DeepImagine: Learning Biomedical Reasoning via Successive Counterfactual Imagining

• URL: http://arxiv.org/abs/2604.23054v1
• Date: Fri, 24 Apr 2026 22:48:10 GMT
• Title: DeepImagine: Learning Biomedical Reasoning via Successive Counterfactual Imagining
• Abstract summary: We propose a framework for teaching LLMs biomedical reasoning through successive counterfactual imagining.<n>We construct both natural and approximate counterfactual pairs from real clinical trials with reported outcomes.<n>We show that DeepImagine consistently improves over untuned language models and traditional correlational baselines.
• Score: 6.221068729338845
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Predicting the outcomes of prospective clinical trials remains a major challenge for large language models. Prior work has shown that both traditional correlational predictors, such as random forests and logistic regression, and strong commercial LLMs achieve limited performance on this task. In this paper, we propose DeepImagine, a framework for teaching LLMs biomedical reasoning through successive counterfactual imagining. The central idea is to approximate hidden causal mechanisms of clinical trials by training models to infer how observed trial results would change under controlled perturbations of experimental conditions, such as dosage, outcome measures, study arms, geography, and other trial attributes. To support this objective, we construct both natural and approximate counterfactual pairs from real clinical trials with reported outcomes. For settings where strict counterfactual supervision is available, such as paired outcome measures or dose-ranging study arms within the same trial, we train models with supervised fine-tuning. For broader settings where only approximate counterfactual pairs can be retrieved, we optimize models with reinforcement learning using verifiable rewards based on downstream benchmark correctness. We further augment training with synthetic reasoning traces that provide causally plausible explanations for local counterfactual transitions. Using this pipeline, we train language models under 10B parameters, including Qwen3.5-9B, and evaluate them on clinical trial outcome prediction. We aim to show that DeepImagine consistently improves over untuned language models and traditional correlational baselines. Finally, we aim to show that the learned reasoning trajectories provide interpretable signals about how models represent trial-level mechanisms, suggesting a practical path toward more mechanistic and scientifically useful biomedical language models.

Related papers

• Position, Not Provenance: Separating Reasoning Mediation from Sycophancy in Medical Vision-Language Models [0.0]
  Medical vision-language models generate chain-of-thought reasoning before answering clinical questions.<n>We present CoT-Mediate, a behavioral framework that perturbs a single clinically meaningful attribute within a model's own generated reasoning.<n>We evaluate LLaVA-Med and MedGemma on 1,000 VQA-RAD samples each.
  arXiv  Detail & Related papers  (2026-07-29T17:11:52Z)
• Bounding the Causal Impact of ML-assisted Decision-Making via Counterfactual Correctness [2.9267249513932008]
  We present a partial-identification approach to constructing bounds on the causal effect of a new model.<n>The core innovation in our approach is to leverage assumptions relating fine-grained predictive accuracy to downstream outcomes.
  arXiv  Detail & Related papers  (2026-07-23T20:45:10Z)
• Investigating the Impact of Histopathological Foundation Models on Regressive Prediction of Homologous Recombination Deficiency [52.50039435394964]
  We systematically evaluate foundation models for regression-based tasks.<n>We extract patch-level features from whole slide images (WSI) using five state-of-the-art foundation models.<n>Models are trained to predict continuous HRD scores based on these extracted features across breast, endometrial, and lung cancer cohorts.
  arXiv  Detail & Related papers  (2026-01-29T14:06:50Z)
• OncoReason: Structuring Clinical Reasoning in LLMs for Robust and Interpretable Survival Prediction [2.904892426557913]
  Large language models (LLMs) have shown strong performance in biomedical NLP.<n>We present a unified, multi-task learning framework that aligns autoregressive LLMs with clinical reasoning for outcome prediction.<n>Our findings underscore the importance of reasoning-aware alignment in multi-task clinical modeling.
  arXiv  Detail & Related papers  (2025-10-20T13:35:12Z)
• Prediction-Powered Causal Inferences [59.98498488132307]
  We focus on Prediction-Powered Causal Inferences (PPCI)<n>We first show that conditional calibration guarantees valid PPCI at population level.<n>We then introduce a sufficient representation constraint transferring validity across experiments.
  arXiv  Detail & Related papers  (2025-02-10T10:52:17Z)
• Counterfactual Generative Modeling with Variational Causal Inference [1.9287470458589586]
  We present a novel variational Bayesian causal inference framework to handle counterfactual generative modeling tasks.<n>In experiments, we demonstrate the advantage of our framework compared to state-of-the-art models in counterfactual generative modeling.
  arXiv  Detail & Related papers  (2024-10-16T16:44:12Z)
• Clinical outcome prediction under hypothetical interventions -- a representation learning framework for counterfactual reasoning [31.97813934144506]
  We introduce a new representation learning framework, which considers the provision of counterfactual explanations as an embedded property of the risk model. Our results suggest that our proposed framework has the potential to help researchers and clinicians improve personalised care.
  arXiv  Detail & Related papers  (2022-05-15T09:41:16Z)
• Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations [97.91630330328815]
  We conduct a crowdsourcing study, where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews. We observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control.
  arXiv  Detail & Related papers  (2021-12-17T18:29:56Z)
• A Twin Neural Model for Uplift [59.38563723706796]
  Uplift is a particular case of conditional treatment effect modeling. We propose a new loss function defined by leveraging a connection with the Bayesian interpretation of the relative risk. We show our proposed method is competitive with the state-of-the-art in simulation setting and on real data from large scale randomized experiments.
  arXiv  Detail & Related papers  (2021-05-11T16:02:39Z)
• Bayesian prognostic covariate adjustment [59.75318183140857]
  Historical data about disease outcomes can be integrated into the analysis of clinical trials in many ways. We build on existing literature that uses prognostic scores from a predictive model to increase the efficiency of treatment effect estimates.
  arXiv  Detail & Related papers  (2020-12-24T05:19:03Z)
• Double Robust Representation Learning for Counterfactual Prediction [68.78210173955001]
  We propose a novel scalable method to learn double-robust representations for counterfactual predictions. We make robust and efficient counterfactual predictions for both individual and average treatment effects. The algorithm shows competitive performance with the state-of-the-art on real world and synthetic data.
  arXiv  Detail & Related papers  (2020-10-15T16:39:26Z)
• Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects [61.03579766573421]
  We study estimation of individual-level causal effects, such as a single patient's response to alternative medication. We devise representation learning algorithms that minimize our bound, by regularizing the representation's induced treatment group distance. We extend these algorithms to simultaneously learn a weighted representation to further reduce treatment group distances.
  arXiv  Detail & Related papers  (2020-01-21T10:16:33Z)

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.