liveBook · Manning

Refusal example

As explained in LLM Customization and Fine-Tuning

A refusal example is a training instance that demonstrates declining a harmful or disallowed request.

A refusal example is a training instance that pairs a harmful or disallowed request with a response declining it. Without such examples, a model trained on helpful answers may learn to answer even when it should refuse. section 5.1.4 section 7.8.1

Safety behavior can regress even when task performance is preserved. In black-box distillation, a student exposed only to benign teacher outputs does not see when or how the teacher refuses. Include harmful prompts paired with the teacher’s refusals, then re-test the student. Check teacher outputs for safety as well as quality: fluent, relevant responses can still be harmful. section 7.8.1

A smaller adapter did not restore safety

An IT-support fine-tuning dataset contained 450 helpful examples and no refusal examples. The base model refused 100% of safety prompts, while adapters at ranks 16 and 8 both refused 60%. Reducing rank did not address the missing safety data. section 5.1.4

Table 5.1 LoRA rank comparison; unexpected results from safety fix attempt
Metric
Base
r=16 (Original)
r=8 (Attempted Fix)
Token-F1
0.149
0.154 (+0.005)
0.167 (+0.018)
Safety
100%
60% (-40%)
60% (-40%)
Hardware F1
0.152
0.188 (+0.037)
0.183 (+0.031)
Linux F1
0.129
0.144 (+0.014)
0.162 (+0.032)

Compare the base model and both adapter ranks on safety and task metrics. section 5.1.4

For a dataset of this scale, plan for 50 to 100 explicit refusal examples, roughly 10% to 20% of the data. Treat rank as a capacity and cost choice, not a safety control. Validate safety empirically against the base model before deployment; adding examples does not guarantee alignment. section 5.1.4

How LLM Customization and Fine-Tuning covers it

How deep it goes
Explains the data gap and recommends example counts, safety checks, and comparison against the base model.
Examples
Compares IT-support adapters at two ranks and cites a medical-domain distillation red-team result.
What you can do after
Evaluate and understand safety regression, then select refusal data and validation checks before deployment.
How it connects
Links safety alignment with LoRA rank, knowledge distillation, and safety evaluation.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of LLM Customization and Fine-Tuning. The section links point to the parts of the book it draws on.