Construct · 2 fields · 5 citations

Where does prompt collide?

One name. Different field. Different construct. One map.

● jingle · one word, two constructs Nearest construct by meaningstimuluscompare the meanings
How to read this

Every construct on the map is compared with every other by the meaning of its definitions, and the closest one is surfaced here. The nearest construct to prompt is stimulus.

Hold this as a prompt, not a verdict. Two constructs sitting close in meaning is a reason to read them side by side and decide for yourself whether they are one idea under two names. It is not proof that they are. Compare the meanings in the Collider.

prompt2 CONSTRUCTSBehavioral promptSKINNER · FADED CUEModel promptBROWN · MODEL PROMPT

Spokes are fields; dashed arcs are shared lineage. Tap a field for its definition, unit, and measures.

1957Behavioral prompt2020Model prompt
2026

Drag to watch the word get claimed. Each field appears at the publication date of the earliest source cited for it. Tap a year to see which.

Behavior analysis

A supplementary antecedent cue that is later faded

In behavior analysis, a prompt is a supplementary stimulus added to the natural cue for a behavior so that a learner responds correctly, after which the prompt is gradually removed, or faded, so that control transfers to the natural cue. B. F. Skinner's 1957 Verbal Behavior treated prompts as supplementary stimuli that strengthen a response already available in the learner, Terrace's 1963 study Discrimination Learning With and Without Errors showed that such supports could be faded with few mistakes, and Cooper, Heron, and Heward's 2007 textbook Applied Behavior Analysis set out the prompt hierarchies used in teaching today. The referent is an engineered teaching cue judged by whether the response occurs and by how quickly the support can be faded, not a whispered line on a stage or an instruction typed to a machine.[1][2][3]

Unit
One supplementary stimulus paired with a target response, at a defined level of a prompt hierarchy
Recovery means
The prompt is deliberately faded so that control transfers to the natural cue
Measured by
Recorded as the prompt level used, percent correct responding, and trials to independent performance

Computing and AI

An input instruction given to a language model

In computing, a prompt is the input that tells a system what to do: the older command-line prompt is the symbol that signals a machine is ready to receive a command, while in modern language technology the prompt is the natural-language text given to a model to elicit a response. Brown and colleagues' 2020 paper Language Models Are Few-Shot Learners showed that a large model could carry out tasks from a worded prompt and a few examples alone, and Liu and colleagues' 2023 survey Pre-train, Prompt, and Predict catalogued the prompting methods that followed. The referent is an instruction or cue supplied to a computational system, distinct from a teaching cue faded in behavior analysis and from a forgotten line supplied to an actor.[4][5]

Unit
One instruction or query submitted to a system, as a command or a block of text
Recovery means
Not applicable
Measured by
Assessed by the quality of the model's output across worded prompts, worked examples, and phrasings

Next

Run it through the Collider, or take the citations with you.

See how prompt sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in ColliderExport BibTeXReport this collision

Nearby collisions

cue4 fields · 7 citationsjingle · one word, four constructsstimulus3 fields · 5 citationsjingle · one word, three constructsconditioning1 fields · 3 citationsanchor · a standalone construct

References

  1. Skinner, B. F. (1957). Verbal behavior. Appleton-Century-Crofts.
  2. Terrace, H. S. (1963). Discrimination learning with and without "errors". Journal of the Experimental Analysis of Behavior, 6(1), 1–27. https://doi.org/10.1901/jeab.1963.6-1
  3. Cooper, J. O., Heron, T. E., & Heward, W. L. (2007). Applied behavior analysis (2nd ed.). Pearson. ISBN 9780131293274
  4. Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., ... Amodei, D. (2020). Language models are few-shot learners. arXiv. https://doi.org/10.48550/arXiv.2005.14165
  5. Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023). Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM Computing Surveys, 55(9), Article 195. https://doi.org/10.1145/3560815

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct