What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness
Hallucination remains one of the key challenges undermining the reliability of Large Vision-Language Models (LVLMs). But what makes an LVLM hallucinate less? Many existing efforts focus on improving internal components of the model. We argue that hallucination fundamentally stems from how the model architecture is designed. To investigate this, we factor the architecture design into three dimensions: Linguistic Foundation (LF), Visual Representation (VR), and Semantic Alignment (SA), and categor
Record details
Published: 29 May 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Finance, VC & PE
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty
arXiv · 29 May 2026
Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Convention Mismatch, and an Honest Baseline at 25.6% WER (13.8% cWER)
arXiv · 29 May 2026
Rationalize: Shared Semantic Reasoning for Human-AI Alignment
arXiv · 28 May 2026
On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance
arXiv · 30 May 2026
Beyond Bilingual Transfer: Multilingual Code-Switching in Instruction Tuning
arXiv · 28 May 2026
Models That Know How Evaluations Are Designed Score Safer
arXiv · 27 May 2026
How to cite this record
ethics.ai (29 May 2026), “What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness,” evidence record 3452, https://ethics.ai/record/3452 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.