Epistemology of Language Models: Do Language Models Have Holistic Knowledge?

• URL: http://arxiv.org/abs/2403.12862v1
• Date: Tue, 19 Mar 2024 16:06:10 GMT
• Title: Epistemology of Language Models: Do Language Models Have Holistic Knowledge?
• Authors: Minsu Kim, James Thorne,
• Abstract summary: This paper investigates the inherent knowledge in language models from the perspective of holism. The purpose of this paper is to explore whether characteristics of language models exhibit consistent with holism.
• Score: 30.02796959216552
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper investigates the inherent knowledge in language models from the perspective of epistemological holism. The purpose of this paper is to explore whether LLMs exhibit characteristics consistent with epistemological holism. These characteristics suggest that core knowledge, such as general scientific knowledge, each plays a specific role, serving as the foundation of our knowledge system and being difficult to revise. To assess these traits related to holism, we created a scientific reasoning dataset and examined the epistemology of language models through three tasks: Abduction, Revision, and Argument Generation. In the abduction task, the language models explained situations while avoiding revising the core knowledge. However, in other tasks, the language models were revealed not to distinguish between core and peripheral knowledge, showing an incomplete alignment with holistic knowledge principles.

Related papers

• Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning [84.94709351266557]
  We focus on the trustworthiness of language models with respect to retrieval augmentation. We deem that retrieval-augmented language models have the inherent capabilities of supplying response according to both contextual and parametric knowledge. Inspired by aligning language models with human preference, we take the first step towards aligning retrieval-augmented language models to a status where it responds relying merely on the external evidence.
  arXiv  Detail & Related papers  (2024-10-22T09:25:21Z)
• Language Models as Models of Language [0.0]
  This chapter critically examines the potential contributions of modern language models to theoretical linguistics. I review a growing body of empirical evidence suggesting that language models can learn hierarchical syntactic structure and exhibit sensitivity to various linguistic phenomena. I conclude that closer collaboration between theoretical linguists and computational researchers could yield valuable insights.
  arXiv  Detail & Related papers  (2024-08-13T18:26:04Z)
• Modelling Language [0.0]
  This paper argues that large language models have a valuable scientific role to play in serving as scientific models of a language. It draws upon recent work in philosophy of science to show how large language models could serve as scientific models.
  arXiv  Detail & Related papers  (2024-04-15T08:40:01Z)
• Language Evolution with Deep Learning [49.879239655532324]
  Computational modeling plays an essential role in the study of language emergence. It aims to simulate the conditions and learning processes that could trigger the emergence of a structured language. This chapter explores another class of computational models that have recently revolutionized the field of machine learning: deep learning models.
  arXiv  Detail & Related papers  (2024-03-18T16:52:54Z)
• A Philosophical Introduction to Language Models -- Part I: Continuity With Classic Debates [0.05657375260432172]
  This article serves both as a primer on language models for philosophers, and as an opinionated survey of their significance. We argue that the success of language models challenges several long-held assumptions about artificial neural networks. This sets the stage for the companion paper (Part II), which turns to novel empirical methods for probing the inner workings of language models.
  arXiv  Detail & Related papers  (2024-01-08T14:12:31Z)
• On General Language Understanding [18.2932386988379]
  This paper sketches the outlines of a model of understanding, which can ground questions of the adequacy of current methods of measurement of model quality. The paper makes three claims: A) That different language use situation types have different characteristics, B) That language understanding is a multifaceted phenomenon, and C) That the choice of Understanding Indicator marks the limits of benchmarking.
  arXiv  Detail & Related papers  (2023-10-27T10:36:54Z)
• Unveiling A Core Linguistic Region in Large Language Models [49.860260050718516]
  This paper conducts an analogical research using brain localization as a prototype. We have discovered a core region in large language models that corresponds to linguistic competence. We observe that an improvement in linguistic competence does not necessarily accompany an elevation in the model's knowledge level.
  arXiv  Detail & Related papers  (2023-10-23T13:31:32Z)
• Commonsense Knowledge Transfer for Pre-trained Language Models [83.01121484432801]
  We introduce commonsense knowledge transfer, a framework to transfer the commonsense knowledge stored in a neural commonsense knowledge model to a general-purpose pre-trained language model. It first exploits general texts to form queries for extracting commonsense knowledge from the neural commonsense knowledge model. It then refines the language model with two self-supervised objectives: commonsense mask infilling and commonsense relation prediction.
  arXiv  Detail & Related papers  (2023-06-04T15:44:51Z)
• O-Dang! The Ontology of Dangerous Speech Messages [53.15616413153125]
  We present O-Dang!: The Ontology of Dangerous Speech Messages, a systematic and interoperable Knowledge Graph (KG) O-Dang! is designed to gather and organize Italian datasets into a structured KG, according to the principles shared within the Linguistic Linked Open Data community. It provides a model for encoding both gold standard and single-annotator labels in the KG.
  arXiv  Detail & Related papers  (2022-07-13T11:50:05Z)
• Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization [49.00409552570441]
  We study the role of conceptualization in commonsense reasoning, and formulate a framework to replicate human conceptual induction. We apply the framework to ATOMIC, a large-scale human-annotated CKG, aided by the taxonomy Probase.
  arXiv  Detail & Related papers  (2022-06-03T12:24:49Z)
• Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language Understanding [1.827510863075184]
  Curriculum is a new format of NLI benchmark for evaluation of broad-coverage linguistic phenomena. We show that this linguistic-phenomena-driven benchmark can serve as an effective tool for diagnosing model behavior and verifying model learning quality.
  arXiv  Detail & Related papers  (2022-04-13T10:32:03Z)

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.