Demonstration Based Prompt Generation For Minority Groups

via “crowdsourced prompt collection and curation”

Crowdsourced LLM evaluation — side-by-side blind voting, Elo ratings, most trusted LLM benchmark.

Unique: Leverages the community to continuously expand the benchmark dataset rather than relying on a fixed set of expert-curated prompts. Prompts are selected for evaluation based on community interest, creating a living benchmark that evolves with user priorities.

vs others: More scalable and diverse than expert-curated benchmarks because it taps community creativity; more representative of real-world usage than synthetic prompt sets

via “demonstration-based-prompt-generation-for-minority-groups”

Microsoft's dataset for implicit toxicity detection.

Unique: Uses a systematic, group-agnostic prompt template that enables consistent generation across 13 minority groups from a single set of human demonstrations, rather than requiring group-specific prompt engineering. The demonstrations_to_prompts.py pipeline abstracts away group-specific details, allowing researchers to focus on demonstration quality rather than prompt tuning.

vs others: More scalable than manual prompt engineering because it automatically generates group-specific prompts from a single demonstration set, reducing the effort needed to create balanced datasets across multiple demographic groups.

via “prompt generation with diversity-aware seeding”

Automated prompt engineering. It generates, tests, and ranks prompts to find the best ones.

Unique: Explicitly seeds candidate generation with diversity instructions rather than generating candidates independently, ensuring the candidate pool explores different solution strategies. Treats diversity as a first-class concern in prompt generation.

vs others: More diverse than independent generation because it explicitly instructs the model to vary approach; more efficient than random sampling because it targets specific diversity dimensions.

via “batch prompt generation from single seed concept”

FLUX-Prompt-Generator — AI demo on HuggingFace

Unique: Generates multiple prompt variants in a single forward pass using sampling diversity rather than requiring sequential API calls, reducing latency and compute cost compared to calling a generic LLM API multiple times

vs others: More efficient than manually calling ChatGPT or Claude multiple times; produces FLUX-optimized variants rather than generic prompt improvements

via “prompt-optimization-and-suggestion-system”

Unique: Provides in-system prompt optimization guidance rather than requiring users to learn through trial-and-error; likely uses prompt quality classifiers or generation success metrics to identify improvement opportunities

vs others: More accessible than external prompt engineering guides or community forums, but less sophisticated than dedicated prompt optimization tools or human expert guidance