MK2 at PBIG Competition: A Prompt Generation Solution
Not on the map. Why?
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.
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
9 of 33 references.
References · 9
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
- 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,184
- 2024Justice or Prejudice? Quantifying Biases in LLM-as-a-Judgecited by 368
- 2023JudgeLM: Fine-tuned Large Language Models are Scalable Judgescited by 367
- 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 363
- 2023SciMON: Scientific Inspiration Machines Optimized for Noveltycited by 179
- 2024Natural Language Processing in the Patent Domain: A Surveycited by 20
- 2024Can Large Language Models Generate High-quality Patent Claims?cited by 19
- 2025Agent Ideate: A Framework for Product Idea Generation from Patents Using Agentic AIcited by 3
Built on by
Citing papers per year: 2026: 3.
3 papers.