Getting aligned on representational alignment
Biological and artificial information processing systems form representations that they can
use to categorize, reason, plan, navigate, and make decisions. How can we measure the …
use to categorize, reason, plan, navigate, and make decisions. How can we measure the …
Alignment with human representations supports robust few-shot learning
I Sucholutsky, T Griffiths - Advances in Neural Information …, 2024 - proceedings.neurips.cc
Should we care whether AI systems have representations of the world that are similar to
those of humans? We provide an information-theoretic analysis that suggests that there …
those of humans? We provide an information-theoretic analysis that suggests that there …
Gromov–Wasserstein unsupervised alignment reveals structural correspondences between the color similarity structures of humans and large language models
Abstract Large Language Models (LLMs), such as the General Pre-trained Transformer
(GPT), have shown remarkable performance in various cognitive tasks. However, it remains …
(GPT), have shown remarkable performance in various cognitive tasks. However, it remains …
Comparing color similarity structures between humans and LLMs via unsupervised alignment
G Kawakita, A Zeleznikow-Johnston… - arXiv preprint arXiv …, 2023 - arxiv.org
Large language models (LLMs), such as the General Pre-trained Transformer (GPT), have
shown remarkable performance in various cognitive tasks. However, it remains unclear …
shown remarkable performance in various cognitive tasks. However, it remains unclear …
Words are all you need? Language as an approximation for human similarity judgments
Human similarity judgments are a powerful supervision signal for machine learning
applications based on techniques such as contrastive learning, information retrieval, and …
applications based on techniques such as contrastive learning, information retrieval, and …
Conceptual structure coheres in human cognition but not in large language models
Neural network models of language have long been used as a tool for developing
hypotheses about conceptual representation in the mind and brain. For many years, such …
hypotheses about conceptual representation in the mind and brain. For many years, such …
[PDF][PDF] Words are all you need? capturing human sensory similarity with textual descriptors
Recent advances in multimodal training use textual descriptions to significantly enhance
machine understanding of images and videos. Yet, it remains unclear to what extent …
machine understanding of images and videos. Yet, it remains unclear to what extent …
Analyzing the roles of language and vision in learning from limited data
A Chen, I Sucholutsky, O Russakovsky… - arXiv preprint arXiv …, 2024 - arxiv.org
Does language help make sense of the visual world? How important is it to actually see the
world rather than having it described with words? These basic questions about the nature of …
world rather than having it described with words? These basic questions about the nature of …
Learning human-like representations to enable learning human values
AH Wynn - 2024 - search.proquest.com
How can we build AI systems that can learn any set of individual human values both quickly
and safely, avoiding causing harm or violating societal standards for acceptable behavior …
and safely, avoiding causing harm or violating societal standards for acceptable behavior …
Text encoders lack knowledge: Leveraging generative llms for domain-specific semantic textual similarity
Amidst the sharp rise in the evaluation of large language models (LLMs) on various tasks,
we find that semantic textual similarity (STS) has been under-explored. In this study, we …
we find that semantic textual similarity (STS) has been under-explored. In this study, we …