort to regenerate representative training data.

Operators add human review, safety checks, confidence filters, or safety alignment because fine-tuned outputs are not treated as automatically safe or reliable.

Freshness and distribution shift show up as operational concerns: Criteo reports calibration issues under new A/B traffic, while other systems use continuous adaptation or incremental inference to keep model behavior current.

02

Implementation Menu

CURATED DEFAULTS
NameKindMaturity
LoRA via PEFTlibraryestablished
Axolotllibraryestablished
Provider fine-tuning APIsserviceestablished
03

Observed in Production

4 APPS