Imagen de Portada

Self-Improving VLM Judges Without Human Annotations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lin, Inna Wanyin, Hu, Yushi, Li, Shuyue Stella, Geng, Scott, Koh, Pang Wei, Zettlemoyer, Luke, Althoff, Tim, Ghazvininejad, Marjan
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Multimodal RewardBench: Holistic Evaluation of Reward Models for Vision Language Models
por: Yasunaga, Michihiro, et al.
Publicado: (2025)

GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluation
por: Kamath, Amita, et al.
Publicado: (2025)

Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image
por: Hu, Yushi, et al.
Publicado: (2025)

Facilitating Self-Guided Mental Health Interventions Through Human-Language Model Interaction: A Case Study of Cognitive Restructuring
por: Sharma, Ashish, et al.
Publicado: (2023)

ALMA: Alignment with Minimal Annotation
por: Yasunaga, Michihiro, et al.
Publicado: (2024)

IMBUE: Improving Interpersonal Effectiveness through Simulation and Just-in-time Feedback with Human-Language Model Interaction
por: Lin, Inna Wanyin, et al.
Publicado: (2024)

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

A Computational Framework for Behavioral Assessment of LLM Therapists
por: Chiu, Yu Ying, et al.
Publicado: (2024)

Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
por: Saha, Swarnadeep, et al.
Publicado: (2025)

Unified Text-Image Generation with Weakness-Targeted Post-Training
por: Chen, Jiahui, et al.
Publicado: (2026)

CandorMD: An AI-Assisted Audio Simulation and Feedback System for Training Clinicians for Medical Error Disclosure
por: Lin, Inna Wanyin, et al.
Publicado: (2026)

Representation Deficiency in Masked Language Modeling
por: Meng, Yu, et al.
Publicado: (2023)

A Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation
por: Zhao, Yi, et al.
Publicado: (2026)

Precise Information Control in Long-Form Text Generation
por: He, Jacqueline, et al.
Publicado: (2025)

RISE: Enhancing VLM Image Annotation with Self-Supervised Reasoning
por: Hu, Suhang, et al.
Publicado: (2025)

Spurious Rewards: Rethinking Training Signals in RLVR
por: Shao, Rulin, et al.
Publicado: (2025)

AutoJudge: Judge Decoding Without Manual Annotation
por: Garipov, Roman, et al.
Publicado: (2025)

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

reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs
por: Wu, Zhaofeng, et al.
Publicado: (2025)

Scaling Retrieval-Based Language Models with a Trillion-Token Datastore
por: Shao, Rulin, et al.
Publicado: (2024)

Anchored Decoding: Provably Reducing Copyright Risk for Any Language Model
por: He, Jacqueline, et al.
Publicado: (2026)

Annotation alignment: Comparing LLM and human annotations of conversational safety
por: Movva, Rajiv, et al.
Publicado: (2024)

Reliable, Adaptable, and Attributable Language Models with Retrieval
por: Asai, Akari, et al.
Publicado: (2024)

Can External Validation Tools Improve Annotation Quality for LLM-as-a-Judge?
por: Findeis, Arduin, et al.
Publicado: (2025)

MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning
por: Li, Shuyue Stella, et al.
Publicado: (2024)

ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data
por: Chen, Tong, et al.
Publicado: (2025)

PrefDisco: Benchmarking Proactive Personalized Reasoning
por: Li, Shuyue Stella, et al.
Publicado: (2025)

Reconstruction Alignment Improves Unified Multimodal Models
por: Xie, Ji, et al.
Publicado: (2025)

TV2TV: A Unified Framework for Interleaved Language and Video Generation
por: Han, Xiaochuang, et al.
Publicado: (2025)

EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics
por: Li, Shuyue Stella, et al.
Publicado: (2026)

CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation
por: Chen, Tong, et al.
Publicado: (2024)

BLaVe-CoT: Consistency-Aware Visual Question Answering for Blind and Low Vision Users
por: Cheng, Wanyin, et al.
Publicado: (2025)

Cold-Start Personalization via Training-Free Priors from Structured World Models
por: Bose, Avinandan, et al.
Publicado: (2026)

V-Zero: Self-Improving Multimodal Reasoning with Zero Annotation
por: Wang, Han, et al.
Publicado: (2026)

Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models
por: Hu, Yushi, et al.
Publicado: (2024)

Improving MoE Compute Efficiency by Composing Weight and Data Sparsity
por: Kilian, Maciej, et al.
Publicado: (2026)

Computational Tradeoffs in Image Synthesis: Diffusion, Masked-Token, and Next-Token Prediction
por: Kilian, Maciej, et al.
Publicado: (2024)

Comparing Hallucination Detection Metrics for Multilingual Generation
por: Kang, Haoqiang, et al.
Publicado: (2024)

(Mis)Fitting: A Survey of Scaling Laws
por: Li, Margaret, et al.
Publicado: (2025)

A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakage
por: Xin, Rui, et al.
Publicado: (2025)