7 papers
IntelliAsk: Learning to Ask High-Quality Research Questions via RLVR
Karun Sharma, Vidushee Vats, Shengzhi Li +3
Peer review relies on substantive, evidence-based questions, yet current LLMs generate surface-level queries that perform worse than human reviewer questions in expert evaluation.…
Efficient Inference for Noisy LLM-as-a-Judge Evaluation
Yiqun T Chen, Sizhu Lu, Sijia Li +2
Large language models (LLMs) are increasingly used as automatic evaluators of generative AI outputs, a paradigm often referred to as "LLM-as-a-judge." In practice, LLM judges are i…
Intention Chain-of-Thought Prompting with Dynamic Routing for Code Generation
Shen Li, Li Huang, Shaoxiong Zhan +4
Large language models (LLMs) exhibit strong generative capabilities and have shown great potential in code generation. Existing chain-of-thought (CoT) prompting methods enhance mod…
Co-EPG: A Framework for Co-Evolution of Planning and Grounding in Autonomous GUI Agents
Yuan Zhao, Hualei Zhu, Tingyu Jiang +3
Graphical User Interface (GUI) task automation constitutes a critical frontier in artificial intelligence research. While effective GUI agents synergistically integrate planning an…
Importance-Aware Data Selection for Efficient LLM Instruction Tuning
Tingyu Jiang, Shen Li, Yiyao Song +6
Instruction tuning plays a critical role in enhancing the performance and efficiency of Large Language Models (LLMs). Its success depends not only on the quality of the instruction…
Activating Visual Context and Commonsense Reasoning through Masked Prediction in VLMs
Jiaao Yu, Shenwei Li, Mingjie Han +4
Recent breakthroughs in reasoning models have markedly advanced the reasoning capabilities of large language models, particularly via training on tasks with verifiable rewards. Yet…