How Should Transformers Encode Numeric Values in Electronic Health Records?

• URL: http://arxiv.org/abs/2607.01391v1
• Date: Wed, 01 Jul 2026 18:49:41 GMT
• Title: How Should Transformers Encode Numeric Values in Electronic Health Records?
• Abstract summary: We show trade-offs between numeric precision, optimisation, and architectural flexibility.<n>We find approaches that explicitly model value-concept interactions perform best on precision-sensitive arithmetic tasks.<n>Across tasks, models consistently exhibit reliable "good enough" numeric computation rather than exact arithmetic.
• Score: 11.191468812375321
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: How do we encode numeric values in transformer-based sequence processing, particularly in electronic health record (EHR) data? We systematically compare discrete, continuous, and hybrid value encoding strategies using synthetic arithmetic tasks embedded within real-world EHR data, as well as real-world clinical prediction tasks. Our study reveals trade-offs between numeric precision, optimisation stability, and architectural flexibility. We find that approaches that explicitly model value-concept interactions perform best on precision-sensitive arithmetic tasks when architectural constraints permit. Hybrid token-based approaches that retain numeric values but apply binning prior to projection provide a more robust and broadly applicable alternative, with the optimal number of bins following a simple empirically derived power-law in dataset size. Across tasks, models consistently exhibit reliable "good enough" numeric computation rather than exact arithmetic, while clinical gains from incorporating laboratory values are task-dependent. This suggests that robustness and deployability often outweigh maximal numeric precision in practice, motivating hybrid token-based approaches as a practical default.

Related papers

• Learning Interpretable Point-Based Clinical Risk Scores via Direct Optimization [16.98127677447133]
  We develop new machine learning algorithms to learn additive scoring directly under explicit and sensible optimality objectives.<n>We apply the proposed method to a large electronic health record (EHR) cohort to construct an integer-weighted comorbidity score for measuring the risk of post-discharge mortality.
  arXiv  Detail & Related papers  (2026-05-18T20:58:39Z)
• Value-Aware Numerical Representations for Transformer Language Models [1.2680800636608986]
  Transformer-based language models often achieve strong results on mathematical reasoning benchmarks.<n>A central limitation is that numbers are processed as symbolic tokens whose embeddings do not explicitly encode numerical value.<n>We introduce a value-aware numerical representation that augments standard tokenized inputs with a dedicated prefix token.
  arXiv  Detail & Related papers  (2026-01-14T18:59:14Z)
• Mixed Precision Training of Neural ODEs [1.3382837742547355]
  This paper presents a mixed precision training framework for neural ODEs.<n>It combines explicit ODE solvers with a custom backpropagation scheme.<n>It achieves approximately 50% memory reduction and up to 2x speedup while maintaining accuracy comparable to single-precision training.
  arXiv  Detail & Related papers  (2025-10-27T16:32:56Z)
• Data-Driven Surrogate Modeling Techniques to Predict the Effective Contact Area of Rough Surface Contact Problems [39.979007027634196]
  The effective contact area plays a critical role in multi-physics phenomena such as wear, sealing, and thermal or electrical conduction.<n>This study proposes a surrogate modeling framework for predicting the effective contact area using fast-to-evaluate data-driven techniques.
  arXiv  Detail & Related papers  (2025-04-24T08:15:46Z)
• Synergistic Development of Perovskite Memristors and Algorithms for Robust Analog Computing [53.77822620185878]
  We propose a synergistic methodology to concurrently optimize perovskite memristor fabrication and develop robust analog DNNs.<n>We develop "BayesMulti", a training strategy utilizing BO-guided noise injection to improve the resistance of analog DNNs to memristor imperfections.<n>Our integrated approach enables use of analog computing in much deeper and wider networks, achieving up to 100-fold improvements.
  arXiv  Detail & Related papers  (2024-12-03T19:20:08Z)
• Discovering physical laws with parallel symbolic enumeration [67.36739393470869]
  We introduce parallel symbolic enumeration (PSE) to efficiently distill generic mathematical expressions from limited data.<n>Experiments show that PSE achieves higher accuracy and faster computation compared to the state-of-the-art baseline algorithms.<n> PSE represents an advance in accurate and efficient data-driven discovery of symbolic, interpretable models.
  arXiv  Detail & Related papers  (2024-07-05T10:41:15Z)
• Fast Shapley Value Estimation: A Unified Approach [71.92014859992263]
  We propose a straightforward and efficient Shapley estimator, SimSHAP, by eliminating redundant techniques. In our analysis of existing approaches, we observe that estimators can be unified as a linear transformation of randomly summed values from feature subsets. Our experiments validate the effectiveness of our SimSHAP, which significantly accelerates the computation of accurate Shapley values.
  arXiv  Detail & Related papers  (2023-11-02T06:09:24Z)
• Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs [75.40636935415601]
  Deep learning often faces the challenge of efficiently processing dynamic inputs, such as sensor data or user inputs. We take an incremental computing approach, looking to reuse calculations as the inputs change. We apply this approach to the transformers architecture, creating an efficient incremental inference algorithm with complexity proportional to the fraction of modified inputs.
  arXiv  Detail & Related papers  (2023-07-27T16:30:27Z)
• A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks [65.34977803841007]
  Predictive coding networks are neuroscience-inspired models with roots in both Bayesian statistics and neuroscience. We show how by simply changing the temporal scheduling of the update rule for the synaptic weights leads to an algorithm that is much more efficient and stable than the original one.
  arXiv  Detail & Related papers  (2022-11-16T00:11:04Z)
• HyperImpute: Generalized Iterative Imputation with Automatic Model Selection [77.86861638371926]
  We propose a generalized iterative imputation framework for adaptively and automatically configuring column-wise models. We provide a concrete implementation with out-of-the-box learners, simulators, and interfaces.
  arXiv  Detail & Related papers  (2022-06-15T19:10:35Z)
• Conservative Objective Models for Effective Offline Model-Based Optimization [78.19085445065845]
  Computational design problems arise in a number of settings, from synthetic biology to computer architectures. We propose a method that learns a model of the objective function that lower bounds the actual value of the ground-truth objective on out-of-distribution inputs. COMs are simple to implement and outperform a number of existing methods on a wide range of MBO problems.
  arXiv  Detail & Related papers  (2021-07-14T17:55:28Z)

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.