Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs

Feilong Tang, Zile Huang, Chengzhi Liu, Qiang Sun, Harry Yang +1 more
2/12/2026

No official code found. Best implementation: Everlyn-Labs/ANTRP (164 stars, last commit 2025-03-12).

Semantic Scholar

Code Implementations(1)

Everlyn-Labs/ANTRPCommunity75%

Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs

16432C, C++Sep 28, 20241 years ago

Similar Papers

EvoRainbow: Combining Improvements in Evolutionary Reinforcement Learning for Policy Search

99% match1 repo402026

SplineGS: Learning Smooth Trajectories in Gaussian Splatting for Dynamic Scene Reconstruction

99% match2026

DynaDojo: An Extensible Platform for Benchmarking Scaling in Dynamical System Identification

99% match2026

LineFit: A Geometric Approach for Fitting Line Segments in Images

99% match2026

CAN: Leveraging Clients As Navigators for Generative Replay in Federated Continual Learning

99% match1 repo32026

Exploring The Forgetting in Adversarial Training: A Novel Method for Enhancing Robustness

99% match2026

Cite this paper

@article{tang2026intervening,
  title  = {Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs},
  author = {Feilong Tang and Zile Huang and Chengzhi Liu and Qiang Sun and Harry Yang and Ser-Nam Lim},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:07d64f525e478d095bb4b38ec72c1d747fbfebb5},
  journal = {ICLR 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/07d64f525e478d095bb4b38ec72c1d747fbfebb5.svg)](https://codeofpaper.com/paper/07d64f525e478d095bb4b38ec72c1d747fbfebb5)

Discussion