Nabeel Seedat

Evgeny S. Saveliev, Samuel Holt, Nabeel Seedat et al.

Large Language Models (LLMs) offer a promising avenue for scientific discovery, yet their application to symbolic regression is often constrained by inefficient search strategies and coarse feedback signals. Current methods typically guide LLMs using scalar metrics (e.g., global Mean Squared Error), which fail to identify which components of a proposed equation are driving performance or causing error. We introduce \textit{Influence-Guided Symbolic Regression} (IGSR), a method that frames equation discovery as an iterative two-step process combining diverse term generation with rigorous selection: an LLM generates candidate basis functions $ψ_j(\mathbf{x})$ for a linear model, which are then evaluated using granular influence scores $Δ_j$. These scores quantify each term's marginal contribution to generalization accuracy, enabling an influence-guided pruning process that systematically refines the model structure. Integrating this mechanism into a Monte Carlo Tree Search (MCTS) enables navigating the combinatorial search space while balancing exploration of novel functional forms with exploitation of high-influence components. We demonstrate IGSR's effectiveness on a diverse suite of benchmarks, including LLM-SRBench, pharmacological PKPD models, an epidemiological simulation, and real-world genomic data. Notably, we validate the framework's capacity for genuine discovery in a case study using a high-dimensional biological dataset, in which IGSR identified a novel relationship between DNA methylation and RNA Polymerase II pausing; a hypothesis that was subsequently supported via wet-lab experimentation.

Nabeel Seedat, Jonathan Crabbé, Ioana Bica et al. · cambridge, oxford

High model performance, on average, can hide that models may systematically underperform on subgroups of the data. We consider the tabular setting, which surfaces the unique issue of outcome heterogeneity - this is prevalent in areas such as healthcare, where patients with similar features can have different outcomes, thus making reliable predictions challenging. To tackle this, we propose Data-IQ, a framework to systematically stratify examples into subgroups with respect to their outcomes. We do this by analyzing the behavior of individual examples during training, based on their predictive confidence and, importantly, the aleatoric (data) uncertainty. Capturing the aleatoric uncertainty permits a principled characterization and then subsequent stratification of data examples into three distinct subgroups (Easy, Ambiguous, Hard). We experimentally demonstrate the benefits of Data-IQ on four real-world medical datasets. We show that Data-IQ's characterization of examples is most robust to variation across similarly performant (yet different) models, compared to baselines. Since Data-IQ can be used with any ML model (including neural networks, gradient boosting etc.), this property ensures consistency of data characterization, while allowing flexible model selection. Taking this a step further, we demonstrate that the subgroups enable us to construct new approaches to both feature acquisition and dataset selection. Furthermore, we highlight how the subgroups can inform reliable model usage, noting the significant impact of the Ambiguous subgroup on model generalization.

Hao Sun, Boris van Breugel, Jonathan Crabbe et al. · cambridge

Uncertainty Quantification (UQ) is essential for creating trustworthy machine learning models. Recent years have seen a steep rise in UQ methods that can flag suspicious examples, however, it is often unclear what exactly these methods identify. In this work, we propose a framework for categorizing uncertain examples flagged by UQ methods in classification tasks. We introduce the confusion density matrix -- a kernel-based approximation of the misclassification density -- and use this to categorize suspicious examples identified by a given uncertainty method into three classes: out-of-distribution (OOD) examples, boundary (Bnd) examples, and examples in regions of high in-distribution misclassification (IDM). Through extensive experiments, we show that our framework provides a new and distinct perspective for assessing differences between uncertainty quantification methods, thereby forming a valuable assessment benchmark.

Nabeel Seedat, Fergus Imrie, Alexis Bellot et al.

Estimating counterfactual outcomes over time has the potential to unlock personalized healthcare by assisting decision-makers to answer ''what-iF'' questions. Existing causal inference approaches typically consider regular, discrete-time intervals between observations and treatment decisions and hence are unable to naturally model irregularly sampled data, which is the common setting in practice. To handle arbitrary observation patterns, we interpret the data as samples from an underlying continuous-time process and propose to model its latent trajectory explicitly using the mathematics of controlled differential equations. This leads to a new approach, the Treatment Effect Neural Controlled Differential Equation (TE-CDE), that allows the potential outcomes to be evaluated at any time point. In addition, adversarial training is used to adjust for time-dependent confounding which is critical in longitudinal settings and is an added challenge not encountered in conventional time-series. To assess solutions to this problem, we propose a controllable simulation environment based on a model of tumor growth for a range of scenarios with irregular sampling reflective of a variety of clinical scenarios. TE-CDE consistently outperforms existing approaches in all simulated scenarios with irregular sampling.

Boris van Breugel, Nabeel Seedat, Fergus Imrie et al.

Evaluating the performance of machine learning models on diverse and underrepresented subgroups is essential for ensuring fairness and reliability in real-world applications. However, accurately assessing model performance becomes challenging due to two main issues: (1) a scarcity of test data, especially for small subgroups, and (2) possible distributional shifts in the model's deployment setting, which may not align with the available test data. In this work, we introduce 3S Testing, a deep generative modeling framework to facilitate model evaluation by generating synthetic test sets for small subgroups and simulating distributional shifts. Our experiments demonstrate that 3S Testing outperforms traditional baselines -- including real test data alone -- in estimating model performance on minority subgroups and under plausible distributional shifts. In addition, 3S offers intervals around its performance estimates, exhibiting superior coverage of the ground truth compared to existing approaches. Overall, these results raise the question of whether we need a paradigm shift away from limited real test data towards synthetic test data.

Lasse Hansen, Nabeel Seedat, Mihaela van der Schaar et al.

Synthetic data serves as an alternative in training machine learning models, particularly when real-world data is limited or inaccessible. However, ensuring that synthetic data mirrors the complex nuances of real-world data is a challenging task. This paper addresses this issue by exploring the potential of integrating data-centric AI techniques which profile the data to guide the synthetic data generation process. Moreover, we shed light on the often ignored consequences of neglecting these data profiles during synthetic data generation -- despite seemingly high statistical fidelity. Subsequently, we propose a novel framework to evaluate the integration of data profiles to guide the creation of more representative synthetic data. In an empirical study, we evaluate the performance of five state-of-the-art models for tabular data generation on eleven distinct tabular datasets. The findings offer critical insights into the successes and limitations of current synthetic data generation techniques. Finally, we provide practical recommendations for integrating data-centric insights into the synthetic data generation process, with a specific focus on classification performance, model selection, and feature selection. This study aims to reevaluate conventional approaches to synthetic data generation and promote the application of data-centric AI techniques in improving the quality and effectiveness of synthetic data.

Nabeel Seedat, Alan Jeffares, Fergus Imrie et al.

Conformal prediction is a powerful distribution-free tool for uncertainty quantification, establishing valid prediction intervals with finite-sample guarantees. To produce valid intervals which are also adaptive to the difficulty of each instance, a common approach is to compute normalized nonconformity scores on a separate calibration set. Self-supervised learning has been effectively utilized in many domains to learn general representations for downstream predictors. However, the use of self-supervision beyond model pretraining and representation learning has been largely unexplored. In this work, we investigate how self-supervised pretext tasks can improve the quality of the conformal regressors, specifically by improving the adaptability of conformal intervals. We train an auxiliary model with a self-supervised pretext task on top of an existing predictive model and use the self-supervised error as an additional feature to estimate nonconformity scores. We empirically demonstrate the benefit of the additional information using both synthetic and real data on the efficiency (width), deficit, and excess of conformal prediction intervals.

Nabeel Seedat, Fergus Imrie, Mihaela van der Schaar

While there have been a number of remarkable breakthroughs in machine learning (ML), much of the focus has been placed on model development. However, to truly realize the potential of machine learning in real-world settings, additional aspects must be considered across the ML pipeline. Data-centric AI is emerging as a unifying paradigm that could enable such reliable end-to-end pipelines. However, this remains a nascent area with no standardized framework to guide practitioners to the necessary data-centric considerations or to communicate the design of data-centric driven ML systems. To address this gap, we propose DC-Check, an actionable checklist-style framework to elicit data-centric considerations at different stages of the ML pipeline: Data, Training, Testing, and Deployment. This data-centric lens on development aims to promote thoughtfulness and transparency prior to system development. Additionally, we highlight specific data-centric AI challenges and research opportunities. DC-Check is aimed at both practitioners and researchers to guide day-to-day development. As such, to easily engage with and use DC-Check and associated resources, we provide a DC-Check companion website (https://www.vanderschaar-lab.com/dc-check/). The website will also serve as an updated resource as methods and tooling evolve over time.

Elisabeth R. M. Heremans, Nabeel Seedat, Bertien Buyse et al.

As machine learning becomes increasingly prevalent in critical fields such as healthcare, ensuring the safety and reliability of machine learning systems becomes paramount. A key component of reliability is the ability to estimate uncertainty, which enables the identification of areas of high and low confidence and helps to minimize the risk of error. In this study, we propose a machine learning pipeline called U-PASS tailored for clinical applications that incorporates uncertainty estimation at every stage of the process, including data acquisition, training, and model deployment. The training process is divided into a supervised pre-training step and a semi-supervised finetuning step. We apply our uncertainty-guided deep learning pipeline to the challenging problem of sleep staging and demonstrate that it systematically improves performance at every stage. By optimizing the training dataset, actively seeking informative samples, and deferring the most uncertain samples to an expert, we achieve an expert-level accuracy of 85% on a challenging clinical dataset of elderly sleep apnea patients, representing a significant improvement over the baseline accuracy of 75%. U-PASS represents a promising approach to incorporating uncertainty estimation into machine learning pipelines, thereby improving their reliability and unlocking their potential in clinical settings.

Nabeel Seedat, Jonathan Crabbé, Zhaozhi Qian et al.

Data quality is crucial for robust machine learning algorithms, with the recent interest in data-centric AI emphasizing the importance of training data characterization. However, current data characterization methods are largely focused on classification settings, with regression settings largely understudied. To address this, we introduce TRIAGE, a novel data characterization framework tailored to regression tasks and compatible with a broad class of regressors. TRIAGE utilizes conformal predictive distributions to provide a model-agnostic scoring method, the TRIAGE score. We operationalize the score to analyze individual samples' training dynamics and characterize samples as under-, over-, or well-estimated by the model. We show that TRIAGE's characterization is consistent and highlight its utility to improve performance via data sculpting/filtering, in multiple regression settings. Additionally, beyond sample level, we show TRIAGE enables new approaches to dataset selection and feature acquisition. Overall, TRIAGE highlights the value unlocked by data characterization in real-world regression applications

Jeroen Berrevoets, Nabeel Seedat, Fergus Imrie et al.

Directed acyclic graphs (DAGs) encode a lot of information about a particular distribution in their structure. However, compute required to infer these structures is typically super-exponential in the number of variables, as inference requires a sweep of a combinatorially large space of potential structures. That is, until recent advances made it possible to search this space using a differentiable metric, drastically reducing search time. While this technique -- named NOTEARS -- is widely considered a seminal work in DAG-discovery, it concedes an important property in favour of differentiability: transportability. To be transportable, the structures discovered on one dataset must apply to another dataset from the same domain. We introduce D-Struct which recovers transportability in the discovered structures through a novel architecture and loss function while remaining fully differentiable. Because D-Struct remains differentiable, our method can be easily adopted in existing differentiable architectures, as was previously done with NOTEARS. In our experiments, we empirically validate D-Struct with respect to edge accuracy and structural Hamming distance in a variety of settings.

Hao Sun, Alex J. Chan, Nabeel Seedat et al.

Evaluating the value of a hypothetical target policy with only a logged dataset is important but challenging. On the one hand, it brings opportunities for safe policy improvement under high-stakes scenarios like clinical guidelines. On the other hand, such opportunities raise a need for precise off-policy evaluation (OPE). While previous work on OPE focused on improving the algorithm in value estimation, in this work, we emphasize the importance of the offline dataset, hence putting forward a data-centric framework for evaluating OPE problems. We propose DataCOPE, a data-centric framework for evaluating OPE, that answers the questions of whether and to what extent we can evaluate a target policy given a dataset. DataCOPE (1) forecasts the overall performance of OPE algorithms without access to the environment, which is especially useful before real-world deployment where evaluating OPE is impossible; (2) identifies the sub-group in the dataset where OPE can be inaccurate; (3) permits evaluations of datasets or data-collection strategies for OPE problems. Our empirical analysis of DataCOPE in the logged contextual bandit settings using healthcare datasets confirms its ability to evaluate both machine-learning and human expert policies like clinical guidelines. Finally, we apply DataCOPE to the task of reward modeling in Large Language Model alignment to demonstrate its scalability in real-world applications.

Nabeel Seedat, Jiashuo Liu, Mihaela van der Schaar

The recent surge in AI agents that autonomously communicate, collaborate with humans and use diverse tools has unlocked promising opportunities in various real-world settings. However, a vital aspect remains underexplored: how agents handle data. Scalable autonomy demands agents that continuously acquire, process, and evolve their data. In this paper, we argue that data-savvy capabilities should be a top priority in the design of agentic systems to ensure reliable real-world deployment. Specifically, we propose four key capabilities to realize this vision: (1) Proactive data acquisition: enabling agents to autonomously gather task-critical knowledge or solicit human input to address data gaps; (2) Sophisticated data processing: requiring context-aware and flexible handling of diverse data challenges and inputs; (3) Interactive test data synthesis: shifting from static benchmarks to dynamically generated interactive test data for agent evaluation; and (4) Continual adaptation: empowering agents to iteratively refine their data and background knowledge to adapt to shifting environments. While current agent research predominantly emphasizes reasoning, we hope to inspire a reflection on the role of data-savvy agents as the next frontier in data-centric AI.

Hongshu Liu, Nabeel Seedat, Julia Ive

Computational models providing accurate estimates of their uncertainty are crucial for risk management associated with decision making in healthcare contexts. This is especially true since many state-of-the-art systems are trained using the data which has been labelled automatically (self-supervised mode) and tend to overfit. In this work, we investigate the quality of uncertainty estimates from a range of current state-of-the-art predictive models applied to the problem of observation detection in radiology reports. This problem remains understudied for Natural Language Processing in the healthcare domain. We demonstrate that Gaussian Processes (GPs) provide superior performance in quantifying the risks of 3 uncertainty labels based on the negative log predictive probability (NLPP) evaluation metric and mean maximum predicted confidence levels (MMPCL), whilst retaining strong predictive performance.

Yichi Zhang, Nabeel Seedat, Yinpeng Dong et al.

As LLM-powered agents have been used for high-stakes decision-making, such as clinical diagnosis, it becomes critical to develop reliable verification of their decisions to facilitate trustworthy deployment. Yet, existing verifiers usually underperform owing to a lack of domain knowledge and limited calibration. To address this, we establish GLEAN, an agent verification framework with Guideline-grounded Evidence Accumulation that compiles expert-curated protocols into trajectory-informed, well-calibrated correctness signals. GLEAN evaluates the step-wise alignment with domain guidelines and aggregates multi-guideline ratings into surrogate features, which are accumulated along the trajectory and calibrated into correctness probabilities using Bayesian logistic regression. Moreover, the estimated uncertainty triggers active verification, which selectively collects additional evidence for uncertain cases via expanding guideline coverage and performing differential checks. We empirically validate GLEAN with agentic clinical diagnosis across three diseases from the MIMIC-IV dataset, surpassing the best baseline by 12% in AUROC and 50% in Brier score reduction, which confirms the effectiveness in both discrimination and calibration. In addition, the expert study with clinicians recognizes GLEAN's utility in practice.

Andrew M. Bean, Nabeel Seedat, Shengzhuang Chen et al.

The prohibitive cost of evaluating large language models (LLMs) on comprehensive benchmarks necessitates the creation of small yet representative data subsets (i.e., tiny benchmarks) that enable efficient assessment while retaining predictive fidelity. Current methods for this task operate under a model-centric paradigm, selecting benchmarking items based on the collective performance of existing models. Such approaches are limited by large upfront costs, an inability to immediately handle new benchmarks (`cold-start'), and the fragile assumption that future models will share the failure patterns of their predecessors. In this work, we challenge this paradigm and propose a item-centric approach to benchmark subset selection, arguing that selection should be based on the intrinsic properties of the task items themselves, rather than on model-specific failure patterns. We instantiate this item-centric efficient benchmarking approach via a novel method, Scales++, where data selection is based on the cognitive demands of the benchmark samples. Empirically, we show Scales++ reduces the upfront selection cost by over 18x while achieving competitive predictive fidelity. On the Open LLM Leaderboard, using just a 0.5\% data subset, we predict full benchmark scores with a 2.9% mean absolute error. We demonstrate that this item-centric approach enables more efficient model evaluation without significant fidelity degradation, while also providing better cold-start performance and more interpretable benchmarking.

Fangyi Yu, Nabeel Seedat, Jonathan Richard Schwarz et al.

Language models deployed in high-stakes professional settings face conflicting demands from users, institutional authorities, and professional norms. How models act when these demands conflict reveals a principal hierarchy -- an implicit ordering over competing stakeholders that determines, for instance, whether a medical AI receiving a cost-reduction directive from a hospital administrator complies at the expense of evidence-based care, or refuses because professional standards require it. Across 7,136 scenarios in legal and medical domains, we test ten frontier models and find that models frequently fail to adhere to professional standards during task execution, such as drafting, when user instructions conflict with those standards -- despite adequately upholding them when users seek advisory guidance. We further find that the hierarchies between user, authority, and professional standards exhibited by these models are unstable across medical and legal contexts and inconsistent across model families. When failing to follow professional standards, the primary failure mechanism is knowledge omission: models that demonstrably possess relevant knowledge produce harmful outputs without surfacing conflicting knowledge. In a particularly troubling instance, we find that a reasoning model recognizes the relevant knowledge in its reasoning trace -- e.g., that a drug has been withdrawn -- yet suppresses this in the user-facing answer and proceeds to recommend the drug under authority pressure anyway. Inconsistent alignment across task framing, domain, and model families suggests that current alignment methods, including published alignment hierarchies, are unlikely to be robust when models are deployed in high-stakes professional settings.

Evgeny Saveliev, Jiashuo Liu, Nabeel Seedat et al.

Machine learning (ML) has the potential to revolutionize various domains, but its adoption is often hindered by the disconnect between the needs of domain experts and translating these needs into robust and valid ML tools. Despite recent advances in LLM-based co-pilots to democratize ML for non-technical domain experts, these systems remain predominantly focused on model-centric aspects while overlooking critical data-centric challenges. This limitation is problematic in complex real-world settings where raw data often contains complex issues, such as missing values, label noise, and domain-specific nuances requiring tailored handling. To address this we introduce CliMB-DC, a human-guided, data-centric framework for LLM co-pilots that combines advanced data-centric tools with LLM-driven reasoning to enable robust, context-aware data processing. At its core, CliMB-DC introduces a novel, multi-agent reasoning system that combines a strategic coordinator for dynamic planning and adaptation with a specialized worker agent for precise execution. Domain expertise is then systematically incorporated to guide the reasoning process using a human-in-the-loop approach. To guide development, we formalize a taxonomy of key data-centric challenges that co-pilots must address. Thereafter, to address the dimensions of the taxonomy, we integrate state-of-the-art data-centric tools into an extensible, open-source architecture, facilitating the addition of new tools from the research community. Empirically, using real-world healthcare datasets we demonstrate CliMB-DC's ability to transform uncurated datasets into ML-ready formats, significantly outperforming existing co-pilot baselines for handling data-centric challenges. CliMB-DC promises to empower domain experts from diverse domains -- healthcare, finance, social sciences and more -- to actively participate in driving real-world impact using ML.

Tennison Liu, Nicolás Astorga, Nabeel Seedat et al.

Bayesian optimization (BO) is a powerful approach for optimizing complex and expensive-to-evaluate black-box functions. Its importance is underscored in many applications, notably including hyperparameter tuning, but its efficacy depends on efficiently balancing exploration and exploitation. While there has been substantial progress in BO methods, striking this balance remains a delicate process. In this light, we present LLAMBO, a novel approach that integrates the capabilities of Large Language Models (LLM) within BO. At a high level, we frame the BO problem in natural language, enabling LLMs to iteratively propose and evaluate promising solutions conditioned on historical evaluations. More specifically, we explore how combining contextual understanding, few-shot learning proficiency, and domain knowledge of LLMs can improve model-based BO. Our findings illustrate that LLAMBO is effective at zero-shot warmstarting, and enhances surrogate modeling and candidate sampling, especially in the early stages of search when observations are sparse. Our approach is performed in context and does not require LLM finetuning. Additionally, it is modular by design, allowing individual components to be integrated into existing BO frameworks, or function cohesively as an end-to-end method. We empirically validate LLAMBO's efficacy on the problem of hyperparameter tuning, highlighting strong empirical performance across a range of diverse benchmarks, proprietary, and synthetic tasks.

Nabeel Seedat, Nicolas Huynh, Boris van Breugel et al.

Machine Learning (ML) in low-data settings remains an underappreciated yet crucial problem. Hence, data augmentation methods to increase the sample size of datasets needed for ML are key to unlocking the transformative potential of ML in data-deprived regions and domains. Unfortunately, the limited training set constrains traditional tabular synthetic data generators in their ability to generate a large and diverse augmented dataset needed for ML tasks. To address this challenge, we introduce CLLM, which leverages the prior knowledge of Large Language Models (LLMs) for data augmentation in the low-data regime. However, not all the data generated by LLMs will improve downstream utility, as for any generative model. Consequently, we introduce a principled curation mechanism, leveraging learning dynamics, coupled with confidence and uncertainty metrics, to obtain a high-quality dataset. Empirically, on multiple real-world datasets, we demonstrate the superior performance of CLLM in the low-data regime compared to conventional generators. Additionally, we provide insights into the LLM generation and curation mechanism, shedding light on the features that enable them to output high-quality augmented datasets.

Nabeel Seedat, Fergus Imrie, Mihaela van der Schaar

Characterizing samples that are difficult to learn from is crucial to developing highly performant ML models. This has led to numerous Hardness Characterization Methods (HCMs) that aim to identify "hard" samples. However, there is a lack of consensus regarding the definition and evaluation of "hardness". Unfortunately, current HCMs have only been evaluated on specific types of hardness and often only qualitatively or with respect to downstream performance, overlooking the fundamental quantitative identification task. We address this gap by presenting a fine-grained taxonomy of hardness types. Additionally, we propose the Hardness Characterization Analysis Toolkit (H-CAT), which supports comprehensive and quantitative benchmarking of HCMs across the hardness taxonomy and can easily be extended to new HCMs, hardness types, and datasets. We use H-CAT to evaluate 13 different HCMs across 8 hardness types. This comprehensive evaluation encompassing over 14K setups uncovers strengths and weaknesses of different HCMs, leading to practical tips to guide HCM selection and future development. Our findings highlight the need for more comprehensive HCM evaluation, while we hope our hardness taxonomy and toolkit will advance the principled evaluation and uptake of data-centric AI methods.

Nabeel Seedat, Mihaela van der Schaar

Schema matching -- the task of finding matches between attributes across disparate data sources with different tables and hierarchies -- is critical for creating interoperable machine learning (ML)-ready data. Addressing this fundamental data-centric problem has wide implications, especially in domains like healthcare, finance and e-commerce -- but also has the potential to benefit ML models more generally, by increasing the data available for ML model training. However, schema matching is a challenging ML task due to structural/hierarchical and semantic heterogeneity between different schemas. Previous ML approaches to automate schema matching have either required significant labeled data for model training, which is often unrealistic or suffer from poor zero-shot performance. To this end, we propose Matchmaker - a compositional language model program for schema matching, comprised of candidate generation, refinement and confidence scoring. Matchmaker also self-improves in a zero-shot manner without the need for labeled demonstrations via a novel optimization approach, which constructs synthetic in-context demonstrations to guide the language model's reasoning process. Empirically, we demonstrate on real-world medical schema matching benchmarks that Matchmaker outperforms previous ML-based approaches, highlighting its potential to accelerate data integration and interoperability of ML-ready data.

Paulius Rauba, Nabeel Seedat, Max Ruiz Luyten et al.

The predominant de facto paradigm of testing ML models relies on either using only held-out data to compute aggregate evaluation metrics or by assessing the performance on different subgroups. However, such data-only testing methods operate under the restrictive assumption that the available empirical data is the sole input for testing ML models, disregarding valuable contextual information that could guide model testing. In this paper, we challenge the go-to approach of data-only testing and introduce context-aware testing (CAT) which uses context as an inductive bias to guide the search for meaningful model failures. We instantiate the first CAT system, SMART Testing, which employs large language models to hypothesize relevant and likely failures, which are evaluated on data using a self-falsification mechanism. Through empirical evaluations in diverse settings, we show that SMART automatically identifies more relevant and impactful failures than alternatives, demonstrating the potential of CAT as a testing paradigm.

Paulius Rauba, Nabeel Seedat, Krzysztof Kacprzyk et al.

Real-world machine learning systems often encounter model performance degradation due to distributional shifts in the underlying data generating process (DGP). Existing approaches to addressing shifts, such as concept drift adaptation, are limited by their reason-agnostic nature. By choosing from a pre-defined set of actions, such methods implicitly assume that the causes of model degradation are irrelevant to what actions should be taken, limiting their ability to select appropriate adaptations. In this paper, we propose an alternative paradigm to overcome these limitations, called self-healing machine learning (SHML). Contrary to previous approaches, SHML autonomously diagnoses the reason for degradation and proposes diagnosis-based corrective actions. We formalize SHML as an optimization problem over a space of adaptation actions to minimize the expected risk under the shifted DGP. We introduce a theoretical framework for self-healing systems and build an agentic self-healing solution H-LLM which uses large language models to perform self-diagnosis by reasoning about the structure underlying the DGP, and self-adaptation by proposing and evaluating corrective actions. Empirically, we analyze different components of H-LLM to understand why and when it works, demonstrating the potential of self-healing ML.

Nicolas Huynh, Jeroen Berrevoets, Nabeel Seedat et al. · cambridge

Identification and appropriate handling of inconsistencies in data at deployment time is crucial to reliably use machine learning models. While recent data-centric methods are able to identify such inconsistencies with respect to the training set, they suffer from two key limitations: (1) suboptimality in settings where features exhibit statistical independencies, due to their usage of compressive representations and (2) lack of localization to pin-point why a sample might be flagged as inconsistent, which is important to guide future data collection. We solve these two fundamental limitations using directed acyclic graphs (DAGs) to encode the training set's features probability distribution and independencies as a structure. Our method, called DAGnosis, leverages these structural interactions to bring valuable and insightful data-centric conclusions. DAGnosis unlocks the localization of the causes of inconsistencies on a DAG, an aspect overlooked by previous approaches. Moreover, we show empirically that leveraging these interactions (1) leads to more accurate conclusions in detecting inconsistencies, as well as (2) provides more detailed insights into why some samples are flagged.

Fangyi Yu, Nabeel Seedat, Dasha Herrmannova et al.

Evaluating long-form answers in high-stakes domains such as law or medicine remains a fundamental challenge. Standard metrics like BLEU and ROUGE fail to capture semantic correctness, and current LLM-based evaluators often reduce nuanced aspects of answer quality into a single undifferentiated score. We introduce DeCE, a decomposed LLM evaluation framework that separates precision (factual accuracy and relevance) and recall (coverage of required concepts), using instance-specific criteria automatically extracted from gold answer requirements. DeCE is model-agnostic and domain-general, requiring no predefined taxonomies or handcrafted rubrics. We instantiate DeCE to evaluate different LLMs on a real-world legal QA task involving multi-jurisdictional reasoning and citation grounding. DeCE achieves substantially stronger correlation with expert judgments ($r=0.78$), compared to traditional metrics ($r=0.12$), pointwise LLM scoring ($r=0.35$), and modern multidimensional evaluators ($r=0.48$). It also reveals interpretable trade-offs: generalist models favor recall, while specialized models favor precision. Importantly, only 11.95% of LLM-generated criteria required expert revision, underscoring DeCE's scalability. DeCE offers an interpretable and actionable LLM evaluation framework in expert domains.

Nabeel Seedat, Caterina Tozzi, Andrea Hita Ardiaca et al.

The reuse of historical clinical trial data has significant potential to accelerate medical research and drug development. However, interoperability challenges, particularly with missing medical codes, hinders effective data integration across studies. While Large Language Models (LLMs) offer a promising solution for automated coding without labeled data, current approaches face challenges on complex coding tasks. We introduce ALIGN, a novel compositional LLM-based system for automated, zero-shot medical coding. ALIGN follows a three-step process: (1) diverse candidate code generation; (2) self-evaluation of codes and (3) confidence scoring and uncertainty estimation enabling human deferral to ensure reliability. We evaluate ALIGN on harmonizing medication terms into Anatomical Therapeutic Chemical (ATC) and medical history terms into Medical Dictionary for Regulatory Activities (MedDRA) codes extracted from 22 immunology trials. ALIGN outperformed the LLM baselines, while also providing capabilities for trustworthy deployment. For MedDRA coding, ALIGN achieved high accuracy across all levels, matching RAG and excelling at the most specific levels (87-90% for HLGT). For ATC coding, ALIGN demonstrated superior performance, particularly at lower hierarchy levels (ATC Level 4), with 72-73% overall accuracy and 86-89% accuracy for common medications, outperforming baselines by 7-22%. ALIGN's uncertainty-based deferral improved accuracy by 17% to 90% accuracy with 30% deferral, notably enhancing performance on uncommon medications. ALIGN achieves this cost-efficiently at \$0.0007 and \$0.02 per code for GPT-4o-mini and GPT-4o, reducing barriers to clinical adoption. ALIGN advances automated medical coding for clinical trial data, contributing to enhanced data interoperability and reusability, positioning it as a promising tool to improve clinical research and accelerate drug development.

Nabeel Seedat, Nicolas Huynh, Fergus Imrie et al.

Pseudo-labeling is a popular semi-supervised learning technique to leverage unlabeled data when labeled samples are scarce. The generation and selection of pseudo-labels heavily rely on labeled data. Existing approaches implicitly assume that the labeled data is gold standard and 'perfect'. However, this can be violated in reality with issues such as mislabeling or ambiguity. We address this overlooked aspect and show the importance of investigating labeled data quality to improve any pseudo-labeling method. Specifically, we introduce a novel data characterization and selection framework called DIPS to extend pseudo-labeling. We select useful labeled and pseudo-labeled samples via analysis of learning dynamics. We demonstrate the applicability and impact of DIPS for various pseudo-labeling methods across an extensive range of real-world tabular and image datasets. Additionally, DIPS improves data efficiency and reduces the performance distinctions between different pseudo-labelers. Overall, we highlight the significant benefits of a data-centric rethinking of pseudo-labeling in real-world settings.

Thomas Pouplin, Alan Jeffares, Nabeel Seedat et al.

Constructing valid prediction intervals rather than point estimates is a well-established approach for uncertainty quantification in the regression setting. Models equipped with this capacity output an interval of values in which the ground truth target will fall with some prespecified probability. This is an essential requirement in many real-world applications where simple point predictions' inability to convey the magnitude and frequency of errors renders them insufficient for high-stakes decisions. Quantile regression is a leading approach for obtaining such intervals via the empirical estimation of quantiles in the (non-parametric) distribution of outputs. This method is simple, computationally inexpensive, interpretable, assumption-free, and effective. However, it does require that the specific quantiles being learned are chosen a priori. This results in (a) intervals that are arbitrarily symmetric around the median which is sub-optimal for realistic skewed distributions, or (b) learning an excessive number of intervals. In this work, we propose Relaxed Quantile Regression (RQR), a direct alternative to quantile regression based interval construction that removes this arbitrary constraint whilst maintaining its strengths. We demonstrate that this added flexibility results in intervals with an improvement in desirable qualities (e.g. mean width) whilst retaining the essential coverage guarantees of quantile regression.

Nabeel Seedat, Jonathan Crabbé, Mihaela van der Schaar

Systematic quantification of data quality is critical for consistent model performance. Prior works have focused on out-of-distribution data. Instead, we tackle an understudied yet equally important problem of characterizing incongruous regions of in-distribution (ID) data, which may arise from feature space heterogeneity. To this end, we propose a paradigm shift with Data-SUITE: a data-centric AI framework to identify these regions, independent of a task-specific model. Data-SUITE leverages copula modeling, representation learning, and conformal prediction to build feature-wise confidence interval estimators based on a set of training instances. These estimators can be used to evaluate the congruence of test instances with respect to the training set, to answer two practically useful questions: (1) which test instances will be reliably predicted by a model trained with the training instances? and (2) can we identify incongruous regions of the feature space so that data owners understand the data's limitations or guide future data collection? We empirically validate Data-SUITE's performance and coverage guarantees and demonstrate on cross-site medical data, biased data, and data with concept drift, that Data-SUITE best identifies ID regions where a downstream model may be reliable (independent of said model). We also illustrate how these identified regions can provide insights into datasets and highlight their limitations.

Nabeel Seedat

Incorporating a human-in-the-loop system when deploying automated decision support is critical in healthcare contexts to create trust, as well as provide reliable performance on a patient-to-patient basis. Deep learning methods while having high performance, do not allow for this patient-centered approach due to the lack of uncertainty representation. Thus, we present a framework of uncertainty representation evaluated for medical image segmentation, using MCU-Net which combines a U-Net with Monte Carlo Dropout, evaluated with four different uncertainty metrics. The framework augments this by adding a human-in-the-loop aspect based on an uncertainty threshold for automated referral of uncertain cases to a medical professional. We demonstrate that MCU-Net combined with epistemic uncertainty and an uncertainty threshold tuned for this application maximizes automated performance on an individual patient level, yet refers truly uncertain cases. This is a step towards uncertainty representations when deploying machine learning based decision support in healthcare settings.

Nabeel Seedat, Vered Aharonson, Ilana Schlesinger

A widely used test for the diagnosis of Parkinson's disease (PD) and Essential tremor (ET) is hand-drawn shapes,where the analysis is observationally performed by the examining neurologist. This method is subjective and is prone to bias amongst different physicians. Due to the similarities in the symptoms of the two diseases, they are often misdiagnosed.Studies which attempt to automate the process typically use digitized input, where the tablet or specialized equipment are not affordable in many clinical settings. This study uses a dataset of scanned pen and paper drawings and a convolutional neural network (CNN) to perform classification between PD, ET and control subjects. The discrimination accuracy of PD from controls was 98.2%. The discrimination accuracy of PD from ET and from controls was 92%. An ablation study was conducted and indicated that correct hyper parameter optimization can increases the accuracy up to 4.33%. Finally, the study indicates the viability of using a CNN-enabled machine vision system to provide robust and accurate detection of movement disorders from hand drawn spirals.

Nabeel Seedat, Vered Aharonson

Clinical methods that assess gait in Parkinson's Disease (PD) are mostly qualitative. Quantitative methods necessitate costly instrumentation or cumbersome wearable devices, which limits their usability. Only few of these methods can discriminate different stages in PD progression. This study applies machine learning methods to discriminate six stages of PD. The data was acquired by low cost walker-mounted sensors in an experiment at a movement disorders clinic and the PD stages were clinically labeled. A large set of features, some unique to this study are extracted and three feature selection methods are compared using a multi-class Random Forest (RF) classifier. The feature subset selected by the Analysis of Variance (ANOVA) method provided performance similar to the full feature set: 93% accuracy and had significantly shorter computation time. Compared to PCA, this method also enabled clinical interpretability of the selected features, an essential attribute to healthcare applications. All selected-feature sets are dominated by information theoretic features and statistical features and offer insights into the characteristics of gait deterioration in PD. The results indicate a feasibility of machine learning to accurately classify PD severity stages from kinematic signals acquired by low-cost, walker-mounted sensors and implies a potential to aid medical practitioners in the quantitative assessment of PD progression. The study presents a solution to the small and noisy data problem, which is common in most sensor-based healthcare assessments.

Nabeel Seedat, Christopher Kanan

For many applications it is critical to know the uncertainty of a neural network's predictions. While a variety of neural network parameter estimation methods have been proposed for uncertainty estimation, they have not been rigorously compared across uncertainty measures. We assess four of these parameter estimation methods to calibrate uncertainty estimation using four different uncertainty measures: entropy, mutual information, aleatoric uncertainty and epistemic uncertainty. We evaluate the calibration of these parameter estimation methods using expected calibration error. Additionally, we propose a novel method of neural network parameter estimation called RECAST, which combines cosine annealing with warm restarts with Stochastic Gradient Langevin Dynamics, capturing more diverse parameter distributions. When benchmarked against mutilated image data, we show that RECAST is well-calibrated and when combined with predictive entropy and epistemic uncertainty it offers the best calibrated measure of uncertainty when compared to recent methods.