Jiasheng Zheng

Knowledge Mechanisms Across the Lifecycle of Large Language Models

hao xiang, Xiusheng Huang, Shangqing Tu, Jiasheng Zheng et autres

Large language models (LLMs) have reshaped artificial intelligence. They now achieve strong performance across question answering, commonsense reasoning, code generation, and mathematical problem solving. These striking capabilities ultimately rest on the knowledge a model acquires during training. The internal processes by which …

ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models

Jun Zhang, Jiasheng Zheng, Boxi Cao, Ye Lu et autres

The emergence of Large Reasoning Models has introduced exceptionally long Chain-of-Thought traces, creating a transparency burden where critical logic is often buried under massive procedural text. To address this, we present ReasoningLens, an open-source framework designed for the hierarchical visualization and diagnostic …

cn (code pays fourni par la source)

ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models

Association for Computational Linguistics 2026, Boxi Cao, Xianpei Han, Jiazhen Jiang et autres

Code sandboxes have emerged as a critical infrastructure for advancing the coding capabilities of large language models, providing verifiable feedback for both RL training and evaluation. However, existing systems fail to provide accurate verification and efficiency under high-concurrency workloads. We present ScaleBox, …

cn (code pays fourni par la source)

Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination

Jiasheng Zheng, Boxi Cao, Boxi Yu, Yuzhong Zhang et autres

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as the cornerstone for shaping the remarkable coding abilities of Large Language Models (LLMs). However, the scalability of RLVR is severely constrained by the scarcity of sufficiently challenging verifiable code tasks that target …

Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination

Jiasheng Zheng, Boxi Cao, Boxi Yu, Yuzhong Zhang et autres

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as the cornerstone for shaping the remarkable coding abilities of Large Language Models (LLMs). However, the scalability of RLVR is severely constrained by the scarcity of sufficiently challenging verifiable code tasks that target …

cn, ie, hk (code pays fourni par la source)

ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models

Jiasheng Zheng, Xin Zheng, Boxi Cao, Pengbo Wang et autres

Code sandboxes have emerged as a critical infrastructure for advancing the coding capabilities of large language models, providing verifiable feedback for both RL training and evaluation. However, existing systems fail to provide accurate verification and efficiency under high-concurrency workloads. We present ScaleBox, …

ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models

Jiasheng Zheng, Xin Zheng, Boxi Cao, Pengbo Wang et autres

Code sandboxes have emerged as a critical infrastructure for advancing the coding capabilities of large language models, providing verifiable feedback for both RL training and evaluation. However, existing systems fail to provide accurate verification and efficiency under high-concurrency workloads. We present ScaleBox, …

cn (code pays fourni par la source)

ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models

Jiasheng Zheng, Xin Zheng, Boxi Cao, Pengbo Wang et autres

Jiasheng Zheng, Xin Zheng, Boxi Cao, Pengbo Wang, Zhengzhao Ma, Qiming Zhu, Jiazhen Jiang, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). 2026.

cn (code pays fourni par la source)

Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models

Jiasheng Zheng, Boxi Cao, Zhengzhao Ma, Ruotong Pan et autres

In recent years, researchers have proposed numerous benchmarks to evaluate the impressive coding capabilities of large language models (LLMs). However, current benchmarks primarily assess the accuracy of LLM-generated code, while neglecting other critical dimensions that also significantly impact code quality in real-world …