Human-like property induction is a challenge for large language models
CogSci'22, 2022.
- from
- AGI & CoCoSci
- added
- 2026-10-10
- likes
- 0
similar
-
Fast and flexible: Human program induction in abstract reasoning tasks arxiv.org
CogSci'21, 2021. [All Versions].
-
Synthesizing theories of human language with Bayesian program induction cap.csail.mit.edu
Nature Communications, 2022. [All Versions].
-
Human-level concept learning through probabilistic program induction science.org
Science, 2015. [All Versions]. [Preprint]. [Supplementary Material]. People learning new concepts can often generalize successfully from just a single example, yet machine learning algorithms typically require tens or hundreds of examples to perform with similar accuracy…
-
Pragmatically Informative Image Captioning with Character-Level Inference cocolab.stanford.edu
NAACL'18, 2018. [All Versions].
-
Synthesizing theories of human language with Bayesian program induction nature.com
Nature Communications, 2022. [All Versions]. Automated, data-driven construction and evaluation of scientific models and theories is a long-standing challenge in artificial intelligence. This work presents a framework for algorithmically synthesizing models of a basic part of…
-
Generating new concepts with hybrid neuro-symbolic models. arxiv.org
CogSci'20, 2020. [All Versions].
AGI & CoCoSci › Papers > Commonsense > AI Commonsense Reasoning: “CogSci'22, 2022.”