AI Paper Atlas

Research map / Large language models / Alignment and preferences

Phrase-grounded APO for Improving Chest X-ray Report Generation

Raziuddin Mahmood, Tanveer Syeda-Mahmood

CVPR 2026 · Large language models › Alignment and preferences · approach: Steering and correcting LLM behavior

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add APO alignment at inference (parameter updates on self-generated preference pairs)seven RRG models · ChestImaGenome Goldaverage improvement over original reports: 39.98% average over metricsImproved
add APO alignment on top of static report correction (ablation)RRG models · ChestImaGenome Goldaverage improvement over original reports: 26.52% -> 39.98%Improved
add phrasal grounding loss term to DPO-style loss (ablation)APO · datasets average (RQ score)average RQ improvement: 11.4% -> 22.7%Improved
replace APO with GRPO using RQ as reward (ablation)RRG models · ChestImaGenome GoldRQ score: overall improvement under 5%No clear effect
apply GRPO alignment to a weaker generator (ablation)XrayGPT · ChestImaGenome GoldRQ score: 0.37 -> 0.36Hurt
apply APO to Maira-2MAIRA-2 · ChestImaGenome GoldRQ score: 0.52 -> 0.61Improved
apply APO to XrayGPTXrayGPT · ChestImaGenome GoldRQ score: 0.37 -> 0.52Improved
apply APO across datasets (MS-CXR, ChestXray8, VinDr-CXR, ChexPert)RRG models · multiple datasetsRQ score average improvement: around 22.7%Improved
use DPO instead of APO on MS-CXR (ablation)RRG models · MS-CXRRQ average improvement: 18.9% -> 0.22%Hurt
static correction of sentences by FC model and LLMLlama3.2 correction · 1000 sampled sentencesclinical errors: 94.5% correct, 4.2% clinical errorsMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy