Summary of Incoherent Probability Judgments in Large Language Models, by Jian-qiao Zhu and Thomas L. Griffiths
Incoherent Probability Judgments in Large Language Models
by Jian-Qiao Zhu, Thomas L. Griffiths
First submitted to arxiv on: 30 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 explores the ability of Autoregressive Large Language Models (LLMs) trained for next-word prediction to form coherent probability judgments. Despite their remarkable proficiency in generating text, our study shows that these models often produce incoherent probability judgments, exhibiting systematic deviations from probability theory rules. We propose that these deviations can be explained by linking autoregressive LLMs to implicit Bayesian inference and drawing parallels with the Bayesian Sampler model of human probability judgments. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how well computer models called Autoregressive Large Language Models (LLMs) do when they try to make smart guesses about chances. These models are really good at making text sound natural, but our research shows that their predictions don’t always follow the rules of chance. We found some interesting patterns in how these models think, and we think it might be similar to how humans decide on odds. |
Keywords
» Artificial intelligence » Autoregressive » Bayesian inference » Probability
