Summary of Non-myopic Generation Of Language Models For Reasoning and Planning, by Chang Ma et al.
Non-myopic Generation of Language Models for Reasoning and Planning
by Chang Ma, Haiteng Zhao, Junlei Zhang, Junxian He, Lingpeng Kong
First submitted to arxiv on: 22 Oct 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL)
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 Large Language Models (LLMs) have excelled at problem-solving by breaking down complex tasks into sequential steps. However, they struggle to ensure reliable and optimal planning due to their inherent myopic nature during autoregressive decoding. To address this challenge, the proposed Predictive-Decoding method leverages Model Predictive Control to improve planning accuracy. By re-weighting LLM distributions based on foresight trajectories, Predictive-Decoding aims to mitigate early errors and promote non-myopic planning. The experiments demonstrate significant improvements in a wide range of tasks for math, coding, and agents, showcasing computational efficiency and outperforming search baselines with reduced resources. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Large Language Models are super smart computers that can solve problems by breaking them down into smaller steps. But sometimes they make mistakes because they’re only looking at the next step, not the whole plan. This paper finds a way to fix this by using a new method called Predictive-Decoding. It helps the computer look ahead and make better plans. The results show that this method works well for many types of problems, like math and coding. |
Keywords
» Artificial intelligence » Autoregressive
