Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hussain, Zak, Mata, Rui, Newell, Ben R., Wulff, Dirk U.
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2412.04936
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910730845945856
author Hussain, Zak
Mata, Rui
Newell, Ben R.
Wulff, Dirk U.
author_facet Hussain, Zak
Mata, Rui
Newell, Ben R.
Wulff, Dirk U.
contents Semantic representations are integral to natural language processing, psycholinguistics, and artificial intelligence. Although often derived from internet text, recent years have seen a rise in the popularity of behavior-based (e.g., free associations) and brain-based (e.g., fMRI) representations, which promise improvements in our ability to measure and model human representations. We carry out the first systematic evaluation of the similarities and differences between semantic representations derived from text, behavior, and brain data. Using representational similarity analysis, we show that word vectors derived from behavior and brain data encode information that differs from their text-derived cousins. Furthermore, drawing on our psychNorms metabase, alongside an interpretability method that we call representational content analysis, we find that, in particular, behavior representations capture unique variance on certain affective, agentic, and socio-moral dimensions. We thus establish behavior as an important complement to text for capturing human representations and behavior. These results are broadly relevant to research aimed at learning human-aligned semantic representations, including work on evaluating and aligning large language models.
format Preprint
id arxiv_https___arxiv_org_abs_2412_04936
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Probing the contents of semantic representations from text, behavior, and brain data using the psychNorms metabase
Hussain, Zak
Mata, Rui
Newell, Ben R.
Wulff, Dirk U.
Computation and Language
Artificial Intelligence
Machine Learning
Semantic representations are integral to natural language processing, psycholinguistics, and artificial intelligence. Although often derived from internet text, recent years have seen a rise in the popularity of behavior-based (e.g., free associations) and brain-based (e.g., fMRI) representations, which promise improvements in our ability to measure and model human representations. We carry out the first systematic evaluation of the similarities and differences between semantic representations derived from text, behavior, and brain data. Using representational similarity analysis, we show that word vectors derived from behavior and brain data encode information that differs from their text-derived cousins. Furthermore, drawing on our psychNorms metabase, alongside an interpretability method that we call representational content analysis, we find that, in particular, behavior representations capture unique variance on certain affective, agentic, and socio-moral dimensions. We thus establish behavior as an important complement to text for capturing human representations and behavior. These results are broadly relevant to research aimed at learning human-aligned semantic representations, including work on evaluating and aligning large language models.
title Probing the contents of semantic representations from text, behavior, and brain data using the psychNorms metabase
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2412.04936