Papers › MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal...

MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization

9 Dec 2024arXiv:2412.06141archive 2025-07-28

Kangyu Zhu, Peng Xia, Yun Li, Hongtu Zhu, Sheng Wang, Huaxiu Yao

The advancement of Large Vision-Language Models (LVLMs) has propelled their application in the medical field. However, Medical LVLMs (Med-LVLMs) encounter factuality challenges due to modality misalignment, where the models prioritize textual knowledge over visual input, leading to hallucinations that contradict information in medical images. Previous attempts to enhance modality alignment in Med-LVLMs through preference optimization have inadequately mitigated clinical relevance in preference data, making these samples easily distinguishable and reducing alignment effectiveness. To address this challenge, we propose MMedPO, a novel multimodal medical preference optimization approach that considers the clinical relevance of preference samples to enhance Med-LVLM alignment. MMedPO curates multimodal preference data by introducing two types of dispreference: (1) plausible hallucinations injected through target Med-LVLMs or GPT-4o to produce medically inaccurate responses, and (2) lesion region neglect achieved through local lesion-noising, disrupting visual understanding of critical areas. We then calculate clinical relevance for each sample based on scores from multiple Med-LLMs and visual tools, and integrate these scores into the preference optimization process as weights, enabling effective alignment. Our experiments demonstrate that MMedPO significantly enhances factual accuracy in Med-LVLMs, achieving substantial improvements over existing preference optimization methods by averaging 14.2% and 51.7% across the Med-VQA and report generation tasks. Our code are available in https://github.com/aiming-lab/MMedPO.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Syntology holds a reference implementation of MMedPO, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='MMedPO') (how to connect); the free check have('2412.06141') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 17 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 13 ran (5 with no instrument failure; 8 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 7 of the 13 samples that ran have no recorded date.

aiming-lab/mmedpo officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 17 samples, 13 ran (8 instrument-failed) · 4 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

17 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
7ran · our draft was wrong
1ran; the contract check could not run
4ran
4unverified

Licence: 0 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from aiming-lab/mmedpo. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

aiming-lab/mmedpo official repository 17 samples, 13 ran (8 instrument-failed) · 4 unverified
whitespace_tokenize in 49 papers curation/Sample_Zero-Shot_Grounding_RSNA/models/tokenization_bert.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · cf9ffa02a42184af · report fixture: signature text:str/0/str · returned list · level recorded, date not recorded
add_gaussian_noise in 25 papers inference/llava-med-1.5_vqa.py ran · violated contract Apache-2.0 (permissive) · d2bfc515570f0eed · report fixture: signature image:Image/0/?, mean:float/0/float, stddev:float/0/float · returned Image · level recorded, date not recorded
add_gaussian_noise in 25 papers inference/llava-med-1.5_report.py ran Apache-2.0 (permissive) · 8f611a3a3069da33 · report fixture: signature image:Image/0/?, mean:float/0/float, stddev:float/0/float · returned Image · level recorded 2026-09-25
bleu in 13 papers eval/eval_report.py ran · our draft was wrong Apache-2.0 (permissive) · cd8fbb4ca9a20927 · report fixture: signature candidate:str/0/str, references:list/1/str, n:int/0/int, weights:list/1/float · returned str · level recorded 2026-09-25
create_loader_RSNA curation/Sample_Zero-Shot_Grounding_RSNA/dataset/dataset_RSNA.py ran Apache-2.0 (permissive) · c15c37b39ee4184f · report fixture: signature datasets:list/1/DummyDataset, samplers:list/1/DummySampler, batch_size:list/1/int, num_workers:list/1/int, is_trains:list/1/bool, collate_fns:list/1/callable · returned list · level recorded, date not recorded
generate_noised_image curation/Sample_Zero-Shot_Grounding_RSNA/inference_attention-map_score.py ran Apache-2.0 (permissive) · de5de3e13616d4f2 · report fixture: signature image_paths:list/1/str, pred_maps:list/1/ndarray · returned list · level recorded 2026-09-25
get_chunk in 197 papers inference/llava-med-1.5_report.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 42a46570620cd9fa · report fixture: signature lst:list/1/int, n:int/0/int, k:int/0/int · returned list · level recorded, date not recorded
get_tokenizer in 156 papers curation/Sample_Zero-Shot_Grounding_RSNA/inference_attention-map_score.py ran Apache-2.0 (permissive) · d070ec2620683428 · report fixture: signature tokenizer:callable/0/?, target_text:list/1/str · returned dict · level recorded 2026-09-25
load_jsonl in 179 papers eval/eval_report.py ran · our draft was wrong Apache-2.0 (permissive) · 77678f2758141df9 · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-25
load_vocab in 107 papers curation/Sample_Zero-Shot_Grounding_RSNA/models/tokenization_bert.py ran · our draft was wrong Apache-2.0 (permissive) · e7fbc7a74a3457c7 · report fixture: signature vocab_file:str/0/str · returned OrderedDict · level recorded, date not recorded
split_list in 223 papers inference/llava-med-1.5_report.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 076c252c52cbb161 · report fixture: signature lst:list/1/int, n:int/0/int · returned list · level recorded, date not recorded
split_to_even_chunks in 41 papers train/dpo/llava_trainer_weighted.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed Apache-2.0 (permissive) · 10893c4608c08075 · report fixture: signature indices:list/1/int, lengths:dict/0/?, num_chunks:int/0/int · returned list · level recorded, date not recorded
tensor_to_serializable inference/utils.py ran · our draft was wrong Apache-2.0 (permissive) · af42eb0093076ad3 · report fixture: signature obj:dict/0/? · returned dict · level recorded 2026-09-25
get_mm_adapter_state_maybe_zero_3 in 44 papers train/dpo/llava_trainer_weighted.py unverified Apache-2.0 (permissive) · bb35e3ac741bb2c9 · report
maybe_zero_3 in 74 papers train/dpo/llava_trainer_weighted.py unverified Apache-2.0 (permissive) · 735025744c1ab0cf · report
normalize_word in 22 papers eval/eval_report.py unverified Apache-2.0 (permissive) · 8f1a44ab20956301 · report
score_cal curation/Sample_Zero-Shot_Grounding_RSNA/inference_attention-map_score.py unverified Apache-2.0 (permissive) · e55695b0b11e1e76 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

1 assembly on this paper: 0 harvested, 1 generated.

generated Assembly for MMedPO (graph method: MMedPO), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. mmedpo_loss entry · level 3 · ran · honoured contract · dc5d9ddb9593596eef88bcef22f1eedef09cb8c50b8b06376f17e72a12f9f589

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2412.06141") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Visual Question Answering (VQA)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections