Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yao, Jihan, Kulshrestha, Achin, Rauschmayr, Nathalie, Roberts, Reed, Zhu, Banghua, Tsvetkov, Yulia, Tombari, Federico
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Gatekeeper: Improving Model Cascades Through Confidence Tuning
par: Rabanser, Stephan, et autres
Publié: (2025)

Omnia de EgoTempo: Benchmarking Temporal Understanding of Multi-Modal LLMs in Egocentric Videos
par: Plizzari, Chiara, et autres
Publié: (2025)

Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
par: Feng, Shangbin, et autres
Publié: (2024)

R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs
par: Xie, Jiahao, et autres
Publié: (2026)

Extracting Training Data from Document-Based VQA Models
par: Pinto, Francesco, et autres
Publié: (2024)

SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models
par: Xie, Jiahao, et autres
Publié: (2026)

Test-Time Visual In-Context Tuning
par: Xie, Jiahao, et autres
Publié: (2025)

BRAVE: Broadening the visual encoding of vision-language models
par: Kar, Oğuzhan Fatih, et autres
Publié: (2024)

Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration
par: Feng, Shangbin, et autres
Publié: (2024)

Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only
par: Yao, Jihan, et autres
Publié: (2024)

Teaching LLMs to Abstain across Languages via Multilingual Feedback
par: Feng, Shangbin, et autres
Publié: (2024)

MMMG: a Comprehensive and Reliable Evaluation Suite for Multitask Multimodal Generation
par: Yao, Jihan, et autres
Publié: (2025)

MapTrace: Scalable Data Generation for Route Tracing on Maps
par: Panagopoulou, Artemis, et autres
Publié: (2025)

JPEG-LM: LLMs as Image Generators with Canonical Codec Representations
par: Han, Xiaochuang, et autres
Publié: (2024)

David helps Goliath: Inference-Time Collaboration Between Small Specialized and Large General Diffusion LMs
par: Han, Xiaochuang, et autres
Publié: (2023)

Know Your Limits: A Survey of Abstention in Large Language Models
par: Wen, Bingbing, et autres
Publié: (2024)

RiemanLine: Riemannian Manifold Representation of 3D Lines for Factor Graph Optimization
par: Li, Yan, et autres
Publié: (2025)

MADFormer: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation
par: Chen, Junhao, et autres
Publié: (2025)

AbstainGNN: Teaching Graph Neural Networks to Abstain for Graph Classification
par: Lin, Xixun, et autres
Publié: (2026)

EgoSocial: Benchmarking Proactive Intervention Ability of Omnimodal LLMs via Egocentric Social Interaction Perception
par: Wang, Xijun, et autres
Publié: (2025)

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

Celebrating Excellence: Recognizing the 2024 SID Award Winners
par: Achin Bhowmik
Publié: (2024)

The Evolving Landscape of Human Interface to Technology
par: Achin Bhowmik
Publié: (2024)

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

Data Swarms: Optimizable Generation of Synthetic Evaluation Data
par: Feng, Shangbin, et autres
Publié: (2025)

Finding Flawed Fictions: Evaluating Complex Reasoning in Language Models via Plot Hole Detection
par: Ahuja, Kabir, et autres
Publié: (2025)

Steerable Chatbots: Personalizing LLMs with Preference-Based Activation Steering
par: Bo, Jessica Y., et autres
Publié: (2025)

Self-supervised Latent Space Optimization with Nebula Variational Coding
par: Wang, Yida, et autres
Publié: (2025)

DocParseNet: Advanced Semantic Segmentation and OCR Embeddings for Efficient Scanned Document Annotation
par: Mohammadshirazi, Ahmad, et autres
Publié: (2024)

Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation
par: Baan, Joris, et autres
Publié: (2026)

Elastic3D: Controllable Stereo Video Conversion with Guided Latent Decoding
par: Metzger, Nando, et autres
Publié: (2025)

Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty
par: Machcha, Sravanthi, et autres
Publié: (2026)

3D-LATTE: Latent Space 3D Editing from Textual Instructions
par: Parelli, Maria, et autres
Publié: (2025)

Trust or Abstain? A Self-Aware RAG Approach
par: Zhu, Xi, et autres
Publié: (2026)

Do not Abstain! Identify and Solve the Uncertainty
par: Liu, Jingyu, et autres
Publié: (2025)

Interpretable and Fair Mechanisms for Abstaining Classifiers
par: Lenders, Daphne, et autres
Publié: (2025)

Interpretable and Fair Mechanisms for Abstaining Classifiers
par: Lenders, Daphne, et autres
Publié: (2024)

Abstaining Machine Learning -- Philosophical Considerations
par: Schuster, Daniela
Publié: (2024)

PRISM: Probabilistic Representation for Integrated Shape Modeling and Generation
par: Cheng, Lei, et autres
Publié: (2025)

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