Summary of From Decoding to Meta-generation: Inference-time Algorithms For Large Language Models, by Sean Welleck et al.
From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
by Sean Welleck, Amanda Bertsch, Matthew Finlayson, Hailey Schoelkopf, Alex Xie, Graham Neubig, Ilia Kulikov, Zaid Harchaoui
First submitted to arxiv on: 24 Jun 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
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 survey explores inference-time approaches for scaling up large language models (LLMs) during inference. It focuses on token-level generation algorithms, meta-generation algorithms, and efficient generation methods. The authors unify perspectives from three research communities: traditional natural language processing, modern LLMs, and machine learning systems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Large language models can get better results when trained with more computing power. But did you know that using more computing power during inference (when the model is making predictions) also makes a big difference? This survey looks at how to make language models work faster and better during inference. It talks about three ways to do this: token-level generation algorithms, meta-generation algorithms, and efficient generation methods. |
Keywords
* Artificial intelligence * Inference * Machine learning * Natural language processing * Token
