SDR: Set-Distance Rewards for Radiology Report Generation

• URL: http://arxiv.org/abs/2606.00440v1
• Date: Sat, 30 May 2026 00:10:51 GMT
• Title: SDR: Set-Distance Rewards for Radiology Report Generation
• Abstract summary: We propose set-to-set distances between generated and reference embeddings as continuous, permutation-invariant rewards.<n>Across two datasets and three vision--language models, post-training with set-to-set distance based rewards via GRPO consistently outperforms supervised fine-tuning.<n>The same set distances also enable test-time best-of-$N$ selection.
• Score: 2.2462804525190427
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement 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 \href{https://anonymous.4open.science/r/Set-Distance-Rewards-CXR-BFDA}{available}.

Related papers

• GATE: Reliability-Gated Gaussian Evidence Fusion for Training-Free Test-Time Adaptation of Vision-Language Models [5.025577782616721]
  GATE is a training-free two-pass transductive test-time adaptation framework.<n>It uses the unlabeled target set while keeping the image encoder, text encoder, and prompt parameters fully frozen.<n>It improves zero-shot performance by an average of 5.41 points and outperforms the strongest non-GATE baseline by 1.94 points.
  arXiv  Detail & Related papers  (2026-08-29T18:33:23Z)
• ClosureBench: A Constructive Benchmark for Compositional Graph Reasoning [1.827510863075184]
  ClosureBench is a constructive benchmark for graph-relational reasoning with.<n> verified ground truth.<n>We evaluate models from 1.5B open weights to frontier systems.
  arXiv  Detail & Related papers  (2026-08-18T18:36:21Z)
• Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training [51.18425726646089]
  We propose textscSURE, a unified latent-space framework for image and video diffusion models.<n>It learns reward distributions and directly uses their reliability to guide dense post-training.<n>textscSURE-REFL achieves the highest VBench quality, semantic, and total scores among the evaluated methods.
  arXiv  Detail & Related papers  (2026-08-06T14:55:42Z)
• ExTra: Exploratory Trajectory Optimization for Language Model Reinforcement Learning [75.26064451955199]
  ExTra is a framework that extracts exploration signals from the model's own rollouts.<n>It improves Qwen3-1.7B over GRPO by about +5 points on pass@1 and +7 points on pass@16.
  arXiv  Detail & Related papers  (2026-06-23T15:51:39Z)
• REVES: REvision and VErification--Augmented Training for Test-Time Scaling [53.197756110943395]
  We propose a two-stage iterative framework that alternates between online data/prompt augmentation and policy optimization.<n>We observe gains of +6.5 points over the RL baseline and +4.0 points over standard multi-turn training.
  arXiv  Detail & Related papers  (2026-06-17T10:37:23Z)
• Adaptive Split-MMD Training for Small-Sample Cross-Dataset P300 EEG Classification [12.103074826558531]
  Cross-dataset shift occurs when trying to boost a small target set with a large source dataset.<n>We introduce Adaptive Split Maximum Mean Discrepancy Training (AS-MMD)<n>AS-MMD combines a target-weighted loss with warm-up tied to the square root of the source/target size ratio.<n>It outperforms target-only and pooled training.
  arXiv  Detail & Related papers  (2025-10-24T18:48:21Z)
• Detect Anything via Next Point Prediction [51.55967987350882]
  Rex- Omni is a 3B-scale MLLM that achieves state-of-the-art object perception performance.<n>On benchmarks like COCO and LVIS, Rex- Omni attains performance comparable to or exceeding regression-based models.
  arXiv  Detail & Related papers  (2025-10-14T17:59:54Z)
• GRAPE: Let GPRO Supervise Query Rewriting by Ranking for Retrieval [19.73916326078242]
  The CLIP model has become a cornerstone of large-scale retrieval systems by aligning text and image data in a unified embedding space.<n>To avoid costly retraining, existing methods mainly adopt query-rewriting strategies with large language models (LLMs)<n>We address this challenge with GRAPE, a plug-and-play enhancement approach that incorporates ranking signals into retrieval-guided query rewriting.
  arXiv  Detail & Related papers  (2025-09-27T15:36:59Z)
• Reinforcing Video Reasoning with Focused Thinking [65.85683941058916]
  We propose TW-GRPO, a novel framework that enhances visual reasoning with focused thinking and dense reward granularity.<n>Specifically, we employ a token weighting mechanism that prioritizes tokens with high informational density.<n>We also reformulate RL training by shifting from single-choice to multi-choice QA tasks.
  arXiv  Detail & Related papers  (2025-05-30T15:42:19Z)
• Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains [13.58151841630302]
  We propose a novel method METEORA that replaces re-ranking in RAG with a rationale-driven selection approach.<n>We show METEORA improves generation accuracy by 33.34% while using approximately 50% fewer chunks than state-of-the-art re-ranking methods.<n>In adversarial settings, METEORA significantly improves the F1 score from 0.10 to 0.44.
  arXiv  Detail & Related papers  (2025-05-21T20:57:16Z)
• 4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on Relational DBs [67.47600679176963]
  RDBs store vast amounts of rich, informative data spread across interconnected tables. The progress of predictive machine learning models falls behind advances in other domains such as computer vision or natural language processing. We explore a class of baseline models predicated on converting multi-table datasets into graphs. We assemble a diverse collection of large-scale RDB datasets and (ii) coincident predictive tasks.
  arXiv  Detail & Related papers  (2024-04-28T15:04:54Z)
• Boosting Continuous Sign Language Recognition via Cross Modality Augmentation [135.30357113518127]
  Continuous sign language recognition deals with unaligned video-text pair. We propose a novel architecture with cross modality augmentation. The proposed framework can be easily extended to other existing CTC based continuous SLR architectures.
  arXiv  Detail & Related papers  (2020-10-11T15:07:50Z)
• Heuristic Semi-Supervised Learning for Graph Generation Inspired by Electoral College [80.67842220664231]
  We propose a novel pre-processing technique, namely ELectoral COllege (ELCO), which automatically expands new nodes and edges to refine the label similarity within a dense subgraph. In all setups tested, our method boosts the average score of base models by a large margin of 4.7 points, as well as consistently outperforms the state-of-the-art.
  arXiv  Detail & Related papers  (2020-06-10T14:48:48Z)

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.