Relational Schemata in BERT Are Inducible, Not Emergent: A Study of Performance vs. Competence in Language Models

• URL: http://arxiv.org/abs/2506.11485v1
• Date: Fri, 13 Jun 2025 06:20:03 GMT
• Title: Relational Schemata in BERT Are Inducible, Not Emergent: A Study of Performance vs. Competence in Language Models
• Authors: Cole Gawin,
• Abstract summary: I investigate whether BERT encodes abstract relational schemata by examining internal representations of concept pairs across taxonomic, mereological, and functional relations.<n>Results reveal that pretrained BERT enables classification accuracy, indicating latent relational signals.<n>These findings demonstrate that behavioral performance does not necessarily imply structured conceptual understanding, though models can acquire inductive biases for grounded relational abstraction through appropriate training.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While large language models like BERT demonstrate strong empirical performance on semantic tasks, whether this reflects true conceptual competence or surface-level statistical association remains unclear. I investigate whether BERT encodes abstract relational schemata by examining internal representations of concept pairs across taxonomic, mereological, and functional relations. I compare BERT's relational classification performance with representational structure in [CLS] token embeddings. Results reveal that pretrained BERT enables high classification accuracy, indicating latent relational signals. However, concept pairs organize by relation type in high-dimensional embedding space only after fine-tuning on supervised relation classification tasks. This indicates relational schemata are not emergent from pretraining alone but can be induced via task scaffolding. These findings demonstrate that behavioral performance does not necessarily imply structured conceptual understanding, though models can acquire inductive biases for grounded relational abstraction through appropriate training.

Related papers

• Relational reasoning and inductive bias in transformers trained on a transitive inference task [2.493955263354982]
  Transformer-based models have demonstrated remarkable reasoning abilities, but the mechanisms underlying relational reasoning remain poorly understood.<n>In this work, we investigate how transformers perform a classic relational reasoning task from the Psychology literature, textittransitive inference<n>We compare transitive inference behavior across two distinct learning regimes: in-weights learning (IWL), where models store information in network parameters, and in-context learning (ICL), where models utilize information presented within the input sequence.<n>These results suggest that pre-training on tasks with underlying structure promotes the development of representations that can scaffold in-context relational reasoning
  arXiv  Detail & Related papers  (2025-06-04T10:15:05Z)
• Pre-training and Diagnosing Knowledge Base Completion Models [58.07183284468881]
  We introduce and analyze an approach to knowledge transfer from one collection of facts to another without the need for entity or relation matching. The main contribution is a method that can make use of large-scale pre-training on facts, which were collected from unstructured text. To understand the obtained pre-trained models better, we then introduce a novel dataset for the analysis of pre-trained models for Open Knowledge Base Completion.
  arXiv  Detail & Related papers  (2024-01-27T15:20:43Z)
• Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Images [76.47980643420375]
  This paper builds on the hypothesis that there is an inherent data-hungry matter in learning semantic correspondences. We demonstrate a simple machine annotator reliably enriches paired key points via machine supervision. Our models surpass current state-of-the-art models on semantic correspondence learning benchmarks like SPair-71k, PF-PASCAL, and PF-WILLOW.
  arXiv  Detail & Related papers  (2023-11-30T13:22:15Z)
• Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation Recognition [4.7938839332508945]
  We propose a Prompt-based Logical Semantics Enhancement (PLSE) method for Implicit Discourse Relation Recognition (IDRR) Our method seamlessly injects knowledge relevant to discourse relation into pre-trained language models through prompt-based connective prediction. Experimental results on PDTB 2.0 and CoNLL16 datasets demonstrate that our method achieves outstanding and consistent performance against the current state-of-the-art models.
  arXiv  Detail & Related papers  (2023-11-01T08:38:08Z)
• Multiple Relations Classification using Imbalanced Predictions Adaptation [0.0]
  The relation classification task assigns the proper semantic relation to a pair of subject and object entities. Current relation classification models employ additional procedures to identify multiple relations in a single sentence. We propose a multiple relations classification model that tackles these issues through a customized output architecture and by exploiting additional input features.
  arXiv  Detail & Related papers  (2023-09-24T18:36:22Z)
• Learning Complete Topology-Aware Correlations Between Relations for Inductive Link Prediction [121.65152276851619]
  We show that semantic correlations between relations are inherently edge-level and entity-independent. We propose a novel subgraph-based method, namely TACO, to model Topology-Aware COrrelations between relations. To further exploit the potential of RCN, we propose Complete Common Neighbor induced subgraph.
  arXiv  Detail & Related papers  (2023-09-20T08:11:58Z)
• Explainable Representations for Relation Prediction in Knowledge Graphs [0.0]
  We propose SEEK, a novel approach for explainable representations to support relation prediction in knowledge graphs. It is based on identifying relevant shared semantic aspects between entities and learning representations for each subgraph. We evaluate SEEK on two real-world relation prediction tasks: protein-protein interaction prediction and gene-disease association prediction.
  arXiv  Detail & Related papers  (2023-06-22T06:18:40Z)
• HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction [63.64877263289319]
  Unsupervised relation extraction aims to extract the relationship between entities from natural language sentences without prior information on relational scope or distribution.<n>We propose a novel contrastive learning framework named HiURE, which has the capability to derive hierarchical signals from relational feature space using cross hierarchy attention.<n> Experimental results on two public datasets demonstrate the advanced effectiveness and robustness of HiURE on unsupervised relation extraction when compared with state-of-the-art models.
  arXiv  Detail & Related papers  (2022-05-04T17:56:48Z)
• Does BERT really agree ? Fine-grained Analysis of Lexical Dependence on a Syntactic Task [70.29624135819884]
  We study the extent to which BERT is able to perform lexically-independent subject-verb number agreement (NA) on targeted syntactic templates. Our results on nonce sentences suggest that the model generalizes well for simple templates, but fails to perform lexically-independent syntactic generalization when as little as one attractor is present.
  arXiv  Detail & Related papers  (2022-04-14T11:33:15Z)
• High-order Semantic Role Labeling [86.29371274587146]
  This paper introduces a high-order graph structure for the neural semantic role labeling model. It enables the model to explicitly consider not only the isolated predicate-argument pairs but also the interaction between the predicate-argument pairs. Experimental results on 7 languages of the CoNLL-2009 benchmark show that the high-order structural learning techniques are beneficial to the strong performing SRL models.
  arXiv  Detail & Related papers  (2020-10-09T15:33:54Z)

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.