Congmin Zheng
YOU?
Author Swipe
View article: A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models
A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models Open
Although Large Language Models (LLMs) exhibit advanced reasoning ability, conventional alignment remains largely dominated by outcome reward models (ORMs) that judge only final answers. Process Reward Models(PRMs) address this gap by evalu…
View article: Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey
Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey Open
The advent of large language models (LLMs), such as GPT, Gemini, and DeepSeek, has significantly advanced natural language processing, giving rise to sophisticated chatbots capable of diverse language-related tasks. The transition from the…
View article: Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning
Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning Open
While large language models (LLMs) have significantly advanced mathematical reasoning, Process Reward Models (PRMs) have been developed to evaluate the logical validity of reasoning steps. However, PRMs still struggle with out-of-distribut…
View article: The mediating effect of work engagement on the relationship between competency and work well-being of community nurses in common chronic diseases management
The mediating effect of work engagement on the relationship between competency and work well-being of community nurses in common chronic diseases management Open
Objective To investigate the status quo of competency and work well-being of community nurses in common chronic diseases management, and to explore the mediating effect of work engagement between them. Methods From December 2023 to May 202…
View article: Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning
Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning Open
View article: [Treatment status of tyrosine kinase inhibitor for newly-diagnosed chronic myeloid leukemia: a domestic multi-centre retrospective real-world study].
[Treatment status of tyrosine kinase inhibitor for newly-diagnosed chronic myeloid leukemia: a domestic multi-centre retrospective real-world study]. Open
Objective: To retrospectively analyze the treatment status of tyrosine kinase inhibitors (TKI) in newly diagnosed patients with chronic myeloid leukemia (CML) in China. Methods: Data of chronic phase (CP) and accelerated phas…
View article: [To compare the efficacy and incidence of severe hematological adverse events of flumatinib and imatinib in patients newly diagnosed with chronic phase chronic myeloid leukemia].
[To compare the efficacy and incidence of severe hematological adverse events of flumatinib and imatinib in patients newly diagnosed with chronic phase chronic myeloid leukemia]. Open
Objective: To analyze and compare therapy responses, outcomes, and incidence of severe hematologic adverse events of flumatinib and imatinib in patients newly diagnosed with chronic phase chronic myeloid leukemia (CML) . Methods:…