✨Towards Mitigating Hallucinations in Large Vision-Language Models by Refining Textual Embeddings

📝 Summary:
Large Vision-Language Models suffer from language bias leading to hallucinations. Our method refines textual embeddings by integrating average-pooled visual features. This simple approach improves visual grounding and reduces hallucinations.

🔹 Publication Date: Published on Nov 7

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.05017
• PDF: https://arxiv.org/pdf/2511.05017

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#VisionLanguageModels #AIHallucinations #VisualGrounding #DeepLearning #NLP

✨HaluMem: Evaluating Hallucinations in Memory Systems of Agents

📝 Summary:
HaluMem is a new benchmark that evaluates memory hallucinations in AI systems by localizing them to specific stages: extraction, updating, and question answering. It uses large human-AI interaction datasets. Findings show current systems accumulate hallucinations during extraction and updating, w...

🔹 Publication Date: Published on Nov 5

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03506
• PDF: https://arxiv.org/pdf/2511.03506
• Github: https://github.com/MemTensor/HaluMem

✨ Datasets citing this paper:
• https://huggingface.co/datasets/IAAR-Shanghai/HaluMem

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#AIHallucinations #AIAgents #MemorySystems #LLM #AIResearch

✨From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language Models

📝 Summary:
Tool-augmented LLMs exhibit Tool-Induced Myopia TIM, treating tool outputs as substitutes for true reasoning. This improves final answer accuracy but significantly degrades reasoning quality. A proposed framework realigns these models to use tools as assistive evidence, enhancing both accuracy an...

🔹 Publication Date: Published on Nov 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.10899
• PDF: https://arxiv.org/pdf/2511.10899

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LLM #AIResearch #Reasoning #ToolAugmentation #AIHallucinations

✨Draft and Refine with Visual Experts

📝 Summary:
The Draft and Refine DnR framework improves visual grounding in LVLMs. It uses a novel question-conditioned utilization metric to measure visual evidence reliance. DnR refines responses with external visual experts, reducing hallucinations and boosting accuracy.

🔹 Publication Date: Published on Nov 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.11005
• PDF: https://arxiv.org/pdf/2511.11005
• Github: https://github.com/EavnJeong/Draft-and-Refine-with-Visual-Experts

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LVLMs #VisualGrounding #AIHallucinations #ComputerVision #DeepLearning

✨Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation

📝 Summary:
MLLMs struggle with hallucinations on counterfactual videos. DualityForge synthesizes counterfactual video data and QA pairs through diffusion-based editing to address this. This method significantly reduces model hallucinations and improves general performance.

🔹 Publication Date: Published on Dec 30, 2025

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2512.24271
• PDF: https://arxiv.org/pdf/2512.24271
• Project Page: https://amap-ml.github.io/Taming-Hallucinations/
• Github: https://github.com/AMAP-ML/Taming-Hallucinations

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#MLLMs #VideoUnderstanding #AIHallucinations #GenerativeAI #MachineLearning

✨Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models

📝 Summary:
Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements - posing a critical barrier to their trustworthy deployment. In this work, we propose a n...

🔹 Publication Date: Published on Mar 16

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.15557
• PDF: https://arxiv.org/pdf/2603.15557
• Github: https://github.com/Lexiang-Xiong/CAD

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#VLM #AIHallucinations #TrustworthyAI #ExplainableAI #AIResearch

✨FINER: MLLMs Hallucinate under Fine-grained Negative Queries

📝 Summary:
Multimodal language models hallucinate under fine-grained negative queries, a gap in existing benchmarks. This paper introduces FINER benchmarks and FINER-Tuning, a DPO method, to address this. It significantly reduces hallucinations and boosts general MLLM capabilities.

🔹 Publication Date: Published on Mar 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.17662
• PDF: https://arxiv.org/pdf/2603.17662
• Project Page: https://explainableml.github.io/finer-project/
• Github: https://github.com/ExplainableML/finer

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#MLLMs #AIHallucinations #Benchmarking #DeepLearning #AIResearch

✨Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models

📝 Summary:
Native omni-modal LLMs surprisingly show a visual preference, unlike traditional text-dominant models. This preference emerges in later layers and helps diagnose cross-modal hallucinations, improving model trustworthiness.

🔹 Publication Date: Published on Apr 18

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.16902
• PDF: https://arxiv.org/pdf/2604.16902
• Github: https://github.com/icip-cas/OmniPreference

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#OmniModalLLM #ModalityPreference #AIHallucinations #TrustworthyAI #AIResearch