BERT is to NLP what AlexNet is to CV: Can pre-trained language models identify analogies?
Analogies play a central role in human commonsense reasoning. The ability to recognize
analogies such as" eye is to seeing what ear is to hearing", sometimes referred to as …
analogies such as" eye is to seeing what ear is to hearing", sometimes referred to as …
The linear representation hypothesis and the geometry of large language models
Informally, the'linear representation hypothesis' is the idea that high-level concepts are
represented linearly as directions in some representation space. In this paper, we address …
represented linearly as directions in some representation space. In this paper, we address …
Analogykb: Unlocking analogical reasoning of language models with a million-scale knowledge base
Analogical reasoning is a fundamental cognitive ability of humans. However, current
language models (LMs) still struggle to achieve human-like performance in analogical …
language models (LMs) still struggle to achieve human-like performance in analogical …
Beneath surface similarity: Large language models make reasonable scientific analogies after structure abduction
The vital role of analogical reasoning in human cognition allows us to grasp novel concepts
by linking them with familiar ones through shared relational structures. Despite the attention …
by linking them with familiar ones through shared relational structures. Despite the attention …
[PDF][PDF] Understanding and fixing the modality gap in vision-language models
V Udandarao - Master's thesis, University of Cambridge, 2022 - mlmi.eng.cam.ac.uk
Contrastive language-image pre-training has emerged to be a simple yet effective way to
train largescale vision-language models [165, 83, 181, 220] that are capable of learning …
train largescale vision-language models [165, 83, 181, 220] that are capable of learning …
Rumor detection in social media based on multi-hop graphs and differential time series
J Chen, W Zhang, H Ma, S Yang - Mathematics, 2023 - mdpi.com
The widespread dissemination of rumors (fake information) on online social media has had
a detrimental impact on public opinion and the social environment. This necessitates the …
a detrimental impact on public opinion and the social environment. This necessitates the …
Contrastive loss is all you need to recover analogies as parallel lines
While static word embedding models are known to represent linguistic analogies as parallel
lines in high-dimensional space, the underlying mechanism as to why they result in such …
lines in high-dimensional space, the underlying mechanism as to why they result in such …
Past Meets Present: Creating Historical Analogy with Large Language Models
Historical analogies, which compare known past events with contemporary but unfamiliar
events, are important abilities that help people make decisions and understand the world …
events, are important abilities that help people make decisions and understand the world …
[PDF][PDF] Compositionality of complex graphemes in the undeciphered Proto-Elamite script using image and text embedding models
We introduce a language modeling architecture which operates over sequences of images,
or over multimodal sequences of images with associated labels. We use this architecture …
or over multimodal sequences of images with associated labels. We use this architecture …
[PDF][PDF] Forging better axes: Evaluating and improving the measurement of semantic dimensions in word embeddings
A Boutyline, E Johnston - Retrieved from osf. io/preprints/socarxiv/576h3, 2023 - files.osf.io
Word embeddings are a powerful tool for measuring cultural meaning using large text
corpora. In sociology, some of their most common applications estimate relationships …
corpora. In sociology, some of their most common applications estimate relationships …