titleSDR: Set-Distance Rewards for Radiology Report Generation
authorsHalil Ibrahim Gulluk, Max Van Puyvelde, Wim Van Criekinge, Olivier Gevaert
date2026-05-30
venuearXiv (preprint, not peer reviewed)
idarXiv:2606.00440
affiliationGevaert Lab
upvotes5 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf
abstractReinforcement learning with verifiable rewards has rapidly advanced reasoning in vision--language models. However, for chest X-ray report generation, the standard rewards (i.e. exact-match accuracy and step-level processes) are incompatible because the reports consist of unordered and orthogonal findings, rather than a causal reasoning chain. We address this gap with a set-based view: each report is split into sentences and embedded by a frozen sentence transformer, yielding unordered embedding sets. We propose the use of set-to-set distances between generated and reference embeddings as continuous, permutation-invariant rewards. Across two datasets and three vision--language models (Qwen3-VL-2B/4B, Gemma3-4B), post-training with set-to-set distance based rewards via GRPO consistently outperforms supervised fine-tuning and exact-match GRPO on all headline metrics (BERTScore, RadGraph F1 and CheXbert F1 by average \%6.80, \%7.82 and \%4.45 relative improvements respectively). The same set distances also enable test-time best-of-N selection: scoring candidates by their distance to training-report embeddings outperforms random selection on our trained models as well as three closed-source LLMs (Mistral-Small, Gemini-2.5 Flash-Lite, GPT-4o-mini) with on average \%16.4 relative improvement on BERTScore. Used as a streaming signal, they support a more efficient form of test-time scaling: pruning low-scoring candidates mid-generation reduces generated tokens by over 50\% while preserving the Findings quality of full best-of-N selection. Together these results establish set-distance rewards as a unified signal for both post-training and test-time scaling in chest X-ray report generation. Our code is publicly https://anonymous.4open.science/r/Set-Distance-Rewards-CXR-BFDA{available}.

cite

@misc{gulluk2026sdr,
  title={SDR: Set-Distance Rewards for Radiology Report Generation},
  author={Halil Ibrahim Gulluk and Max Van Puyvelde and Wim Van Criekinge and Olivier Gevaert},
  year={2026},
  eprint={2606.00440},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2606.00440}
}