Ganqu Cui

papers

1,185

total citations

papers (10)

RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback

CVPR 2024arXiv

361

citations

ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback

ICML 2024arXiv

214

citations

Advancing LLM Reasoning Generalists with Preference Trees

ICLR 2025arXiv

183

citations

Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations

NEURIPS 2023arXiv

134

citations

AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset

COLM 2025arXiv

citations

Moderate-fitting as a Natural Backdoor Defender for Pre-trained Language Models

NEURIPS 2022

citations

Ganqu Cui

papers (10)

RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback

ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback

Advancing LLM Reasoning Generalists with Preference Trees

Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations

TTRL: Test-Time Reinforcement Learning

A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks

RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness

Scaling Physical Reasoning with the PHYSICS Dataset

AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset

Moderate-fitting as a Natural Backdoor Defender for Pre-trained Language Models

papers (10)

RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback

ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback

Advancing LLM Reasoning Generalists with Preference Trees

Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations

TTRL: Test-Time Reinforcement Learning

A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks

RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness

Scaling Physical Reasoning with the PHYSICS Dataset

AIR: A Systematic Analysis of Annotations, Instructions, and Response Pairs in Preference Dataset

Moderate-fitting as a Natural Backdoor Defender for Pre-trained Language Models