arXiv AI

ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision Transformers

The paper introduces ResLRP, an extension of Layer-wise Relevance Propagation that explicitly handles residual connections in Vision Transformers to prevent attribution explosion. It demonstrates that residual cancellation causes instability in ViT explanations, and that ResLRP improves faithfulness and localization across a wide range of ViT architectures, including Vision Language Models. The method also provides a diagnostic measure for predicting attribution degradation and successfully localizes Sparse Autoencoder features.

arXiv AI
Sep 2

HiLRP: Toward One Trustworthy Explanation for Vision Transformer: Conservation-Valid Attribution via Attention Primitives

HiLRP introduces a unified attribution framework for Vision Transformers (ViTs) that addresses the challenges posed by diverse architectural designs. By decomposing ViT operations into four basic types—linear maps, bilinear mixing, normalization/gating, and reindexing—HiLRP applies conservation‑satisfying relevance rules, enabling reliable explanations across a wide range of backbones. The method outperforms 14 existing attribution techniques on 10 architectures, maintaining conservation and improving localization accuracy (0.97 Pointing) compared to competitors.

By Sathiyamohan Nishankar, Pubudu Sanjeewani, Asanka Perera, Selvarajah Thuseethan
arXiv Computer Vision
Aug 28

Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information

The paper introduces Visual Retrieval Heads (VRHs), a small fraction of attention heads in vision‑language models that are causally responsible for grounding text descriptions to image regions. By recasting head‑scoring methods and evaluating across eleven VLMs and five benchmarks, the authors show that masking the top 20 VRHs can drop grounding accuracy by up to 80 percentage points, while random masking has little effect. VRHs generalize across various visual reference tasks, preserve output format while corrupting localization, and transfer causally across models sharing an LLM backbone.

By Chanho Park, Daehyeon Choi, Jihyun Lee, Minhyuk Sung
arXiv Machine Learning
Jul 14

Gradient-Skipping Relevance Propagation for Efficient Explainability of Vision Transformers

arXiv:2607. 10365v1 Announce Type: cross Abstract: Vision Transformers (ViTs) are difficult to interpret because current methods of relevance propagation and attention flow do not fully consider some key architectural features, such as the uneven importance of attention heads and residual connections.

By Christopher Buratti, Michele Marchetti, Federica Parlapiano, Davide Traini, Domenico Ursino, Luca Virgili
arXiv AI
Jun 30

FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models

arXiv:2606. 29431v1 Announce Type: new Abstract: Despite the impressive capabilities of Large Vision-Language Models (LVLMs), they remain susceptible to hallucination, generating content inconsistent with the input image.

By Yichen Guo, Kai Tang, Fenglai Lin, Yiding Sun, Dongshuo Zhang, Wenya Wang, Lin William Cong, Shanghang Zhang
arXiv AI
Jun 16

Mitigating Object Hallucinations in LVLMs via Attention Imbalance Rectification

arXiv:2603. 24058v2 Announce Type: replace-cross Abstract: Object hallucination in Large Vision-Language Models (LVLMs) severely compromises their reliability in real-world applications, posing a critical barrier to their deployment in high-stakes scenarios such as autonomous driving and medical image analysis.

By Han Sun, Qin Li, Peixin Wang, Min Zhang
arXiv Machine Learning
Sep 10

LLM Layers Immediately Correct Each Other

arXiv:2609.07876v1 Announce Type: cross Abstract: Recent methods in language model interpretability employ techniques such as sparse autoencoders to decompose residual stream contributions into linea...

By Arjun Patrawala, Jiahai Feng, Erik Jones, Jacob Steinhardt
Hugging Face Trending Papers
Aug 27

Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information

The paper demonstrates that vision‑language models (VLMs) possess a small set of attention heads, called Visual Retrieval Heads (VRHs), that are causally responsible for linking text prompts to specific image regions. By adapting head‑scoring techniques from language models, the authors identify VRHs as the heads whose attention from output prediction tokens, summed over the ground‑truth referent region, most reliably indicates causal grounding. Experiments across eleven VLMs and five referring‑expression benchmarks show that masking the top 20 VRHs can drop grounding accuracy by up to 80 percentage points, while random masking has little effect, and that VRHs generalize across diverse visual tasks and transfer across models sharing an LLM backbone.