Rethinking in Spikes: Mitigating Hallucinations in MDLMs with Step-Aware Decoding
Rethinking in Spikes: Mitigating Hallucinations in MDLMs with Step-Aware Decoding
Step-Aware Decoding reduces the hallucination problem of Multimodal Large Models (MDLMs) by introducing a context-aware mechanism in the decoding steps. This method reduces the hallucination rate by 15% on benchmark tests such as MMLU and HumanEval, while improving reasoning speed by 2.1x. The technology is open-source, supporting context lengths of 128k tokens, and can be called via API.
Published on Oct 14
Authors:
,
,
,
,
,
,
,
,
,
,
View arXiv page View PDF GitHub 3 Add to collection
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.12901 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.12901 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.12901 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
Source: Hugging Face Daily Papers · huggingface.co