Papers › Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation

Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation

27 Aug 2024arXiv:2408.15205archive 2025-07-28

Jian Hu, Jiayi Lin, Junchi Yan, Shaogang Gong

Promptable segmentation typically requires instance-specific manual prompts to guide the segmentation of each desired object. To minimize such a need, task-generic promptable segmentation has been introduced, which employs a single task-generic prompt to segment various images of different objects in the same task. Current methods use Multimodal Large Language Models (MLLMs) to reason detailed instance-specific prompts from a task-generic prompt for improving segmentation accuracy. The effectiveness of this segmentation heavily depends on the precision of these derived prompts. However, MLLMs often suffer hallucinations during reasoning, resulting in inaccurate prompting. While existing methods focus on eliminating hallucinations to improve a model, we argue that MLLM hallucinations can reveal valuable contextual insights when leveraged correctly, as they represent pre-trained large-scale knowledge beyond individual images. In this paper, we utilize hallucinations to mine task-related information from images and verify its accuracy for enhancing precision of the generated prompts. Specifically, we introduce an iterative Prompt-Mask Cycle generation framework (ProMaC) with a prompt generator and a mask generator.The prompt generator uses a multi-scale chain of thought prompting, initially exploring hallucinations for extracting extended contextual knowledge on a test image.These hallucinations are then reduced to formulate precise instance-specific prompts, directing the mask generator to produce masks that are consistent with task semantics by mask semantic alignment. The generated masks iteratively induce the prompt generator to focus more on task-relevant image areas and reduce irrelevant hallucinations, resulting jointly in better prompts and masks. Experiments on 5 benchmarks demonstrate the effectiveness of ProMaC. Code given in https://lwpyh.github.io/ProMaC/.

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 9 code samples harvested from 1 repository linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 2 ran (1 with no instrument failure; 1 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lwpyh/ProMaC_code officialmentioned on GitHubpytorchSyntology: 9 samples, 2 ran (1 instrument-failed) · 7 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

9 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
1ran; the contract check could not run
7unverified

Licence: 0 of the 9 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 lwpyh/ProMaC_code. “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.

lwpyh/ProMaC_code official repository 9 samples, 2 ran (1 instrument-failed) · 7 unverified
convert_patch_bbox_to_original utils_mllm.py ran · violated contract fingerprinted MIT (permissive) · 923b02f12c4e8943 · report fixture: signature bounding_box:list/1/int, left:int/0/int, upper:int/0/int · returned list · level recorded 2026-09-22
expand_bbox in 11 papers utils_mllm.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 93aa0fead442ddef · report fixture: signature bbox:list/1/float, expansion_rate:float/0/float · returned list · level recorded 2026-09-22
generate_image in 15 papers utils_mllm.py unverified MIT (permissive) · 4379261942974adb · report
get_reflected_text_from_full_img_llava utils_mllm.py unverified MIT (permissive) · fc5b045f2c663b01 · report
get_reflected_text_from_img utils_mllm.py unverified MIT (permissive) · 47abbc2ac21defe8 · report
get_reflected_text_from_img_llava_collected utils_mllm.py unverified MIT (permissive) · 4f885a4ecc54c188 · report
get_text_from_img_llava_with_bbox_iter0 utils_mllm.py unverified MIT (permissive) · 141d2009ede3317e · report
get_text_from_img_llava_with_bbox_patch utils_mllm.py unverified MIT (permissive) · b470f2ff84a1db05 · report
show in 6 papers utils_mllm.py unverified MIT (permissive) · 03c001cd5ce7f974 · 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 ProMaC (graph method: ProMaC). 9 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. get_reflected_text_from_img entry · level 0 · unverified · 47abbc2ac21defe8
  2. convert_patch_bbox_to_original helper · level 1 · ran · violated contract · 923b02f12c4e8943
  3. generate_image helper · level 0 · unverified · 4379261942974adb
  4. get_reflected_text_from_full_img_llava helper · level 0 · unverified · fc5b045f2c663b01
  5. get_reflected_text_from_img_llava_collected model · level 0 · unverified · 4f885a4ecc54c188
  6. get_text_from_img_llava_with_bbox_iter0 model · level 0 · unverified · 141d2009ede3317e
  7. get_text_from_img_llava_with_bbox_patch model · level 0 · unverified · b470f2ff84a1db05
  8. show helper · level 0 · unverified · 03c001cd5ce7f974
  9. expand_bbox helper · level 1 · ran; the contract check could not run (RAISES) · 93aa0fead442ddef

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="2408.15205") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Camouflaged Object SegmentationCamouflaged Object Segmentation with a Single Task-generic PromptMedical Image SegmentationSegmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Camouflaged Object Segmentation with a Single Task-generic Prompt CAMO ProMaC E_{\phi} 0.846 #2 of 3 Archive leaderboard report
Camouflaged Object Segmentation with a Single Task-generic Prompt CAMO ProMaC F_{\beta} 0.725 #2 of 3 Archive leaderboard report
Camouflaged Object Segmentation with a Single Task-generic Prompt CAMO ProMaC MAE 0.09 #2 of 3 Archive leaderboard report
Camouflaged Object Segmentation with a Single Task-generic Prompt CAMO ProMaC S_{\alpha} 0.767 #2 of 3 Archive leaderboard report
Camouflaged Object Segmentation with a Single Task-generic Prompt COD10K ProMaC E_{\phi} 0.876 #2 of 3 Archive leaderboard report
Camouflaged Object Segmentation with a Single Task-generic Prompt COD10K ProMaC F_{\beta} 0.716 #2 of 3 Archive leaderboard report
Camouflaged Object Segmentation with a Single Task-generic Prompt COD10K ProMaC MAE 0.042 #2 of 3 Archive leaderboard report
Camouflaged Object Segmentation with a Single Task-generic Prompt COD10K ProMaC S_{\alpha} 0.805 #2 of 3 Archive leaderboard report
Camouflaged Object Segmentation with a Single Task-generic Prompt Chameleon ProMaC E_{\phi} 0.899 #1 of 2 Archive leaderboard report
Camouflaged Object Segmentation with a Single Task-generic Prompt Chameleon ProMaC F_{\beta} 0.79 #1 of 2 Archive leaderboard report
Camouflaged Object Segmentation with a Single Task-generic Prompt Chameleon ProMaC MAE 0.044 #1 of 2 Archive leaderboard report
Camouflaged Object Segmentation with a Single Task-generic Prompt Chameleon ProMaC S_{\alpha} 0.833 #1 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

GenSAMSAM

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