Human-like Category Learning by Injecting Ecological Priors from Large Language Models into Neural Networks

• URL: http://arxiv.org/abs/2402.01821v2
• Date: Tue, 28 May 2024 07:40:53 GMT
• Title: Human-like Category Learning by Injecting Ecological Priors from Large Language Models into Neural Networks
• Authors: Akshay K. Jagadish, Julian Coda-Forno, Mirko Thalmann, Eric Schulz, Marcel Binz,
• Abstract summary: We develop a class of models called ecologically rational meta-learned inference (ERMI) ERMI quantitatively explains human data better than seven other cognitive models in two different experiments. We show that ERMI's ecologically valid priors allow it to achieve state-of-the-art performance on the OpenML-CC18 classification benchmark.
• Score: 8.213829427624407
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Ecological rationality refers to the notion that humans are rational agents adapted to their environment. However, testing this theory remains challenging due to two reasons: the difficulty in defining what tasks are ecologically valid and building rational models for these tasks. In this work, we demonstrate that large language models can generate cognitive tasks, specifically category learning tasks, that match the statistics of real-world tasks, thereby addressing the first challenge. We tackle the second challenge by deriving rational agents adapted to these tasks using the framework of meta-learning, leading to a class of models called ecologically rational meta-learned inference (ERMI). ERMI quantitatively explains human data better than seven other cognitive models in two different experiments. It additionally matches human behavior on a qualitative level: (1) it finds the same tasks difficult that humans find difficult, (2) it becomes more reliant on an exemplar-based strategy for assigning categories with learning, and (3) it generalizes to unseen stimuli in a human-like way. Furthermore, we show that ERMI's ecologically valid priors allow it to achieve state-of-the-art performance on the OpenML-CC18 classification benchmark.

Related papers

• System 2 Reasoning via Generality and Adaptation [5.806160172544203]
  This paper explores the limitations of existing approaches in achieving advanced System 2 reasoning. We propose four key research directions to address these gaps. We aim to advance the ability to generalize and adapt, bringing computational models closer to the reasoning capabilities required for Artificial General Intelligence (AGI)
  arXiv  Detail & Related papers  (2024-10-10T12:34:25Z)
• Blocks as Probes: Dissecting Categorization Ability of Large Multimodal Models [31.47100708645748]
  Recent development of Large Multimodal Models (LMMs) has demonstrated impressive results in high-level visual tasks. We propose a novel, challenging, and efficient benchmark based on composite blocks, called ComBo, which provides a disentangled evaluation framework. We find that although LMMs exhibit acceptable generalization ability in learning new categories, there are still gaps compared to humans in many ways.
  arXiv  Detail & Related papers  (2024-09-03T02:55:36Z)
• 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)
• Ontology Completion with Natural Language Inference and Concept Embeddings: An Analysis [26.918368764004796]
  We consider the problem of finding plausible knowledge that is missing from a given ontology, as a generalisation of the well-studied taxonomy expansion task. One line of work treats this task as a Natural Language Inference (NLI) problem, relying on the knowledge captured by language models to identify the missing knowledge. Another line of work uses concept embeddings to identify what different concepts have in common, taking inspiration from cognitive models for category based induction.
  arXiv  Detail & Related papers  (2024-03-25T21:46:35Z)
• Can Foundation Models Watch, Talk and Guide You Step by Step to Make a Cake? [62.59699229202307]
  Despite advances in AI, it remains a significant challenge to develop interactive task guidance systems. We created a new multimodal benchmark dataset, Watch, Talk and Guide (WTaG) based on natural interaction between a human user and a human instructor. We leveraged several foundation models to study to what extent these models can be quickly adapted to perceptually enabled task guidance.
  arXiv  Detail & Related papers  (2023-11-01T15:13:49Z)
• User Behavior Simulation with Large Language Model based Agents [116.74368915420065]
  We propose an LLM-based agent framework and design a sandbox environment to simulate real user behaviors. Based on extensive experiments, we find that the simulated behaviors of our method are very close to the ones of real humans.
  arXiv  Detail & Related papers  (2023-06-05T02:58:35Z)
• ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base [51.777618249271725]
  ANALOGYKB is a million-scale analogy knowledge base derived from existing knowledge graphs (KGs) It identifies two types of analogies from the KGs: 1) analogies of the same relations, which can be directly extracted from the KGs, and 2) analogies of analogous relations, which are identified with a selection and filtering pipeline enabled by large language models (LLMs)
  arXiv  Detail & Related papers  (2023-05-10T09:03:01Z)
• Modelling human logical reasoning process in dynamic environmental stress with cognitive agents [13.171768256928509]
  We propose a cognitive agent integrating drift-diffusion with deep reinforcement learning to simulate granular stress effects on logical reasoning process. Leveraging a large dataset of 21,157 logical responses, we investigate performance impacts of dynamic stress. Quantitatively, the framework improves cognition modelling by capturing both subject-specific and stimuli-specific behavioural differences. Overall, this work demonstrates a powerful, data-driven methodology to simulate and understand the vagaries of human logical reasoning process in dynamic contexts.
  arXiv  Detail & Related papers  (2023-01-15T23:46:37Z)
• Autonomous Reinforcement Learning: Formalism and Benchmarking [106.25788536376007]
  Real-world embodied learning, such as that performed by humans and animals, is situated in a continual, non-episodic world. Common benchmark tasks in RL are episodic, with the environment resetting between trials to provide the agent with multiple attempts. This discrepancy presents a major challenge when attempting to take RL algorithms developed for episodic simulated environments and run them on real-world platforms.
  arXiv  Detail & Related papers  (2021-12-17T16:28:06Z)
• Task-Agnostic Morphology Evolution [94.97384298872286]
  Current approaches that co-adapt morphology and behavior use a specific task's reward as a signal for morphology optimization. This often requires expensive policy optimization and results in task-dependent morphologies that are not built to generalize. We propose a new approach, Task-Agnostic Morphology Evolution (TAME), to alleviate both of these issues.
  arXiv  Detail & Related papers  (2021-02-25T18:59:21Z)
• Machine Common Sense [77.34726150561087]
  Machine common sense remains a broad, potentially unbounded problem in artificial intelligence (AI) This article deals with the aspects of modeling commonsense reasoning focusing on such domain as interpersonal interactions.
  arXiv  Detail & Related papers  (2020-06-15T13:59:47Z)

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.