CS PAPERS DEEP-READ · PAPER 11

GPT-3 (Language Models are Few-Shot Learners)

Brown et al. · OpenAI · NeurIPS 2020

中文 →

What did this paper do?

In 2020, OpenAI released GPT-3 — the direct ancestor of ChatGPT. What the paper did sounds almost crude: scale a language model up to an unprecedented 175 billion parameters and have it read a huge slice of the internet. Then they showed something strange: this model never needs task-specific training again — show it a few examples right in the input, and it can translate, answer questions, write articles, and do arithmetic on the spot, picking things up "at a glance" the way people do.

First, the old world's problem

Before this, AI worked "one job, one training course." Want a model that translates? First collect tens of thousands of hand-labeled translation pairs and train on them. Want it to judge whether a movie review is positive? Collect and train all over again. Every new task meant paying people to label data and running another round of training — like sending an employee to a months-long bootcamp every time they switch roles. Expensive, slow, and only accessible to people who could train models.

The new idea: skip the bootcamp, hire a well-read veteran

GPT-3's approach: instead of running a bootcamp per task, raise one veteran who has read everything. During training it does exactly one thing — read oceans of text and practice "guess the next word." Once trained, you never touch it again: write the task in plain language on a note, attach two or three worked examples, and it follows along. The paper calls this "few-shot learning" — not re-teaching the model, just reminding it.

Why are a few examples enough?

The key: those examples aren't "teaching" it a new skill — they're telling it which skill to pull out. Picture a giant jukebox. The songs (the skills) were recorded while it read the internet: grammar, common sense, correspondences between languages, the rhythm of question-and-answer. The examples you write are like punching in a song number, helping it lock on: "ah, we're playing the English-to-French game now."

And the paper's most important finding is: the bigger the model, the better this trick works. For small models, showing examples barely helps; only past a certain scale does "learning from examples" suddenly start working well. "Bigger" isn't just more of the same. One honest caveat: at bottom it is still just continuing text, and fluent doesn't mean true — it will fabricate facts with a straight face, a flaw that runs from GPT-3 straight through to today's chatbots.

What it brought

The way we use AI changed: no longer "engineers collect data and train models," but "anyone commands a model with a paragraph of text" — the prompts everyone writes today became a craft starting with this paper. Two years later, OpenAI added a layer of "follow human instructions" training on top of its successor, and that became ChatGPT.

One line to remember

Scale "guess the next word" up to 175 billion parameters and the model can pick up new tasks on the spot from a few examples, with no task-specific training — GPT-3 proved that size itself buys generality, opened the prompting era, and is ChatGPT's direct ancestor.

Want the diagram of the three prompting modes, the scaling curves, and the real benchmark numbers? → Switch to Deep