Are Transformers Able to Reason by Connecting Separated Knowledge in Training Data?

• URL: http://arxiv.org/abs/2501.15857v2
• Date: Sun, 16 Feb 2025 20:20:23 GMT
• Title: Are Transformers Able to Reason by Connecting Separated Knowledge in Training Data?
• Authors: Yutong Yin, Zhaoran Wang,
• Abstract summary: Humans exhibit remarkable compositional reasoning by integrating knowledge from various sources. We introduce a synthetic learning task to validate the potential of Transformers in replicating this skill. We find that few-shot Chain-of-Thought prompting enables Transformers to perform compositional reasoning on FTCT.
• Score: 55.90575874130038
• License:
• Abstract: Humans exhibit remarkable compositional reasoning by integrating knowledge from various sources. For example, if someone learns ( B = f(A) ) from one source and ( C = g(B) ) from another, they can deduce ( C=g(B)=g(f(A)) ) even without encountering ( ABC ) together, showcasing the generalization ability of human intelligence. In this paper, we introduce a synthetic learning task, "FTCT" (Fragmented at Training, Chained at Testing), to validate the potential of Transformers in replicating this skill and interpret its inner mechanism. In the training phase, data consist of separated knowledge fragments from an overall causal graph. During testing, Transformers must infer complete causal graph traces by integrating these fragments. Our findings demonstrate that few-shot Chain-of-Thought prompting enables Transformers to perform compositional reasoning on FTCT by revealing correct combinations of fragments, even if such combinations were absent in the training data. Furthermore, the emergence of compositional reasoning ability is strongly correlated with the model complexity and training-testing data similarity. We propose, both theoretically and empirically, that Transformers learn an underlying generalizable program from training, enabling effective compositional reasoning during testing.

Related papers

• Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis [82.51626700527837]
  Chain-of-shift (CoT) is an efficient method that enables the reasoning ability of large language models by augmenting the query using examples with multiple intermediate steps. We show that despite the theoretical success of CoT, it fails to provide an accurate generalization when CoT does.
  arXiv  Detail & Related papers  (2024-10-03T03:12:51Z)
• In-Context Learning with Representations: Contextual Generalization of Trained Transformers [66.78052387054593]
  In-context learning (ICL) refers to a capability of pretrained large language models, which can learn a new task given a few examples during inference. This paper investigates the training dynamics of transformers by gradient descent through the lens of non-linear regression tasks.
  arXiv  Detail & Related papers  (2024-08-19T16:47:46Z)
• Towards Understanding the Relationship between In-context Learning and Compositional Generalization [7.843029855730508]
  We train a causal Transformer in a setting that renders ordinary learning very difficult. The model can solve the task, however, by utilizing earlier examples to generalize to later ones. In evaluations on the datasets, SCAN, COGS, and GeoQuery, models trained in this manner indeed show improved compositional generalization.
  arXiv  Detail & Related papers  (2024-03-18T14:45:52Z)
• Reasoning in Transformers - Mitigating Spurious Correlations and Reasoning Shortcuts [1.024113475677323]
  Transformer language models are neural networks used for a wide variety of tasks concerning natural language. We investigate to what extent transformers can be trained to approximate reasoning in propositional logic. We find that SIP-BART succeeds in avoiding reasoning shortcuts, while WP-BART does not.
  arXiv  Detail & Related papers  (2024-03-17T19:32:12Z)
• Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks [23.516986266146855]
  We train autoregressive Transformer models on a synthetic data-generating process. We show that autoregressive Transformers can learn compositional structures from small amounts of training data.
  arXiv  Detail & Related papers  (2023-11-21T21:16:54Z)
• When can transformers reason with abstract symbols? [25.63285482210457]
  We prove that for any relational reasoning task in a large family of tasks, transformers learn the abstract relations and generalize to the test set. This is in contrast to classical fully-connected networks, which we prove fail to learn to reason.
  arXiv  Detail & Related papers  (2023-10-15T06:45:38Z)
• Characterizing Intrinsic Compositionality in Transformers with Tree Projections [72.45375959893218]
  neural models like transformers can route information arbitrarily between different parts of their input. We show that transformers for three different tasks become more treelike over the course of training. These trees are predictive of model behavior, with more tree-like models generalizing better on tests of compositional generalization.
  arXiv  Detail & Related papers  (2022-11-02T17:10:07Z)
• Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks [86.10875837475783]
  Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. Existing neural models have been shown to lack this basic ability in learning symbolic structures. We propose two auxiliary sequence prediction tasks that track the progress of function and argument semantics.
  arXiv  Detail & Related papers  (2021-09-30T16:41:19Z)
• More data or more parameters? Investigating the effect of data structure on generalization [17.249712222764085]
  Properties of data impact the test error as a function of the number of training examples and number of training parameters. We show that noise in the labels and strong anisotropy of the input data play similar roles on the test error.
  arXiv  Detail & Related papers  (2021-03-09T16:08:41Z)
• Category-Learning with Context-Augmented Autoencoder [63.05016513788047]
  Finding an interpretable non-redundant representation of real-world data is one of the key problems in Machine Learning. We propose a novel method of using data augmentations when training autoencoders. We train a Variational Autoencoder in such a way, that it makes transformation outcome predictable by auxiliary network.
  arXiv  Detail & Related papers  (2020-10-10T14:04:44Z)

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.