Relational reasoning and inductive bias in transformers trained on a transitive inference task

• URL: http://arxiv.org/abs/2506.04289v1
• Date: Wed, 04 Jun 2025 10:15:05 GMT
• Title: Relational reasoning and inductive bias in transformers trained on a transitive inference task
• Authors: Jesse Geerts, Stephanie Chan, Claudia Clopath, Kimberly Stachenfeld,
• Abstract summary: 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
• Score: 2.493955263354982
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Transformer-based models have demonstrated remarkable reasoning abilities, but the mechanisms underlying relational reasoning in different learning regimes remain poorly understood. In this work, we investigate how transformers perform a classic relational reasoning task from the Psychology literature, \textit{transitive inference}, which requires inference about indirectly related items by integrating information across observed adjacent item pairs (e.g., if A>B and B>C, then A>C). 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 flexibly utilize information presented within the input sequence. Our findings reveal that IWL naturally induces a generalization bias towards transitive inference, despite being trained only on adjacent items, whereas ICL models trained solely on adjacent items do not generalize transitively. Mechanistic analysis shows that ICL models develop induction circuits that implement a simple match-and-copy strategy that performs well at relating adjacent pairs, but does not encoding hierarchical relationships among indirectly related items. Interestingly, when pre-trained on in-context linear regression tasks, transformers successfully exhibit in-context generalizable transitive inference. Moreover, like IWL, they display both \textit{symbolic distance} and \textit{terminal item effects} characteristic of human and animal performance, without forming induction circuits. These results suggest that pre-training on tasks with underlying structure promotes the development of representations that can scaffold in-context relational reasoning.

Related papers

• Provable In-Context Learning of Nonlinear Regression with Transformers [58.018629320233174]
  In-context learning (ICL) is the ability to perform unseen tasks using task-specific prompts without updating parameters.<n>Recent research has actively explored the training dynamics behind ICL.<n>This paper investigates more complex nonlinear regression tasks, aiming to uncover how transformers acquire in-context learning capabilities.
  arXiv  Detail & Related papers  (2025-07-28T00:09:28Z)
• Relational Schemata in BERT Are Inducible, Not Emergent: A Study of Performance vs. Competence in Language Models [0.0]
  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.
  arXiv  Detail & Related papers  (2025-06-13T06:20:03Z)
• How does Transformer Learn Implicit Reasoning? [41.315116538534106]
  We study how implicit multi-hop reasoning emerges by training transformers from scratch in a controlled symbolic environment.<n>We find that training with atomic triples is not necessary but accelerates learning, and that second-hop generalization relies on query-level exposure to specific compositional structures.
  arXiv  Detail & Related papers  (2025-05-29T17:02:49Z)
• Toward Understanding In-context vs. In-weight Learning [50.24035812301655]
  We identify simplified distributional properties that give rise to the emergence and disappearance of in-context learning.<n>We then extend the study to a full large language model, showing how fine-tuning on various collections of natural language prompts can elicit similar in-context and in-weight learning behaviour.
  arXiv  Detail & Related papers  (2024-10-30T14:09:00Z)
• A distributional simplicity bias in the learning dynamics of transformers [50.91742043564049]
  We show that transformers, trained on natural language data, also display a simplicity bias.<n>Specifically, they sequentially learn many-body interactions among input tokens, reaching a saturation point in the prediction error for low-degree interactions.<n>This approach opens up the possibilities of studying how interactions of different orders in the data affect learning, in natural language processing and beyond.
  arXiv  Detail & Related papers  (2024-10-25T15:39:34Z)
• Strengthening Structural Inductive Biases by Pre-training to Perform Syntactic Transformations [75.14793516745374]
  We propose to strengthen the structural inductive bias of a Transformer by intermediate pre-training. Our experiments confirm that this helps with few-shot learning of syntactic tasks such as chunking. Our analysis shows that the intermediate pre-training leads to attention heads that keep track of which syntactic transformation needs to be applied to which token.
  arXiv  Detail & Related papers  (2024-07-05T14:29:44Z)
• 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)
• The mechanistic basis of data dependence and abrupt learning in an in-context classification task [0.3626013617212666]
  We show that specific distributional properties inherent in language control the trade-off or simultaneous appearance of two forms of learning. In-context learning is driven by the abrupt emergence of an induction head, which subsequently competes with in-weights learning. We propose that the sharp transitions in attention-based networks arise due to a specific chain of multi-layer operations necessary to achieve ICL.
  arXiv  Detail & Related papers  (2023-12-03T20:53:41Z)
• Inductive Relation Prediction from Relational Paths and Context with Hierarchical Transformers [23.07740200588382]
  This paper proposes a novel method that captures both connections between entities and the intrinsic nature of entities. REPORT relies solely on relation semantics and can naturally generalize to the fully-inductive setting. In the experiments, REPORT performs consistently better than all baselines on almost all the eight version subsets of two fully-inductive datasets.
  arXiv  Detail & Related papers  (2023-04-01T03:49:47Z)
• Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers [4.562331048595688]
  An extension of Transformers is proposed that enables explicit relational reasoning through a novel module called the Abstractor. At the core of the Abstractor is a variant of attention called relational cross-attention. The approach is motivated by an architectural inductive bias for relational learning that disentangles relational information from object-level features.
  arXiv  Detail & Related papers  (2023-04-01T01:49:08Z)
• On Neural Architecture Inductive Biases for Relational Tasks [76.18938462270503]
  We introduce a simple architecture based on similarity-distribution scores which we name Compositional Network generalization (CoRelNet) We find that simple architectural choices can outperform existing models in out-of-distribution generalizations.
  arXiv  Detail & Related papers  (2022-06-09T16:24:01Z)

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.