RECORD
A Framework for Lightweight Responsible Prompting Recommendation
Information Retrieval · Submitted 29 Mar 2025
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim With the proposed framework and open-source system, the contributions presented can be applied in multiple contexts where end-users can benefit from guidance for interacting with GenAI in a more responsible way, recommending positive values to be added and harmful sentences to be removed.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Computer Science and Design practitioners have been researching and proposing alternatives for a dearth of recommendations, standards, or best practices in user interfaces for decades. Now, with the advent of generative Artificial Intelligence (GenAI), we have yet again an emerging, powerful technology that lacks sufficient guidance in terms of possible interactions, inputs, and outcomes. In this context, this work proposes a lightweight framework for responsible prompting recommendation to be added before the prompt is sent to GenAI. The framework is comprised of (1) a human-curated dataset for recommendations, (2) a red team dataset for assessing recommendations, (3) a sentence transformer for semantics mapping, (4) a similarity metric to map input prompt to recommendations, (5) a set of similarity thresholds, (6) quantized sentence embeddings, (7) a recommendation engine, and (8) an evaluation step to use the red team dataset. With the proposed framework and open-source system, the contributions presented can be applied in multiple contexts where end-users can benefit from guidance for interacting with GenAI in a more responsible way, recommending positive values to be added and harmful sentences to be removed.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Computer Science and Design practitioners have been researching and proposing alternatives for a dearth of recommendations, standards, or best practices in user interfaces for decades. | background 0.99 | 0.03 | 0.02 | asserted 1.00 |
| s1 | Now, with the advent of generative Artificial Intelligence (GenAI), we have yet again an emerging, powerful technology that lacks sufficient guidance in terms of possible interactions, inputs, and outcomes. | background 0.52 | 0.06 | 0.03 | asserted 0.99 |
| s2 | In this context, this work proposes a lightweight framework for responsible prompting recommendation to be added before the prompt is sent to GenAI. | contribution 1.00 | 0.81 | 0.36 | asserted 0.99 |
| s3 | The framework is comprised of (1) a human-curated dataset for recommendations, (2) a red team dataset for assessing recommendations, (3) a sentence transformer for semantics mapping, (4) a similarity metric to map input prompt to recommendations, (5) a set of similarity thresholds, (6) quantized sentence embeddings, (7) a recommendation engine, and (8) an evaluation step to use the red team dataset. | method 0.97 | 0.86 | 0.09 | asserted 0.99 |
| s4 | With the proposed framework and open-source system, the contributions presented can be applied in multiple contexts where end-users can benefit from guidance for interacting with GenAI in a more responsible way, recommending positive values to be added and harmful sentences to be removed. | interpretation 0.58 | 0.60 | 0.61 | asserted 0.51 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Computer Science and Design practitioners have been researching and proposing alternatives for a dearth of recommendations, standards, or best practices in user interfaces for decades. Now, with the advent of generative Artificial Intelligence (GenAI), we have yet again an emerging, powerful technology that lacks sufficient guidance in terms of possible interactions, inputs, and outcomes. In this context, this work proposes a lightweight framework for responsible prompting recommendation to be added before the prompt is sent to GenAI. The framework is comprised of (1) a human-curated dataset for recommendations, (2) a red team dataset for assessing recommendations, (3) a sentence transformer for semantics mapping, (4) a similarity metric to map input prompt to recommendations, (5) a set of similarity thresholds, (6) quantized sentence embeddings, (7) a recommendation engine, and (8) an evaluation step to use the red team dataset. With the proposed framework and open-source system, the contributions presented can be applied in multiple contexts where end-users can benefit from guidance for interacting with GenAI in a more responsible way, recommending positive values to be added and harmful sentences to be removed.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 8 sentences without a confident label
Uses the method or tool of 1 paper
-
During the debriefing, participants were instructed to interact with the system as needed, as proposed in retrospective end-user walkthrough [ref] .
Retrospective End-User Walkthrough: A Method for Assessing How People Combine Multiple AI Models in Decision-Making Systems · Experiment design · 1.00
Cites as background 4 papers
-
With the emergence and adoption of attention mechanisms [ref] and transformer architectures [ref] , texts are embedded into fix-sized representations, and metrics that are used to calculate the distances between vectors can be adapted to represent the similarity between pairs of texts.
Attention Is All You Need · Similarity Metrics · 0.85
-
With the emergence and adoption of attention mechanisms [ref] and transformer architectures [ref] , texts are embedded into fix-sized representations, and metrics that are used to calculate the distances between vectors can be adapted to represent the similarity between pairs of texts.
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding · Similarity Metrics · 0.85
-
These systems are designed for a diversity of specific goals, such as image generation [ref] and LLM jailbreak [ref] .
Open Sesame! Universal Black Box Jailbreaking of Large Language Models · Machine Generated Prompts · 0.87
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.