Development of Cognitive Intelligence in Pre-trained Language Models
- URL: http://arxiv.org/abs/2407.01047v3
- Date: Fri, 12 Jul 2024 05:47:31 GMT
- Title: Development of Cognitive Intelligence in Pre-trained Language Models
- Authors: Raj Sanjay Shah, Khushi Bhardwaj, Sashank Varma,
- Abstract summary: Recent studies show evidence for emergent cognitive abilities in Large Pre-trained Language Models.
The developmental trajectories of PLMs consistently exhibit a window of maximal alignment to human cognitive development.
After that window, training appears to serve the engineering goal of reducing loss but not the scientific goal of increasing alignment with human cognition.
- Score: 3.1815791977708834
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Recent studies show evidence for emergent cognitive abilities in Large Pre-trained Language Models (PLMs). The increasing cognitive alignment of these models has made them candidates for cognitive science theories. Prior research into the emergent cognitive abilities of PLMs has largely been path-independent to model training, i.e., has focused on the final model weights and not the intermediate steps. However, building plausible models of human cognition using PLMs would benefit from considering the developmental alignment of their performance during training to the trajectories of children's thinking. Guided by psychometric tests of human intelligence, we choose four sets of tasks to investigate the alignment of ten popular families of PLMs and evaluate their available intermediate and final training steps. These tasks are Numerical ability, Linguistic abilities, Conceptual understanding, and Fluid reasoning. We find a striking regularity: regardless of model size, the developmental trajectories of PLMs consistently exhibit a window of maximal alignment to human cognitive development. Before that window, training appears to endow "blank slate" models with the requisite structure to be poised to rapidly learn from experience. After that window, training appears to serve the engineering goal of reducing loss but not the scientific goal of increasing alignment with human cognition.
Related papers
- PersLLM: A Personified Training Approach for Large Language Models [63.75008885222351]
We propose PersLLM, integrating psychology-grounded principles of personality: social practice, consistency, and dynamic development.
We incorporate personality traits directly into the model parameters, enhancing the model's resistance to induction, promoting consistency, and supporting the dynamic evolution of personality.
arXiv Detail & Related papers (2024-07-17T08:13:22Z) - Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice [4.029252551781513]
We propose a novel way to enhance the utility of Large Language Models as cognitive models.
We show that an LLM pretrained on an ecologically valid arithmetic dataset, predicts human behavior better than many traditional cognitive models.
arXiv Detail & Related papers (2024-05-29T17:37:14Z) - Exploring the LLM Journey from Cognition to Expression with Linear Representations [10.92882688742428]
This paper presents an in-depth examination of the evolution and interplay of cognitive and expressive capabilities in large language models (LLMs)
We define and explore the model's cognitive and expressive capabilities through linear representations across three critical phases: Pretraining, Supervised Fine-Tuning (SFT), and Reinforcement Learning from Human Feedback (RLHF)
Our findings unveil a sequential development pattern, where cognitive abilities are largely established during Pretraining, whereas expressive abilities predominantly advance during SFT and RLHF.
arXiv Detail & Related papers (2024-05-27T08:57:04Z) - ConcEPT: Concept-Enhanced Pre-Training for Language Models [57.778895980999124]
ConcEPT aims to infuse conceptual knowledge into pre-trained language models.
It exploits external entity concept prediction to predict the concepts of entities mentioned in the pre-training contexts.
Results of experiments show that ConcEPT gains improved conceptual knowledge with concept-enhanced pre-training.
arXiv Detail & Related papers (2024-01-11T05:05:01Z) - Interpreting Pretrained Language Models via Concept Bottlenecks [55.47515772358389]
Pretrained language models (PLMs) have made significant strides in various natural language processing tasks.
The lack of interpretability due to their black-box'' nature poses challenges for responsible implementation.
We propose a novel approach to interpreting PLMs by employing high-level, meaningful concepts that are easily understandable for humans.
arXiv Detail & Related papers (2023-11-08T20:41:18Z) - On the Unexpected Abilities of Large Language Models [0.0]
Large Language Models (LLMs) are capable of displaying a wide range of abilities that are not directly connected with the task for which they are trained.
I discuss the nature of the indirect process that leads to the acquisition of these cognitive abilities, their relation to other indirect processes, and the implications for the acquisition of integrated abilities.
arXiv Detail & Related papers (2023-08-09T09:15:07Z) - Artificial Neuropsychology: Are Large Language Models Developing
Executive Functions? [0.0]
We evaluate the planning function and working memory of GPT using the popular Towers of Hanoi method.
Preliminary results show that LLMs generates near-optimal solutions in Towers of Hanoi related tasks.
These abilities are quite limited and worse than well-trained humans when the tasks are not known.
arXiv Detail & Related papers (2023-05-06T20:53:22Z) - Define, Evaluate, and Improve Task-Oriented Cognitive Capabilities for
Instruction Generation Models [5.975913042883176]
Recent work studies the cognitive capabilities of language models through psychological tests designed for humans.
We formulate task-oriented cognitive capabilities, which are human-like cognitive capabilities that language models leverage to perform tasks.
arXiv Detail & Related papers (2022-12-21T04:43:19Z) - Learning Theory of Mind via Dynamic Traits Attribution [59.9781556714202]
We propose a new neural ToM architecture that learns to generate a latent trait vector of an actor from the past trajectories.
This trait vector then multiplicatively modulates the prediction mechanism via a fast weights' scheme in the prediction neural network.
We empirically show that the fast weights provide a good inductive bias to model the character traits of agents and hence improves mindreading ability.
arXiv Detail & Related papers (2022-04-17T11:21:18Z) - AGENT: A Benchmark for Core Psychological Reasoning [60.35621718321559]
Intuitive psychology is the ability to reason about hidden mental variables that drive observable actions.
Despite recent interest in machine agents that reason about other agents, it is not clear if such agents learn or hold the core psychology principles that drive human reasoning.
We present a benchmark consisting of procedurally generated 3D animations, AGENT, structured around four scenarios.
arXiv Detail & Related papers (2021-02-24T14:58:23Z) - Pretrained Language Model Embryology: The Birth of ALBERT [68.5801642674541]
We investigate the developmental process from a set of randomly parameters to a totipotent language model.
Our results show that ALBERT learns to reconstruct and predict tokens of different parts of speech (POS) in different learning speeds during pretraining.
These findings suggest that knowledge of a pretrained model varies during pretraining, and having more pretrain steps does not necessarily provide a model with more comprehensive knowledge.
arXiv Detail & Related papers (2020-10-06T05:15:39Z)
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.