1 |
Finding the best way to put media bias research into practice via an annotation app ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Are neural language models sensitive to false belief? A computational study. ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Structured, flexible, and robust: comparing linguistic plans and explanations generated by humans and large language models ...
|
|
|
|
Abstract:
How much can be learned about the structure of thinking from the statistics of language alone? Large language models -- neural models trained on next-word prediction tasks over large corpuses of text -- have made striking advances in modeling the statistical distribution of language. Sufficiently large corpuses contain language in which humans describe their beliefs and intentions, their goals and plans, and their stories about occurrences in real and imaginary worlds. Richly structured cognitive processes underlie this language that we produce; however, can such structure be captured when modeling distributional co-occurance of words alone? Is language modeling alone sufficiently flexible, accurate, and robust enough to generate language for novel, out-of-distribution queries, or are model-based approaches needed? In this study, we compare human and large-language-model performance on two domains which draw on structured, model-based thinking: 1) goal-based planning, and 2) explanation generation for causal ...
|
|
Keyword:
Artificial Intelligence and Robotics; Computer Sciences; GPT-3; Language Models; Natural Language Processing; Physical Sciences and Mathematics; Planning
|
|
URL: https://dx.doi.org/10.17605/osf.io/cy72b https://osf.io/cy72b/
|
|
BASE
|
|
Hide details
|
|
4 |
Similarity between person roles in a card sorting experiment ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Can distributional semantics explain performance on the false belief task? ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Characterizing News Portrayal of Civil Unrest in Hong Kong, 1998–2020 ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Measuring Semantic Similarity of Documents by Using Named Entity Recognition Methods
|
|
|
|
In: Masters (2022)
|
|
BASE
|
|
Show details
|
|
10 |
Realistic motion avatars are the future for social interaction in virtual reality
|
|
|
|
In: Research outputs 2022 to 2026 (2022)
|
|
BASE
|
|
Show details
|
|
11 |
Machine infelicity in a poignant visitor setting: Comparing human and AI’s ability to analyze discourse
|
|
|
|
In: Research outputs 2014 to 2021 (2022)
|
|
BASE
|
|
Show details
|
|
12 |
Pharyngeal Constriction as a Cause for Late Acquisition and Speech Sound Disorders of Rhotic Sounds in English, Spanish, and French
|
|
|
|
In: The Downtown Review (2021)
|
|
BASE
|
|
Show details
|
|
14 |
Development of language and the use of musical engagement as a stress coping mechanism during the COVID-19 pandemic ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Measuring Equity Mindsets and Improvisational Practices Through Language Patterns in Equity Simulations ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
A causal eco-industrial park hierarchical transition model with qualitative information: Policy and regulatory framework leads to collaboration among firms
|
|
|
|
In: Research outputs 2014 to 2021 (2021)
|
|
BASE
|
|
Show details
|
|
18 |
Early and Late Implication of Subcortical Brain Structures in Speech Motor Sequence Learning: a Pre-registered fMRI Study ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|