Papers › From Uncertainty to Trust: Enhancing Reliability in Vision-Language Models with...

From Uncertainty to Trust: Enhancing Reliability in Vision-Language Models with Uncertainty-Guided Dropout Decoding

9 Dec 2024arXiv:2412.06474archive 2025-07-28

Yixiong Fang, Ziran Yang, Zhaorun Chen, Zhuokai Zhao, Jiawei Zhou

Large vision-language models (LVLMs) demonstrate remarkable capabilities in multimodal tasks but are prone to misinterpreting visual inputs, often resulting in hallucinations and unreliable outputs. To address these challenges, we propose Dropout Decoding, a novel inference-time approach that quantifies the uncertainty of visual tokens and selectively masks uncertain tokens to improve decoding. Our method measures the uncertainty of each visual token by projecting it onto the text space and decomposing it into aleatoric and epistemic components. Specifically, we focus on epistemic uncertainty, which captures perception-related errors more effectively. Inspired by dropout regularization, we introduce uncertainty-guided token dropout, which applies the dropout principle to input visual tokens instead of model parameters, and during inference rather than training. By aggregating predictions from an ensemble of masked decoding contexts, Dropout Decoding robustly mitigates errors arising from visual token misinterpretations. Evaluations on benchmarks including CHAIR, THRONE, and MMBench demonstrate that Dropout Decoding significantly reduces object hallucinations (OH) and enhances both reliability and quality of LVLM outputs across diverse visual contexts.

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.

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

Code

Syntology 18 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 12 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 14 ran (2 with no instrument failure; 12 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 between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 14 samples that ran have no recorded date.

kigb/dropoutdecoding officialmentioned in paperpytorchSyntology: 18 samples, 14 ran (12 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

18 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 12 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
10ran · our draft was wrong
2ran; the contract check could not run
1ran
4unverified

Licence: 18 of the 18 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 kigb/dropoutdecoding. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

kigb/dropoutdecoding official repository 18 samples, 14 ran (12 instrument-failed) · 4 unverified
add_diffusion_noise in 5 papers models/VCD/vcd_add_noise.py ran no licence file found · pointer only · fe66de066c32d0fc · report fixture: signature image_tensor:Tensor/4/float, noise_step:Tensor/0/int · returned Tensor · level recorded 2026-09-25
argmax in 23 papers models/llavanext.py ran · our draft was wrong fingerprinted no licence file found · pointer only · eb627f04ba74cba6 · report fixture: signature output:Tensor/2/float · returned int · level recorded 2026-09-25
combine_coco_captions in 11 papers chair_test/chair_metrics/chair.py ran · our draft was wrong no licence file found · pointer only · 25585704d77cafb4 · report fixture: signature annotation_path:str/0/str · returned dict · level recorded, date not recorded
combine_coco_instances in 9 papers chair_test/chair_metrics/chair.py ran · our draft was wrong no licence file found · pointer only · 66415dc1dd50f555 · report fixture: signature annotation_path:str/0/str · returned dict · level recorded, date not recorded
get_blank_prediction_path chair_test/chair_metrics/lm_consistency.py ran · our draft was wrong fingerprinted no licence file found · pointer only · a24f296c7f2750a0 · report fixture: signature tag:str/0/str · returned str · level recorded 2026-09-25
get_label_dicts chair_test/chair_metrics/im_consistency.py ran · our draft was wrong no licence file found · pointer only · 1b18bf83296c81a8 · report fixture: signature robust:bool/0/bool · returned tuple · level recorded 2026-09-25
get_sentence_scores_from_hallucination_file chair_test/chair_metrics/misc.py ran · our draft was wrong no licence file found · pointer only · 521fb486761a4172 · report fixture: signature hallucination_file:str/0/str · returned dict · level recorded 2026-09-25
hallucination_file_to_dict chair_test/chair_metrics/misc.py ran · our draft was wrong no licence file found · pointer only · 0bb2534b6701d132 · report fixture: signature hallucinated_json:str/0/str · returned dict · level recorded 2026-09-25
load_generated_captions in 10 papers chair_test/chair_metrics/chair.py ran · our draft was wrong no licence file found · pointer only · c6889eebaff1566f · report fixture: signature cap_file:str/0/str · returned tuple · level recorded 2026-09-25
load_json in 344 papers utils/compare.py ran · our draft was wrong no licence file found · pointer only · 53d425eb1278ddda · report fixture: signature file_path:str/0/str · returned dict · level recorded 2026-09-22
read_vocab in 7 papers chair_test/chair_metrics/lm_consistency.py ran · our draft was wrong no licence file found · pointer only · 3fda39b99e8fcada · report fixture: returned defaultdict · level recorded 2026-09-25
select_by_average models/llava.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 64b4a235a9c34b8a · report fixture: signature outputs_all:list/1/list · returned list · level recorded 2026-09-25
select_by_vote models/llavanext.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 13246077f0242fbf · report fixture: signature outputs_all:list/1/tuple · returned tuple · level recorded 2026-09-25
softmax in 240 papers
census: 53 implementations from 63 papers, 16 distinct outputs across 8 buckets, one shared input per bucket
chair_test/chair_metrics/lm_consistency.py ran · violated contract fingerprinted no licence file found · pointer only · bfe1425c081169ef · report fixture: signature array:ndarray/1/float · returned ndarray · level recorded 2026-09-25
get_consistency chair_test/chair_metrics/misc.py unverified no licence file found · pointer only · d9a1b1be427abb03 · report
get_im_consistency chair_test/chair_metrics/im_consistency.py unverified no licence file found · pointer only · c9a73d69abdd252a · report
select_by_vote models/llava.py unverified no licence file found · pointer only · 2a5e72bfe7b8597f · 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. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

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

harvested Assembly for DROPOUT DECODING (graph method: DROPOUT DECODING). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

  1. sample entry · level 0 · unverified · 265b8739e27fe5c8

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="2412.06474") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DropoutFocus

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