Language Models are Few-Shot Learners
E457860
"Language Models are Few-Shot Learners" is a landmark research paper that demonstrated large-scale transformer-based language models can perform diverse tasks from just a few examples without task-specific training.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Language Models are Few-Shot Learners canonical | 2 |
How this entity was disambiguated
This entity first appeared as the object of triple T4651147 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Language Models are Few-Shot Learners Context triple: [Tom B. Brown, notableWork, Language Models are Few-Shot Learners]
-
A.
Language Models are Unsupervised Multitask Learners
"Language Models are Unsupervised Multitask Learners" is a 2019 OpenAI research paper that demonstrated how large-scale unsupervised language models like GPT-2 can perform a wide range of tasks without task-specific training.
-
B.
Exploring the Limits of Language Modeling
"Exploring the Limits of Language Modeling" is a research paper that investigates how far large-scale neural language models can be pushed in terms of performance, scalability, and generalization on natural language tasks.
-
C.
LLaMA
LLaMA is a family of large language models developed by Meta AI, designed for efficient training and inference across a range of natural language processing tasks.
-
D.
LLM
LLM is the ICAO airline designator assigned to Yamal Airlines, a Russian regional carrier.
-
E.
Longformer
Longformer is a transformer-based neural network architecture designed for efficient processing of very long sequences using sparse attention mechanisms.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Language Models are Few-Shot Learners Target entity description: "Language Models are Few-Shot Learners" is a landmark research paper that demonstrated large-scale transformer-based language models can perform diverse tasks from just a few examples without task-specific training.
-
A.
Language Models are Unsupervised Multitask Learners
"Language Models are Unsupervised Multitask Learners" is a 2019 OpenAI research paper that demonstrated how large-scale unsupervised language models like GPT-2 can perform a wide range of tasks without task-specific training.
-
B.
Exploring the Limits of Language Modeling
"Exploring the Limits of Language Modeling" is a research paper that investigates how far large-scale neural language models can be pushed in terms of performance, scalability, and generalization on natural language tasks.
-
C.
LLaMA
LLaMA is a family of large language models developed by Meta AI, designed for efficient training and inference across a range of natural language processing tasks.
-
D.
LLM
LLM is the ICAO airline designator assigned to Yamal Airlines, a Russian regional carrier.
-
E.
Longformer
Longformer is a transformer-based neural network architecture designed for efficient processing of very long sequences using sparse attention mechanisms.
- F. None of above. chosen
Statements (59)
| Predicate | Object |
|---|---|
| instanceOf |
research paper
ⓘ
scientific article ⓘ |
| alsoKnownAs | GPT-3 paper NERFINISHED ⓘ |
| architecture | transformer ⓘ |
| author |
Aditya Ramesh
NERFINISHED
ⓘ
Alec Radford NERFINISHED ⓘ Amanda Askell NERFINISHED ⓘ Ariel Herbert-Voss NERFINISHED ⓘ Arvind Neelakantan NERFINISHED ⓘ Benjamin Chess NERFINISHED ⓘ Benjamin Mann NERFINISHED ⓘ Christopher Berner NERFINISHED ⓘ Christopher Hesse NERFINISHED ⓘ Clemens Winter NERFINISHED ⓘ Daniel M. Ziegler NERFINISHED ⓘ Dario Amodei NERFINISHED ⓘ Eric Sigler NERFINISHED ⓘ Girish Sastry NERFINISHED ⓘ Gretchen Krueger NERFINISHED ⓘ Ilya Sutskever NERFINISHED ⓘ Jack Clark NERFINISHED ⓘ Jared Kaplan NERFINISHED ⓘ Jeffrey Wu NERFINISHED ⓘ Mark Chen NERFINISHED ⓘ Mateusz Litwin NERFINISHED ⓘ Melanie Subbiah NERFINISHED ⓘ Nick Ryder NERFINISHED ⓘ Prafulla Dhariwal NERFINISHED ⓘ Pranav Shyam NERFINISHED ⓘ Rewon Child NERFINISHED ⓘ Sam McCandlish NERFINISHED ⓘ Sandhini Agarwal NERFINISHED ⓘ Scott Gray NERFINISHED ⓘ Tom B. Brown NERFINISHED ⓘ Tom Henighan NERFINISHED ⓘ |
| demonstrates |
few-shot learning capabilities of large language models
ⓘ
one-shot learning capabilities of large language models ⓘ zero-shot learning capabilities of large language models ⓘ |
| field |
artificial intelligence
ⓘ
machine learning ⓘ natural language processing ⓘ |
| impact | landmark paper in large-scale language modeling ⓘ |
| institution | OpenAI NERFINISHED ⓘ |
| language | English ⓘ |
| mainSubject |
few-shot learning
ⓘ
large language models ⓘ transformer models ⓘ |
| modelParameterCount | 175 billion ⓘ |
| proposes | GPT-3 NERFINISHED ⓘ |
| publicationYear | 2020 ⓘ |
| publishedIn | Proceedings of the 34th Conference on Neural Information Processing Systems NERFINISHED ⓘ |
| publisher | NeurIPS 2020 NERFINISHED ⓘ |
| shows | performance scaling with model size across many NLP tasks ⓘ |
| taskTypesEvaluated |
cloze tasks
ⓘ
commonsense reasoning ⓘ question answering ⓘ reading comprehension ⓘ translation ⓘ |
| title | Language Models are Few-Shot Learners NERFINISHED ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Language Models are Few-Shot Learners Description of subject: "Language Models are Few-Shot Learners" is a landmark research paper that demonstrated large-scale transformer-based language models can perform diverse tasks from just a few examples without task-specific training.
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.
subject surface form:
Tom B. Brown
subject surface form:
GPT-3