AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Mitigating Entity Hallucinations in 3D Radiology Report Generation via Dual-Stream Alignment

Lingyu Zhou, Yue Yu, Zhang Yi, Xiuyuan Xu

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Preference tuning against hallucination · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a dual-stream alignment approach to reduce entity hallucinations in 3D CT radiology report generation by using medical entity phrases as multi-modal prompts.

Problem

Entity hallucination in radiology report generation for 3D CT scans, where complex spatial context amplifies factual errors; existing methods use unified cross-attention for volume-phrase alignment, which fails to account for anatomical structure differences.

Approach

Uses medical entity phrases as carriers for multi-modal prompting and replaces unified cross-attention volume-phrase alignment with a dual-stream alignment that separates alignment paths (abstract is truncated, so the exact streams are not specified).

Measured effects reported in the paper

What was changedWhereMeasuredEffect
split entity phrases into organ and lesion streams with separate cross-attention (ablation)DEAR · CT-RATEGREEN: 0.219 -> 0.247Improved
add organ-guided cross-attention (OGCA) to dual-stream aligner (ablation)DEAR · CT-RATEGREEN: 0.247 -> 0.439Improved
add lesion-guided cross-attention (LGCA) to dual-stream aligner (ablation)DEAR · CT-RATEGREEN: 0.247 -> 0.381Improved
combine OGCA and LGCA (ablation)DEAR · CT-RATEGREEN: 0.439 -> 0.511Improved
add Top-k voxel token selection in OGCA (ablation)DEAR OGCA · BIMCV-RGREEN: 0.287 -> 0.366Improved
use 3D dilation factor 3 instead of 1 (ablation)DEAR OGCA · BIMCV-RGREEN: 0.312 -> 0.366Improved
use 3D dilation factor 3 instead of 4 (ablation)DEAR OGCA · BIMCV-RGREEN: 0.348 -> 0.366Improved
add residual 3D Laplacian filtering in LGCA (ablation)DEAR LGCA · CTRG-ChestGREEN: 0.448 -> 0.463Improved
use Laplacian filtering without residual connection (ablation)DEAR LGCA · CTRG-ChestPrecision: 0.463 -> 0.452Hurt
use DEAR instead of fVLM (unified alignment)3D radiology report generation · CT-RATEGREEN: 0.401 -> 0.511Improved
use DEAR instead of CT2-Rep3D radiology report generation · CT-RATEBLEU-4: 0.369 -> 0.366No clear effect

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