Large Language Models as a Tool for Mining Object Knowledge

• URL: http://arxiv.org/abs/2410.12959v1
• Date: Wed, 16 Oct 2024 18:46:02 GMT
• Title: Large Language Models as a Tool for Mining Object Knowledge
• Authors: Hannah YoungEun An, Lenhart K. Schubert,
• Abstract summary: Large language models fall short as trustworthy intelligent systems due to opacity of basis for their answers and tendency to confabulate facts when questioned. This paper investigates explicit knowledge about common artifacts in the everyday world. We produce a repository of data on the parts and materials of about 2,300 objects and their subtypes. This contribution to knowledge mining should prove useful to AI research on reasoning about object structure and composition.
• Score: 0.42970700836450487
• License:
• Abstract: Commonsense knowledge is essential for machines to reason about the world. Large language models (LLMs) have demonstrated their ability to perform almost human-like text generation. Despite this success, they fall short as trustworthy intelligent systems, due to the opacity of the basis for their answers and a tendency to confabulate facts when questioned about obscure entities or technical domains. We hypothesize, however, that their general knowledge about objects in the everyday world is largely sound. Based on that hypothesis, this paper investigates LLMs' ability to formulate explicit knowledge about common physical artifacts, focusing on their parts and materials. Our work distinguishes between the substances that comprise an entire object and those that constitute its parts$\unicode{x2014}$a previously underexplored distinction in knowledge base construction. Using few-shot with five in-context examples and zero-shot multi-step prompting, we produce a repository of data on the parts and materials of about 2,300 objects and their subtypes. Our evaluation demonstrates LLMs' coverage and soundness in extracting knowledge. This contribution to knowledge mining should prove useful to AI research on reasoning about object structure and composition and serve as an explicit knowledge source (analogous to knowledge graphs) for LLMs performing multi-hop question answering.

Related papers

• A Perspective on Large Language Models, Intelligent Machines, and Knowledge Acquisition [0.6138671548064355]
  Large Language Models (LLMs) are known for their remarkable ability to generate 'knowledge' However, there is a huge gap between LLM's and human capabilities for understanding abstract concepts and reasoning. We discuss these issues in a larger philosophical context of human knowledge acquisition and the Turing test.
  arXiv  Detail & Related papers  (2024-08-13T03:25:49Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• POSQA: Probe the World Models of LLMs with Size Comparisons [38.30479784257936]
  Embodied language comprehension emphasizes that language understanding is not solely a matter of mental processing in the brain. With the explosive growth of Large Language Models (LLMs) and their already ubiquitous presence in our daily lives, it is becoming increasingly necessary to verify their real-world understanding.
  arXiv  Detail & Related papers  (2023-10-20T10:05:01Z)
• MechGPT, a language-based strategy for mechanics and materials modeling that connects knowledge across scales, disciplines and modalities [0.0]
  We use a Large Language Model (LLM) to distill question-answer pairs from raw sources followed by fine-tuning. The resulting MechGPT LLM foundation model is used in a series of computational experiments to explore its capacity for knowledge retrieval, various language tasks, hypothesis generation, and connecting knowledge across disparate areas.
  arXiv  Detail & Related papers  (2023-10-16T14:29:35Z)
• Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators [78.63553017938911]
  Large language models (LLMs) outperform information retrieval techniques for downstream knowledge-intensive tasks. However, community concerns abound regarding the factuality and potential implications of using this uncensored knowledge. We introduce CONNER, designed to evaluate generated knowledge from six important perspectives.
  arXiv  Detail & Related papers  (2023-10-11T08:22:37Z)
• Do Large Language Models Know about Facts? [60.501902866946]
  Large language models (LLMs) have recently driven striking performance improvements across a range of natural language processing tasks. We aim to evaluate the extent and scope of factual knowledge within LLMs by designing the benchmark Pinocchio. Pinocchio contains 20K diverse factual questions that span different sources, timelines, domains, regions, and languages.
  arXiv  Detail & Related papers  (2023-10-08T14:26:55Z)
• From task structures to world models: What do LLMs know? [0.0]
  In what sense does a large language model have knowledge? We answer by granting LLMs "instrumental knowledge"; knowledge defined by a certain set of abilities. We then ask how such knowledge is related to the more ordinary, "worldly" knowledge exhibited by human agents, and explore this in terms of the degree to which instrumental knowledge can be said to incorporate the structured world models of cognitive science.
  arXiv  Detail & Related papers  (2023-10-06T14:21:59Z)
• Brain in a Vat: On Missing Pieces Towards Artificial General Intelligence in Large Language Models [83.63242931107638]
  We propose four characteristics of generally intelligent agents. We argue that active engagement with objects in the real world delivers more robust signals for forming conceptual representations. We conclude by outlining promising future research directions in the field of artificial general intelligence.
  arXiv  Detail & Related papers  (2023-07-07T13:58:16Z)
• Do Large Language Models Know What They Don't Know? [74.65014158544011]
  Large language models (LLMs) have a wealth of knowledge that allows them to excel in various Natural Language Processing (NLP) tasks. Despite their vast knowledge, LLMs are still limited by the amount of information they can accommodate and comprehend. This study aims to evaluate LLMs' self-knowledge by assessing their ability to identify unanswerable or unknowable questions.
  arXiv  Detail & Related papers  (2023-05-29T15:30:13Z)
• Learning by Asking Questions for Knowledge-based Novel Object Recognition [64.55573343404572]
  In real-world object recognition, there are numerous object classes to be recognized. Conventional image recognition based on supervised learning can only recognize object classes that exist in the training data, and thus has limited applicability in the real world. Inspired by this, we study a framework for acquiring external knowledge through question generation that would help the model instantly recognize novel objects. Our pipeline consists of two components: the Object-based object recognition, and the Question Generator, which generates knowledge-aware questions to acquire novel knowledge.
  arXiv  Detail & Related papers  (2022-10-12T02:51:58Z)

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.