# CACSurv: Concordance-Aligned Comparative Learning with Large Language Models for Cancer Survival Prediction

arXiv: https://arxiv.org/abs/2608.16594 · HTML: https://mlsanity.com/paper/2608.16594/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Builds on (most cited first, 11 of 11)

- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network](https://mlsanity.com/paper/1606.00931/) (2016)
- [BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains](https://mlsanity.com/paper/2402.10373/) (2024)
- [Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction](https://mlsanity.com/paper/2304.06819/) (2023)
- [Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Prediction](https://mlsanity.com/paper/2306.08330/) (2023)
- [DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole-Slide Image Survival Prediction](https://mlsanity.com/paper/2510.00053/) (2025)
- [Cancer Type, Stage and Prognosis Assessment from Pathology Reports using LLMs](https://mlsanity.com/paper/2503.01194/) (2025)
- [Multimodal Cancer Modeling in the Age of Foundation Model Embeddings](https://mlsanity.com/paper/2505.07683/) (2025)
- [REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge](https://mlsanity.com/paper/2603.17145/) (2026)

## Abstract (arXiv)

Cancer survival prediction supports treatment planning, risk stratification, and follow-up management. Existing methods use structured clinical variables, whole-slide images, genomic profiles, or multimodal inputs, while patient reports remain underexplored. We study report-centric survival prediction using reports that organize pathological, clinical, and molecular evidence. Large language models (LLMs) can reason over such reports, but case-wise time regression introduces two mismatches. First, a formulation mismatch arises because survival evaluation depends on ordering comparable patients, whereas independent time predictions do not enforce ranking consistency. Second, a supervision mismatch arises because a censored patient's observed time indicates survival beyond that point and cannot serve as an exact regression target, although it still implies orderings relative to patients who died earlier. To address these mismatches, we propose CACSurv, a Concordance-Aligned Comparative framework for report-centric survival prediction. CACSurv reformulates survival modeling as mini-cohort comparative reasoning, where an LLM predicts relative prognostic orderings. We introduce concordance-aligned rewards derived from comparable relations under right censoring, enabling censored outcomes to provide ranking supervision without exact event-time targets. At inference, Monte Carlo Reference Aggregation compares each patient with sampled references and aggregates positions into a cohort-level ranking. We establish TCGA-SurvReport, a benchmark covering six TCGA cancer cohorts. CACSurv achieves the highest C-index on all six cohorts and an average C-index of 0.722, outperforming the strongest published survival model by 6.5 percentage points and the strongest LLM time-regression baseline by 4.2 percentage points. Our code, models, and dataset will be available at https://github.com/xmed-lab/CACSurv.