Why Do We Need Neuro-symbolic AI to Model Pragmatic Analogies?

• URL: http://arxiv.org/abs/2308.01936v2
• Date: Tue, 12 Sep 2023 16:33:15 GMT
• Title: Why Do We Need Neuro-symbolic AI to Model Pragmatic Analogies?
• Authors: Thilini Wijesiriwardene and Amit Sheth and Valerie L. Shalin and Amitava Das
• Abstract summary: A hallmark of intelligence is the ability to use a familiar domain to make inferences about a less familiar domain, known as analogical reasoning. We discuss analogies at four distinct levels of complexity: lexical analogies, syntactic analogies, semantic analogies, and pragmatic analogies. We employ Neuro-symbolic AI techniques that combine statistical and symbolic AI, informing the representation of unstructured text to highlight and augment relevant content, provide abstraction and guide the mapping process.
• Score: 6.8107181513711055
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A hallmark of intelligence is the ability to use a familiar domain to make inferences about a less familiar domain, known as analogical reasoning. In this article, we delve into the performance of Large Language Models (LLMs) in dealing with progressively complex analogies expressed in unstructured text. We discuss analogies at four distinct levels of complexity: lexical analogies, syntactic analogies, semantic analogies, and pragmatic analogies. As the analogies become more complex, they require increasingly extensive, diverse knowledge beyond the textual content, unlikely to be found in the lexical co-occurrence statistics that power LLMs. To address this, we discuss the necessity of employing Neuro-symbolic AI techniques that combine statistical and symbolic AI, informing the representation of unstructured text to highlight and augment relevant content, provide abstraction and guide the mapping process. Our knowledge-informed approach maintains the efficiency of LLMs while preserving the ability to explain analogies for pedagogical applications.

Related papers

• Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents [55.63497537202751]
  Article explores the convergence of connectionist and symbolic artificial intelligence (AI) Traditionally, connectionist AI focuses on neural networks, while symbolic AI emphasizes symbolic representation and logic. Recent advancements in large language models (LLMs) highlight the potential of connectionist architectures in handling human language as a form of symbols.
  arXiv  Detail & Related papers  (2024-07-11T14:00:53Z)
• Explaining Text Similarity in Transformer Models [52.571158418102584]
  Recent advances in explainable AI have made it possible to mitigate limitations by leveraging improved explanations for Transformers. We use BiLRP, an extension developed for computing second-order explanations in bilinear similarity models, to investigate which feature interactions drive similarity in NLP models. Our findings contribute to a deeper understanding of different semantic similarity tasks and models, highlighting how novel explainable AI methods enable in-depth analyses and corpus-level insights.
  arXiv  Detail & Related papers  (2024-05-10T17:11:31Z)
• StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding [72.38872974837462]
  We evaluate the ability to identify and generate analogies by constructing a first-of-its-kind large-scale story-level analogy corpus. textscStory Analogy contains 24K story pairs from diverse domains with human annotations on two similarities from the extended Structure-Mapping Theory. We observe that the data in textscStory Analogy can improve the quality of analogy generation in large language models.
  arXiv  Detail & Related papers  (2023-10-19T16:29:23Z)
• On the Relationship between Sentence Analogy Identification and Sentence Structure Encoding in Large Language Models [7.716762867270514]
  We look at how Large Language Models' abilities to capture sentence analogies vary with their abilities to encode syntactic and semantic structures. We find that the LLMs which capture syntactic structures better, also have higher abilities in identifying sentence analogies.
  arXiv  Detail & Related papers  (2023-10-11T18:59:48Z)
• ARN: Analogical Reasoning on Narratives [13.707344123755126]
  We develop a framework that operationalizes dominant theories of analogy, using narrative elements to create surface and system mappings. We show that while all LLMs can largely recognize near analogies, even the largest ones struggle with far analogies in a zero-shot setting.
  arXiv  Detail & Related papers  (2023-10-02T08:58:29Z)
• Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension [80.99865844249106]
  We propose a holistic graph network (HGN) which deals with context at both discourse level and word level, as the basis for logical reasoning. Specifically, node-level and type-level relations, which can be interpreted as bridges in the reasoning process, are modeled by a hierarchical interaction mechanism.
  arXiv  Detail & Related papers  (2023-06-21T07:34:27Z)
• Beneath Surface Similarity: Large Language Models Make Reasonable Scientific Analogies after Structure Abduction [46.2032673640788]
  The vital role of analogical reasoning in human cognition allows us to grasp novel concepts by linking them with familiar ones through shared relational structures. This work suggests that Large Language Models (LLMs) often overlook the structures that underpin these analogies. This paper introduces a task of analogical structure abduction, grounded in cognitive psychology, designed to abduce structures that form an analogy between two systems.
  arXiv  Detail & Related papers  (2023-05-22T03:04:06Z)
• 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)
• Scientific and Creative Analogies in Pretrained Language Models [24.86477727507679]
  This paper examines the encoding of analogy in large-scale pretrained language models, such as BERT and GPT-2. We introduce the Scientific and Creative Analogy dataset (SCAN), a novel analogy dataset containing systematic mappings of multiple attributes and relational structures across dissimilar domains. We find that state-of-the-art LMs achieve low performance on these complex analogy tasks, highlighting the challenges still posed by analogy understanding.
  arXiv  Detail & Related papers  (2022-11-28T12:49:44Z)
• Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes [12.8252101640812]
  Much research has suggested that analogies are key to non-brittle systems that can adapt to new domains. Despite their importance, analogies received little attention in the NLP community.
  arXiv  Detail & Related papers  (2022-10-21T18:54:17Z)
• Understanding Narratives through Dimensions of Analogy [17.68704739786042]
  Analogical reasoning is a powerful tool that enables humans to connect two situations, and to generalize their knowledge from familiar to novel situations. Modern scalable AI techniques with the potential to reason by analogy have been only applied to the special case of proportional analogy. In this paper, we aim to bridge the gap by: 1) formalizing six dimensions of analogy based on mature insights from Cognitive Science research, 2) annotating a corpus of fables with each of these dimensions, and 3) defining four tasks with increasing complexity that enable scalable evaluation of AI techniques.
  arXiv  Detail & Related papers  (2022-06-14T20:56:26Z)

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.