Explainability surfaces the training data that influenced fine-tuned model outputs. By tracing model responses back to specific question-and-answer pairs from the training dataset, explainability helps debug model behavior, audit responses, and build trust in model outputs.

How explainability works

When a fine-tuned model generates a response, explainability identifies the most influential training examples that shaped that output. Each influential example receives an influence level (high, medium, or low) indicating its contribution to the model's response.

Requirements

Explainability is available for:

• Fine-tuned models created through SeekrFlow
• Models trained after September 22, 2025
• Deployed models with active endpoints

Influence levels

Training examples are ranked by their influence on model outputs:

Irrelevant training examples are filtered out and not returned.

Use cases

Explainability supports several important workflows:

Debugging model behavior – Identify which training examples drive unexpected or incorrect responses

Auditing outputs – Trace model decisions back to source training data for compliance and verification

Dataset refinement – Discover patterns in influential training examples to improve fine-tuning datasets

Building trust – Provide transparency into model decision-making for stakeholders

Traceability

Explainability responses include file identifiers linking back to source documents. This traceability connects model outputs to original training materials, supporting debugging and dataset updates.