# MK2 at PBIG Competition: A Prompt Generation Solution

arXiv: https://arxiv.org/abs/2507.08335 · HTML: https://mlsanity.com/paper/2507.08335/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 33 references that are in the map.
- First posted on arXiv 11 Jul 2025.

## Builds on (most cited first, 9 of 9)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [SciMON: Scientific Inspiration Machines Optimized for Novelty](https://mlsanity.com/paper/2305.14259/) (2023)
- [Natural Language Processing in the Patent Domain: A Survey](https://mlsanity.com/paper/2403.04105/) (2024)
- [Can Large Language Models Generate High-quality Patent Claims?](https://mlsanity.com/paper/2406.19465/) (2024)
- [Agent Ideate: A Framework for Product Idea Generation from Patents Using Agentic AI](https://mlsanity.com/paper/2507.01717/) (2025)

## Built on by (most cited first, 3 of 3)

- [Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judge](https://mlsanity.com/paper/2602.02219/) (2026)
- [Aggregate vs. Personalized Judges in Business Idea Evaluation: Evidence from Expert Disagreement](https://mlsanity.com/paper/2604.22517/) (2026)
- [MBA: Multimodal Benchmark and Agents for Real-World Business Ideation](https://mlsanity.com/paper/2608.11616/) (2026)

## Abstract (arXiv)

The Patent-Based Idea Generation task asks systems to turn real patents into product ideas viable within three years. We propose MK2, a prompt-centric pipeline: Gemini 2.5 drafts and iteratively edits a prompt, grafting useful fragments from weaker outputs; GPT-4.1 then uses this prompt to create one idea per patent, and an Elo loop judged by Qwen3-8B selects the best prompt-all without extra training data. Across three domains, two evaluator types, and six criteria, MK2 topped the automatic leaderboard and won 25 of 36 tests. Only the materials-chemistry track lagged, indicating the need for deeper domain grounding; yet, the results show that lightweight prompt engineering has already delivered competitive, commercially relevant ideation from patents.