Large language models as probes into latent psychology
- URL: http://arxiv.org/abs/2402.04470v2
- Date: Tue, 27 Feb 2024 03:21:04 GMT
- Title: Large language models as probes into latent psychology
- Authors: Zhicheng Lin
- Abstract summary: We argue that language models should be embraced as flexible simulation tools.
The models themselves should not be equated to or anthropomorphized as human minds.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Advances in AI invite the misuse of language models as stand-ins for human
minds or participants, which fundamentally mischaracterizes these statistical
algorithms. We argue that language models should be embraced as flexible
simulation tools, able to mimic a wide range of behaviors, perspectives, and
psychological attributes evident in human language data, but the models
themselves should not be equated to or anthropomorphized as human minds.
Related papers
- Computational Models to Study Language Processing in the Human Brain: A Survey [47.81066391664416]
This paper reviews efforts in using computational models for brain research, highlighting emerging trends.
Our analysis reveals that no single model outperforms others on all datasets.
arXiv Detail & Related papers (2024-03-20T08:01:22Z) - Formal Aspects of Language Modeling [74.16212987886013]
Large language models have become one of the most commonly deployed NLP inventions.
These notes are the accompaniment to the theoretical portion of the ETH Z"urich course on large language models.
arXiv Detail & Related papers (2023-11-07T20:21:42Z) - From Word Models to World Models: Translating from Natural Language to
the Probabilistic Language of Thought [124.40905824051079]
We propose rational meaning construction, a computational framework for language-informed thinking.
We frame linguistic meaning as a context-sensitive mapping from natural language into a probabilistic language of thought.
We show that LLMs can generate context-sensitive translations that capture pragmatically-appropriate linguistic meanings.
We extend our framework to integrate cognitively-motivated symbolic modules.
arXiv Detail & Related papers (2023-06-22T05:14:00Z) - Turning large language models into cognitive models [0.0]
We show that large language models can be turned into cognitive models.
These models offer accurate representations of human behavior, even outperforming traditional cognitive models in two decision-making domains.
Taken together, these results suggest that large, pre-trained models can be adapted to become generalist cognitive models.
arXiv Detail & Related papers (2023-06-06T18:00:01Z) - Language Models are Bounded Pragmatic Speakers: Understanding RLHF from
a Bayesian Cognitive Modeling Perspective [2.8282906214258805]
This paper formulates a probabilistic cognitive model called the bounded pragmatic speaker.
We demonstrate that large language models fine-tuned with reinforcement learning from human feedback embody a model of thought that resembles a fast-and-slow model.
arXiv Detail & Related papers (2023-05-28T16:04:48Z) - Beyond the limitations of any imaginable mechanism: large language
models and psycholinguistics [0.0]
Large language models provide a model for language.
They are useful as a practical tool, as an illustrative comparative, and philosophical, as a basis for recasting the relationship between language and thought.
arXiv Detail & Related papers (2023-02-28T20:49:38Z) - Chain of Hindsight Aligns Language Models with Feedback [62.68665658130472]
We propose a novel technique, Chain of Hindsight, that is easy to optimize and can learn from any form of feedback, regardless of its polarity.
We convert all types of feedback into sequences of sentences, which are then used to fine-tune the model.
By doing so, the model is trained to generate outputs based on feedback, while learning to identify and correct negative attributes or errors.
arXiv Detail & Related papers (2023-02-06T10:28:16Z) - A fine-grained comparison of pragmatic language understanding in humans
and language models [2.231167375820083]
We compare language models and humans on seven pragmatic phenomena.
We find that the largest models achieve high accuracy and match human error patterns.
Preliminary evidence that models and humans are sensitive to similar linguistic cues.
arXiv Detail & Related papers (2022-12-13T18:34:59Z) - What Artificial Neural Networks Can Tell Us About Human Language
Acquisition [47.761188531404066]
Rapid progress in machine learning for natural language processing has the potential to transform debates about how humans learn language.
To increase the relevance of learnability results from computational models, we need to train model learners without significant advantages over humans.
arXiv Detail & Related papers (2022-08-17T00:12:37Z) - Estimating the Personality of White-Box Language Models [0.589889361990138]
Large-scale language models, which are trained on large corpora of text, are being used in a wide range of applications everywhere.
Existing research shows that these models can and do capture human biases.
Many of these biases, especially those that could potentially cause harm, are being well-investigated.
However, studies that infer and change human personality traits inherited by these models have been scarce or non-existent.
arXiv Detail & Related papers (2022-04-25T23:53:53Z) - Scaling Language Models: Methods, Analysis & Insights from Training
Gopher [83.98181046650664]
We present an analysis of Transformer-based language model performance across a wide range of model scales.
Gains from scale are largest in areas such as reading comprehension, fact-checking, and the identification of toxic language.
We discuss the application of language models to AI safety and the mitigation of downstream harms.
arXiv Detail & Related papers (2021-12-08T19:41:47Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.