Summary of Monte Carlo Tree Search For Recipe Generation Using Gpt-2, by Karan Taneja and Richard Segal and Richard Goodwin
Monte Carlo Tree Search for Recipe Generation using GPT-2
by Karan Taneja, Richard Segal, Richard Goodwin
First submitted to arxiv on: 10 Jan 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel method for generating automatic food recipes using a large language model (LLM) and Monte Carlo Tree Search (MCTS). The authors aim to create realistic-sounding recipes that meet individual preferences, dietary constraints, and adapt to available ingredients. They introduce RecipeMC, a text generation method built upon GPT-2 that incorporates soft constraints through reward functions. The results show that human evaluators prefer recipes generated with RecipeMC more often than those from baseline methods when compared to real recipes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us create new and interesting food recipes using computers! Imagine having a tool that can make up yummy recipe ideas based on what you like, your dietary needs, and what ingredients you have at home. The researchers tried using big language models (LLMs) to generate recipes before, but they found those recipes often didn’t quite meet the requirements. So, they created a new method called RecipeMC that uses a combination of LLMs and another technique called Monte Carlo Tree Search (MCTS). This way, they can control what kind of recipe is generated. The results show that people prefer these generated recipes more often than ones from other methods when compared to real recipes. |
Keywords
» Artificial intelligence » Gpt » Large language model » Text generation
