Object Hallucination

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

Most implemented papers archive 2025-07-28

30 shown of 42 papers with code (71 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
  28 Nov 2023 7 repositories listed Syntology ran 9 of 14 samples · 5 unverified · 1 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.
• Evaluating Object Hallucination in Large Vision-Language Models
  17 May 2023 6 repositories listed Syntology ran 6 of 12 samples · 6 unverified · 4 pointer-only (licence)
  Despite the promising progress on LVLMs, we find that LVLMs suffer from the hallucination problem, i.
• RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
  27 May 2024 5 repositories listed Syntology ran 14 of 22 samples · 8 unverified · 8 pointer-only (licence)
  Traditional feedback learning for hallucination reduction relies on labor-intensive manual labeling or expensive proprietary models.
• MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
  29 Jan 2024 3 repositories listed Syntology ran 0 of 2 samples · 2 unverified · 2 pointer-only (licence)
  In this work, we propose a simple yet effective training strategy MoE-Tuning for LVLMs.
• Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models
  12 Jun 2024 2 repositories listed
  Large audio-language models (LALMs) enhance traditional large language models by integrating audio perception capabilities, allowing them to tackle audio-related tasks.
• HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
  1 Mar 2024 2 repositories listed Syntology ran 7 of 12 samples · 5 unverified
  While large vision-language models (LVLMs) have demonstrated impressive capabilities in interpreting multi-modal contexts, they invariably suffer from object hallucinations (OH).
• Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding
  23 Feb 2024 2 repositories listed Syntology ran 11 of 17 samples · 6 unverified · 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.
• Ferret: Refer and Ground Anything Anywhere at Any Granularity
  11 Oct 2023 2 repositories listed Syntology ran 7 of 8 samples · 1 unverified · 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.
• HallE-Control: Controlling Object Hallucination in Large Multimodal Models
  3 Oct 2023 2 repositories listed Syntology ran 5 of 9 samples · 4 unverified · 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.
• Revisit What You See: Disclose Language Prior in Vision Tokens for Efficient Guided Decoding of LVLMs
  11 Jun 2025 1 repository listed
  Our 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…
• SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding
  10 Jun 2025 1 repository listed Syntology ran 2 of 4 samples · 2 unverified · 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.
• Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models
  26 May 2025 1 repository listed
  Despite significant advancements in Large Vision-Language Models, Object Hallucination (OH) remains a persistent challenge.
• CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning
  25 Mar 2025 1 repository listed Syntology ran 4 of 5 samples · 1 unverified · 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.
• ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models
  17 Mar 2025 1 repository listed Syntology ran 0 of 1 samples · 1 unverified · 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,…
• TruthPrInt: Mitigating LVLM Object Hallucination Via Latent Truthful-Guided Pre-Intervention
  13 Mar 2025 1 repository listed
  In 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.
• Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow
  28 Feb 2025 1 repository listed Syntology ran 3 of 11 samples · 8 unverified
  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.
• Vision-Encoders (Already) Know What They See: Mitigating Object Hallucination via Simple Fine-Grained CLIPScore
  27 Feb 2025 1 repository listed
  Recently, Large Vision-Language Models (LVLMs) show remarkable performance across various domains.
• HALLUCINOGEN: A Benchmark for Evaluating Object Hallucination in Large Visual-Language Models
  29 Dec 2024 1 repository listed
  Large Vision-Language Models (LVLMs) have demonstrated remarkable performance in performing complex multimodal tasks.
• Extract Free Dense Misalignment from CLIP
  24 Dec 2024 1 repository listed
  However, 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.
• Unified Triplet-Level Hallucination Evaluation for Large Vision-Language Models
  30 Oct 2024 1 repository listed
  The 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.
• Mitigating Object Hallucination via Concentric Causal Attention
  21 Oct 2024 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  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.
• Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding
  17 Oct 2024 1 repository listed
  Lastly, 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.
• Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models
  4 Oct 2024 1 repository listed Syntology ran 2 of 3 samples · 1 unverified · 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.
• Understanding Multimodal Hallucination with Parameter-Free Representation Alignment
  2 Sep 2024 1 repository listed
  To 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…
• Multi-Object Hallucination in Vision-Language Models
  8 Jul 2024 1 repository listed Syntology ran 7 of 8 samples · 1 unverified · 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 Tasks
  27 May 2024 1 repository listed
  During answer inference, GAMA integrates the image, generated narrative, and a task-specific question prompt to infer answers for different vision-language tasks.
• Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models
  18 Feb 2024 1 repository listed Syntology ran 0 of 3 samples · 3 unverified · 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.
• EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models
  15 Feb 2024 1 repository listed Syntology ran 6 of 7 samples · 1 unverified · 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…
• Instruction Makes a Difference
  1 Feb 2024 1 repository listed
  We 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…
• Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency
  8 Dec 2023 1 repository listed Syntology ran 13 of 17 samples · 4 unverified · 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.

Syntology lines on 18 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. Read from the graph 2026-09-24.