Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding
Large vision-language models (LVLMs) achieve strong performance on multimodal tasks, yet they often default to their language prior (LP) -- memorized textual patterns from pre-training while under-utilizing visual evidence. Prior analyses of LP mostly rely on input-output probing, which fails to reveal the internal mechanisms governing when and how vision influences model behavior. To address this gap, we present the first systematic analysis of language prior through the lens of chain-of-embedding, which examines the layer-wise representation dynamics within LVLMs. Our analysis reveals a universal phenomenon: each model exhibits a Visual Integration Point (VIP), a critical layer at which visual information begins to meaningfully reshape hidden representations and influence decoding for multimodal reasoning. Building on this observation, we introduce the Total Visual Integration (TVI) estimator, which aggregates representational discrepancy beyond the VIP to quantify how strongly visual query influences response generation. Across 60 model-dataset combinations spanning 10 contemporary LVLMs and 6 benchmarks, we demonstrate that VIP consistently emerges, and that TVI reliably predicts the strength of language prior. This offers a principled toolkit for diagnosing and understanding language prior in LVLMs.
Code (0)
등록된 구현이 없습니다.
Tasks
Multimodal ReasoningResponse GenerationSimilar Papers 제목 키워드 기반
DRIVINGVQA: Analyzing Visual Chain-of-Thought Reasoning of Vision Language Models in Real-World Scenarios with Driving Theory Tests
Large vision-language models (LVLMs) augment language models with visual understanding, enabling multimodal reasoning. However, due to the modality gap between textual and visual data, they often face significant challen…
Multimodal ReasoningMultiple-choiceVisual ReasoningVisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors
Understanding multi-image, multi-turn scenarios is a critical yet underexplored capability for Large Vision-Language Models (LVLMs). Existing benchmarks predominantly focus on static or horizontal comparisons -- e.g., sp…
Visual ReasoningSVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding
Despite the significant advancements of Large Vision-Language Models (LVLMs) on established benchmarks, there remains a notable gap in suitable evaluation regarding their applicability in the emerging domain of long-cont…
Question AnsweringStreaming video understandingVideo UnderstandingR-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs
Large vision-language models (LVLMs) have demonstrated impressive performance in various multimodal understanding and reasoning tasks. However, they still struggle with object hallucinations, i.e., the claim of nonexiste…
Response GenerationChain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models
In the realm of vision-language understanding, the proficiency of models in interpreting and reasoning over visual content has become a cornerstone for numerous applications. However, it is challenging for the visual enc…
Instruction Followingvisual instruction followingVisual Question Answering