Cover Image

Reading Between the Lines: Abstaining from VLM-Generated OCR Errors via Latent Representation Probes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yao, Jihan, Kulshrestha, Achin, Rauschmayr, Nathalie, Roberts, Reed, Zhu, Banghua, Tsvetkov, Yulia, Tombari, Federico
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Gatekeeper: Improving Model Cascades Through Confidence Tuning
by: Rabanser, Stephan, et al.
Published: (2025)

Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos
by: Plizzari, Chiara, et al.
Published: (2025)

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
by: Feng, Shangbin, et al.
Published: (2024)

R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs
by: Xie, Jiahao, et al.
Published: (2026)

Extracting Training Data from Document-Based VQA Models
by: Pinto, Francesco, et al.
Published: (2024)

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models
by: Xie, Jiahao, et al.
Published: (2026)

Test-Time Visual In-Context Tuning
by: Xie, Jiahao, et al.
Published: (2025)

BRAVE: Broadening the visual encoding of vision-language models
by: Kar, Oğuzhan Fatih, et al.
Published: (2024)

Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration
by: Feng, Shangbin, et al.
Published: (2024)

Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only
by: Yao, Jihan, et al.
Published: (2024)

Teaching LLMs to Abstain across Languages via Multilingual Feedback
by: Feng, Shangbin, et al.
Published: (2024)

MMMG: a Comprehensive and Reliable Evaluation Suite for Multitask Multimodal Generation
by: Yao, Jihan, et al.
Published: (2025)

MapTrace: Scalable Data Generation for Route Tracing on Maps
by: Panagopoulou, Artemis, et al.
Published: (2025)

JPEG-LM: LLMs as Image Generators with Canonical Codec Representations
by: Han, Xiaochuang, et al.
Published: (2024)

David helps Goliath: Inference-Time Collaboration Between Small Specialized and Large General Diffusion LMs
by: Han, Xiaochuang, et al.
Published: (2023)

Know Your Limits: A Survey of Abstention in Large Language Models
by: Wen, Bingbing, et al.
Published: (2024)

RiemanLine: Riemannian Manifold Representation of 3D Lines for Factor Graph Optimization
by: Li, Yan, et al.
Published: (2025)

MADFormer: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation
by: Chen, Junhao, et al.
Published: (2025)

AbstainGNN: Teaching Graph Neural Networks to Abstain for Graph Classification
by: Lin, Xixun, et al.
Published: (2026)

EgoSocial: Benchmarking Proactive Intervention Ability of Omnimodal LLMs via Egocentric Social Interaction Perception
by: Wang, Xijun, et al.
Published: (2025)

Chronic Kidney Disease Detection Using RF Based Data Imputation and Meta-Ensemble Learning
by: Jain, Achin
Published: (2026)

Celebrating Excellence: Recognizing the 2024 SID Award Winners
by: Achin Bhowmik
Published: (2024)

The Evolving Landscape of Human Interface to Technology
by: Achin Bhowmik
Published: (2024)

Traversing the Color Gamut: Visual Realism or Artistic Surrealism?
by: Achin Bhowmik
Published: (2024)

Data Swarms: Optimizable Generation of Synthetic Evaluation Data
by: Feng, Shangbin, et al.
Published: (2025)

Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection
by: Ahuja, Kabir, et al.
Published: (2025)

Steerable Chatbots: Personalizing LLMs with Preference-Based Activation Steering
by: Bo, Jessica Y., et al.
Published: (2025)

Self-supervised Latent Space Optimization with Nebula Variational Coding
by: Wang, Yida, et al.
Published: (2025)

DocParseNet: Advanced Semantic Segmentation and OCR Embeddings for Efficient Scanned Document Annotation
by: Mohammadshirazi, Ahmad, et al.
Published: (2024)

Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation
by: Baan, Joris, et al.
Published: (2026)

Elastic3D: Controllable Stereo Video Conversion with Guided Latent Decoding
by: Metzger, Nando, et al.
Published: (2025)

Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty
by: Machcha, Sravanthi, et al.
Published: (2026)

3D-LATTE: Latent Space 3D Editing from Textual Instructions
by: Parelli, Maria, et al.
Published: (2025)

Trust or Abstain? A Self-Aware RAG Approach
by: Zhu, Xi, et al.
Published: (2026)

Do not Abstain! Identify and Solve the Uncertainty
by: Liu, Jingyu, et al.
Published: (2025)

Interpretable and Fair Mechanisms for Abstaining Classifiers
by: Lenders, Daphne, et al.
Published: (2025)

Interpretable and Fair Mechanisms for Abstaining Classifiers
by: Lenders, Daphne, et al.
Published: (2024)

Abstaining Machine Learning -- Philosophical Considerations
by: Schuster, Daniela
Published: (2024)

PRISM: Probabilistic Representation for Integrated Shape Modeling and Generation
by: Cheng, Lei, et al.
Published: (2025)

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
by: Sclar, Melanie, et al.
Published: (2023)