An input-output pair is one training sample: a prompt that states the task and a completion that demonstrates the desired response. Fine-tuning uses many task-relevant pairs to steer a pretrained language model toward a particular domain, audience, scenario, or text type. section 7.4.1
Teach audience-specific titles
For a general-public title, pair “Generate a title for the general public about topic X” with “X revealed to you!” A model trained on similar pairs can produce a comparable title for a new topic, such as relativity. section 7.4.1
Table 7.2 The samples based on the information to convey
|
Information to Convey
|
Prompt
|
Completion
a
|
|---|---|---|
|
Parts of a whole
|
Percentage of participants in the conference by type (researchers 5%, students 30%, professors 65%)
|
More professors participated in the conference (65%). Researchers were not interested in the event (5%).
|
|
Comparison among entities
|
Comparison between red (80%), yellow, and green performance
|
Compared to yellow and green, red experienced an improvement in performance of 80%.
|
|
Trend
|
Sales changed in the last 12 months (–12%), due to fewer subscribers and video views.
|
Over the last 12 months, sales decreased by 12% based on various metrics, including subscribers and video views.
|
|
Outcomes of a survey or a questionnaire
|
Questionnaire: 3 positive answers, 7 negative answers
|
Three out of 10 people answered the questionnaire with a positive answer.
|
|
Distribution
|
Sales of product A (+30%) and product B over the last 12 months
|
Compared to product B, sales of product A have increased by 30% over the last 12 months.
|
|
Spatial information
|
Sales in North Europe (+23%) compared to South Europe
|
Compared to South Europe, sales in North Europe increased by 23%.
|
|
Relationship
|
The sales trend line from 1990 to 2020 increased by 120%.
|
Between 1990 and 2020, sales increased by 120%.
|
|
Comparison among entities
|
Top ingredients for our recipe: sugar and salt
|
The chosen ingredients for our recipe are sugar and salt.
|
|
Comparison among entities
|
Comparison between gold (30), silver (20), and bronze (40)
|
Bronze beats silver and gold with 40.
|
|
Distribution
|
Distribution of household chores (cooking 35%, cleaning 30%, laundry 20%, and yard work 15%)
|
Cooking takes up the most significant portion at 35%. Cleaning follows at 30%, while laundry and yard work account for 20% and 15%, respectively.
|
| a. The word completion may be confusing, but it is used by the OpenAI API. Completion refers to the output produced by the model. | ||
Use paired samples to demonstrate how to turn data-storytelling inputs into concise commentary for patterns such as parts of a whole, comparisons, trends, surveys, and distributions. section 7.4.1
Specificity matters: separate datasets can target the general public, professionals, decision makers, particular products or topics, and outputs such as titles, annotations, or commentary. A JSONL sample can represent the behavior as system, user, and assistant messages. section 7.4.1 section 7.4.1
