No article text was recorded for this version.
training-free hallucination mitigation
Version 2 of 285 papers99 conceptsfrozen 2026-10-04
Papers in this version
- Blog: CAAC: Confidence-Aware Attention Calibration to Reduce Hallucinations in Large Vision-Language Models
- Blog: Efficient Contrastive Decoding with Probabilistic Hallucination Detection - Mitigating Hallucinations in Large Vision Language Models -
- Blog: A Large Vision-Language Model based Environment Perception System for Visually Impaired People
- Blog: Capturing Gaze Shifts for Guidance: Cross-Modal Fusion Enhancement for VLM Hallucination Mitigation
- Blog: Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention
- Blog: Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy
- Blog: Mitigating Large Vision-Language Model Hallucination at Post-hoc via Multi-agent System
- Blog: Beyond Logits: Coherent Hallucination Mitigation via Attention Contrastive Decoding
- Blog: Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
- Blog: Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance
- Blog: Mitigating Hallucinations in Multi-modal Large Language Models via Image Token Attention-Guided Decoding
- Blog: ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models
- Blog: Mitigating Object Hallucination in Large Vision-Language Models via Classifier-Free Guidance
- Blog: Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
- Blog: CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention
- Blog: A Unified Hallucination Mitigation Framework for Large Vision-Language Models
- Blog: Detection-Guided Attention Steering for Vision Language Models
- Blog: INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling
- Blog: VSCoDe: Visual-Augmentation Selection for Contrastive Decoding
- Blog: Fantastic Tractor-Dogs and How Not to Find Them With Open-Vocabulary Detectors
- Blog: SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense
- Blog: Pelican: Correcting Hallucination in Vision-LLMs via Claim Decomposition and Program of Thought Verification
- Blog: Mitigating Hallucination in Visual-Language Models via Re-Balancing Contrastive Decoding
- Blog: Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models
- Blog: HalluTrace: Causal Attribution and Source-Targeted Decoding for Hallucination in Large Vision-Language Models
- Blog: Mitigating Hallucinations in Large Vision-Language Models (LVLMs) via Language-Contrastive Decoding (LCD)
- Blog: SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision
- Blog: Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence
- Blog: PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
- Blog: IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models
- Blog: Multi-Frequency Contrastive Decoding: Alleviating Hallucinations for Large Vision-Language Models
- Blog: OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation
- Blog: Treble Counterfactual VLMs: A Causal Approach to Hallucination
- Blog: Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMs
- Blog: INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling
- Blog: Fidelity-Enriched Contrastive Search: Reconciling the Faithfulness-Diversity Trade-Off in Text Generation
- Blog: Gradient-guided Attention Map Editing: Towards Efficient Contextual Hallucination Mitigation
- Blog: Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding
- Blog: Do You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble Decoding
- Blog: Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Information
- Blog: MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation
- Blog: Mixture of Decoding: An Attention-Inspired Adaptive Decoding Strategy to Mitigate Hallucinations in Large Vision-Language Models
- Blog: Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs
- Blog: Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
- Blog: Beyond Attention Imbalance: Mitigating Hallucinations via Spectral Surgery
- Blog: Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
- Blog: CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding
- Blog: Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding
- Blog: Scalpel: Fine-Grained Alignment of Attention Activation Manifolds via Mixture Gaussian Bridges to Mitigate Multimodal Hallucination
- Blog: Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence
- Blog: MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation
- Blog: HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding
- Blog: Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding
- Blog: MedHEval: Benchmarking Hallucinations and Mitigation Strategies in Medical Large Vision-Language Models
- Blog: Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs
- Blog: ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models
- Blog: Distillation of encoder-decoder transformers for sequence labelling
- Blog: Sycophancy in vision-language models: A systematic analysis and an inference-time mitigation framework
- Blog: ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large Language Models
- Blog: MASS: Overcoming Language Bias in Image-Text Matching
Showing 60 of 85 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_training_free_hallucination_mitigation_efe3f5d1,
title = {training-free hallucination mitigation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/training-free-hallucination-mitigation/rdr_efe3f5d1a07147c88b5da2822914ed61},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_training_free_hallucination_mitigation_efe3f5d1_v2,
title = {training-free hallucination mitigation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/training-free-hallucination-mitigation/rdr_efe3f5d1a07147c88b5da2822914ed61/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}