TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs
- 12 September 2026
- book chapter
- Published by Springer Nature
- p. 580-598
Abstract
No abstract availableKeywords
All Related Versions
This publication has 55 references indexed in Scilit:
- Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs2024
- MM1: Methods, Analysis and Insights from Multimodal LLM Pre-training2024
- CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs2024
- Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization2024
- Effectiveness assessment of recent large vision-language modelsVisual Intelligence, 2024
- MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model2023
- An Empirical Study of Training End-to-End Vision-and-Language Transformers2022
- Causal Attention for Vision-Language Tasks2021
- An algorithm for the machine calculation of complex Fourier seriesMathematics of Computation, 1965
- RANK ANALYSIS OF INCOMPLETE BLOCK DESIGNSBiometrika, 1952