paper-with-me

Papers

From Words to Worlds: Compositionality for Cognitive Architectures

2024-07-18 · Ruchira Dhar, Anders Søgaard

Large language models (LLMs) are very performant connectionist systems, but do they exhibit more compositionality? More importantly, is that part of why they perform so well? We present empirical analyses across four LLM families (12 models) and three task categories, including a novel task introduced below. Our findings reveal a nuanced relationship in learning of compositional strategies by LLMs -- while scaling enhances compositional abilities, instruction tuning often has a reverse effect. Such disparity brings forth some open issues regarding the development and improvement of large language models in alignment with human cognitive capacities.

📄 PDF Abstract BibTeX arXiv:2407.13419

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Design for a Darwinian Brain: Part 1. Philosophy and Neuroscience

2013-03-28 · Chrisantha Fernando

Physical symbol systems are needed for open-ended cognition. A good way to understand physical symbol systems is by comparison of thought to chemistry. Both have systematicity, productivity and compositionality. The stat…

Philosophy

AOGNets: Compositional Grammatical Architectures for Deep Learning

2017-11-15 · CVPR 2019 6 · Xilai Li, Xi Song, Tianfu Wu

Neural architectures are the foundation for improving performance of deep neural networks (DNNs). This paper presents deep compositional grammatical architectures which harness the best of two worlds: grammar models and …

Adversarial DefenseDeep LearningImage Classificationobject-detection+3

Analyzing Compositionality-Sensitivity of NLI Models

2018-11-16 · Yixin Nie, Yicheng Wang, Mohit Bansal

Success in natural language inference (NLI) should require a model to understand both lexical and compositional semantics. However, through adversarial evaluation, we find that several state-of-the-art models with divers…

DiagnosticNatural Language InferenceSensitivity

Bootstrapping Cognitive Agents with a Large Language Model

2024-02-25 · Feiyu Zhu, Reid Simmons

Large language models contain noisy general knowledge of the world, yet are hard to train or fine-tune. On the other hand cognitive architectures have excellent interpretability and are flexible to update but require a l…

General KnowledgeLanguage ModelingLanguage ModellingLarge Language Model

Contextualized word senses: from attention to compositionality

2023-12-01 · Pablo Gamallo

The neural architectures of language models are becoming increasingly complex, especially that of Transformers, based on the attention mechanism. Although their application to numerous natural language processing tasks h…