Papers
arxiv:2304.00612

Eight Things to Know about Large Language Models

Published on Apr 2, 2023
Authors:

Abstract

A survey identifies eight potentially surprising findings about large language models, including predictable capability gains from investment, unpredictable emergent behaviors, learned world representations, and challenges in steering and interpreting them.

The widespread public deployment of large language models (LLMs) in recent months has prompted a wave of new attention and engagement from advocates, policymakers, and scholars from many fields. This attention is a timely response to the many urgent questions that this technology raises, but it can sometimes miss important considerations. This paper surveys the evidence for eight potentially surprising such points: 1. LLMs predictably get more capable with increasing investment, even without targeted innovation. 2. Many important LLM behaviors emerge unpredictably as a byproduct of increasing investment. 3. LLMs often appear to learn and use representations of the outside world. 4. There are no reliable techniques for steering the behavior of LLMs. 5. Experts are not yet able to interpret the inner workings of LLMs. 6. Human performance on a task isn't an upper bound on LLM performance. 7. LLMs need not express the values of their creators nor the values encoded in web text. 8. Brief interactions with LLMs are often misleading.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2304.00612
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2304.00612 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2304.00612 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2304.00612 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.