Browse State-of-the-Art › Object Hallucination
Object Hallucination
42 papers with code · 0 benchmarks · 0 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
No benchmark for this task in the archive.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
No dataset record in the archive lists this task.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 71 · with a code link: 42 · where Syntology ran a sample: 18 (16 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (18 of 71 tagged: 16 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 71 of 71, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding28 Nov 2023 7 repositories listed Syntology official (archive's flag): 9 ran · 10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified (of 14 harvested samples) · 11 pointer-only (licence)Large Vision-Language Models (LVLMs) have advanced considerably, intertwining visual recognition and language understanding to generate content that is not only coherent but also contextually attuned.
-
17 May 2023 6 repositories listed Syntology official (archive's flag): 6 ran · 11 ran (of which 2 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 12 harvested samples) · 5 pointer-only (licence)Despite the promising progress on LVLMs, we find that LVLMs suffer from the hallucination problem, i. e. they tend to generate objects that are inconsistent with the target images in the descriptions.
-
27 May 2024 5 repositories listed Syntology official (archive's flag): 11 ran · 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 3 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified (of 22 harvested samples) · 17 pointer-only (licence)Traditional feedback learning for hallucination reduction relies on labor-intensive manual labeling or expensive proprietary models.
-
29 Jan 2024 3 repositories listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples) · 2 pointer-only (licence)In this work, we propose a simple yet effective training strategy MoE-Tuning for LVLMs.
-
12 Jun 2024 2 repositories listedLarge audio-language models (LALMs) enhance traditional large language models by integrating audio perception capabilities, allowing them to tackle audio-related tasks.
-
1 Mar 2024 2 repositories listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified (of 12 harvested samples)While large vision-language models (LVLMs) have demonstrated impressive capabilities in interpreting multi-modal contexts, they invariably suffer from object hallucinations (OH).
-
23 Feb 2024 2 repositories listed Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified (of 17 harvested samples) · 17 pointer-only (licence)Large Vision-Language Models (LVLMs) are susceptible to object hallucinations, an issue in which their generated text contains non-existent objects, greatly limiting their reliability and practicality.
-
11 Oct 2023 2 repositories listed Syntology official (archive's flag): 7 ran · 7 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; 6 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples) · 8 pointer-only (licence)We introduce Ferret, a new Multimodal Large Language Model (MLLM) capable of understanding spatial referring of any shape or granularity within an image and accurately grounding open-vocabulary descriptions.
-
3 Oct 2023 2 repositories listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified (of 9 harvested samples) · 9 pointer-only (licence)Current Large Multimodal Models (LMMs) achieve remarkable progress, yet there remains significant uncertainty regarding their ability to accurately apprehend visual details, that is, in performing detailed captioning.
-
11 Jun 2025 1 repository listedOur approach leverages the semantic information embedded within vision tokens by projecting them into the text token distribution space, and dynamically selecting the most relevant vision token at each decoding step…
-
10 Jun 2025 1 repository listed Syntology official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples) · 4 pointer-only (licence)Despite significant advancements in Vision-Language Models (VLMs), the performance of existing VLMs remains hindered by object hallucination, a critical challenge to achieving accurate visual understanding.
-
26 May 2025 1 repository listedDespite significant advancements in Large Vision-Language Models, Object Hallucination (OH) remains a persistent challenge.
-
25 Mar 2025 1 repository listed Syntology official (archive's flag): 1 ran · 4 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; 3 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 4 pointer-only (licence)The rapid advancement of large vision-language models (LVLMs) has driven significant progress in multimodal tasks, enabling models to interpret, reason, and generate outputs across both visual and textual domains.
-
17 Mar 2025 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)However, these methods present two main limitations: (1) bluntly suppressing language priors can compromise coherence and accuracy of generated content, and (2) processing contrastive inputs adds computational load…
-
13 Mar 2025 1 repository listedIn this paper, we first conduct an in-depth exploration of LVLM internal states in relation to OH issues and discover that (1) LVLM internal states are high-specificity per-token indicators of hallucination behaviors.
-
28 Feb 2025 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified (of 11 harvested samples) · 2 pointer-only (licence)Furthermore, we propose an entropy-based noise-controlling strategy to enable the injected noise to be adaptively constrained regarding the smoothness of the similarity distribution.
-
27 Feb 2025 1 repository listedRecently, Large Vision-Language Models (LVLMs) show remarkable performance across various domains.
-
29 Dec 2024 1 repository listedLarge Vision-Language Models (LVLMs) have demonstrated remarkable performance in performing complex multimodal tasks.
-
24 Dec 2024 1 repository listedHowever, current approaches primarily rely on large foundation models in a zero-shot manner or fine-tuned models with human annotations, which limits scalability due to significant computational costs.
-
30 Oct 2024 1 repository listedThe core idea of our framework is to conduct hallucination evaluation on (object, relation, object) triplets extracted from LVLMs' responses, and thus, could be easily generalized to different vision-language tasks.
-
21 Oct 2024 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)Due to the long-term decay in RoPE, LVLMs tend to hallucinate more when relevant visual cues are distant from instruction tokens in the multimodal input sequence.
-
17 Oct 2024 1 repository listedLastly, we observe that although existing methods struggle to balance the reduction of object hallucinations with maintaining text quality, SGD demonstrates robustness in handling this challenge.
-
4 Oct 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)Large Vision-Language Models (LVLMs) have achieved impressive performance, yet research has pointed out a serious issue with object hallucinations within these models.
-
2 Sep 2024 1 repository listedTo analyze image representations while completely avoiding the influence of all other factors other than the image representation itself, we propose a parametric-free representation alignment metric (Pfram) that can…
-
8 Jul 2024 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples) · 8 pointer-only (licence)Large vision language models (LVLMs) often suffer from object hallucination, producing objects not present in the given images.
-
Think Before You Act: A Two-Stage Framework for Mitigating Gender Bias Towards Vision-Language Tasks27 May 2024 1 repository listedDuring answer inference, GAMA integrates the image, generated narrative, and a task-specific question prompt to infer answers for different vision-language tasks.
-
18 Feb 2024 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 3 unverified (of 3 harvested samples) · 3 pointer-only (licence)In this work, we adopt the intuition that the LVLM tends to respond logically consistently for existent objects but inconsistently for hallucinated objects.
-
15 Feb 2024 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 pointer-only (licence)Multimodal large language models (MLLMs) have attracted increasing attention in the past few years, but they may still generate descriptions that include objects not present in the corresponding images, a phenomenon…
-
1 Feb 2024 1 repository listedWe introduce Instruction Document Visual Question Answering (iDocVQA) dataset and Large Language Document (LLaDoc) model, for training Language-Vision (LV) models for document analysis and predictions on document…
-
8 Dec 2023 1 repository listed Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 4 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified (of 17 harvested samples) · 17 pointer-only (licence)Results show that ASUKA mitigates object hallucination and improves color consistency over standard diffusion and rectified flow models and other inpainting methods.
-
4 Dec 2023 1 repository listed
-
13 Oct 2023 1 repository listed
-
1 Oct 2023 1 repository listed Syntology official (archive's flag): 7 ran · 7 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; 5 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples) · 8 pointer-only (licence)
-
11 Aug 2023 1 repository listed
-
7 Aug 2023 1 repository listed
-
31 Jul 2023 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 7 pointer-only (licence)
-
15 Jun 2023 1 repository listed
-
14 Oct 2022 1 repository listed
-
4 Oct 2021 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
11 Feb 2021 1 repository listed
-
4 Jan 2020 1 repository listed
-
6 Sep 2018 1 repository listed
-
Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding8 Jun 2025 0 repositories listed
-
Visual Instruction Bottleneck Tuning20 May 2025 0 repositories listed
-
A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models4 May 2025 0 repositories listed
-
Black-Box Visual Prompt Engineering for Mitigating Object Hallucination in Large Vision Language Models30 Apr 2025 0 repositories listed
-
OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting11 Mar 2025 0 repositories listed
-
Seeing What's Not There: Spurious Correlation in Multimodal LLMs11 Mar 2025 0 repositories listed
-
EAZY: Eliminating Hallucinations in LVLMs by Zeroing out Hallucinatory Image Tokens10 Mar 2025 0 repositories listed
-
The Role of Background Information in Reducing Object Hallucination in Vision-Language Models: Insights from Cutoff API Prompting21 Feb 2025 0 repositories listed
-
CutPaste&Find: Efficient Multimodal Hallucination Detector with Visual-aid Knowledge Base18 Feb 2025 0 repositories listed
-
Mitigating Object Hallucinations in Large Vision-Language Models via Attention Calibration4 Feb 2025 0 repositories listed
-
Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs31 Jan 2025 0 repositories listed
-
Evaluating Hallucination in Large Vision-Language Models based on Context-Aware Object Similarities25 Jan 2025 0 repositories listed
-
ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models22 Nov 2024 0 repositories listed
-
DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination6 Oct 2024 0 repositories listed
-
Does Object Grounding Really Reduce Hallucination of Large Vision-Language Models?20 Jun 2024 0 repositories listed
-
Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?18 Jun 2024 0 repositories listed
-
28 May 2024 0 repositories listed Syntology 6 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; 4 where Syntology's instrument failed) · 4 unverified (of 10 harvested samples) · 10 pointer-only (licence)
-
RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in Large Vision Language Models28 May 2024 0 repositories listed
-
ALOHa: A New Measure for Hallucination in Captioning Models3 Apr 2024 0 repositories listed
-
Effectiveness Assessment of Recent Large Vision-Language Models7 Mar 2024 0 repositories listed
-
26 Feb 2024 0 repositories listed
-
Mitigating Object Hallucination in Large Vision-Language Models via Classifier-Free Guidance13 Feb 2024 0 repositories listed
-
KNVQA: A Benchmark for evaluation knowledge-based VQA21 Nov 2023 0 repositories listed
-
Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models9 Oct 2023 0 repositories listed
-
11 May 2023 0 repositories listed
-
Deep Learning Approaches on Image Captioning: A Review31 Jan 2022 0 repositories listed
-
Consensus Graph Representation Learning for Better Grounded Image Captioning2 Dec 2021 0 repositories listed
-
Relational Graph Learning for Grounded Video Description Generation2 Dec 2021 0 repositories listed
-
``I've Seen Things You People Wouldn't Believe'': Hallucinating Entities in GuessWhat?!1 Aug 2021 0 repositories listed
Syntology lines on 22 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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