Pith. sign in

REVIEW

Improving Alignment in LVLMs with Debiased Self-Judgment

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2508.20655 v2 pith:GJIXOLH4 submitted 2025-08-28 cs.CV cs.CL

Improving Alignment in LVLMs with Debiased Self-Judgment

classification cs.CV cs.CL
keywords alignmentlvlmstuningaligningapproachdebiasedexternallarge
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The rapid advancements in Large Language Models (LLMs) and Large Visual-Language Models (LVLMs) have opened up new opportunities for integrating visual and linguistic modalities. However, effectively aligning these modalities remains challenging, often leading to hallucinations--where generated outputs are not grounded in the visual input--and raising safety concerns across various domains. Existing alignment methods, such as instruction tuning and preference tuning, often rely on external datasets, human annotations, or complex post-processing, which limit scalability and increase costs. To address these challenges, we propose a novel approach that generates the debiased self-judgment score, a self-evaluation metric created internally by the model without relying on external resources. This enables the model to autonomously improve alignment. Our method enhances both decoding strategies and preference tuning processes, resulting in reduced hallucinations, enhanced safety, and improved overall capability. Empirical results show that our approach significantly outperforms traditional methods, offering a more effective solution for aligning LVLMs.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.