7 papers
A Systematic Analysis of Hybrid Linear Attention
Dustin Wang, Rui-Jie Zhu, Steven Abreu +9
Transformers face quadratic complexity and memory issues with long sequences, prompting the adoption of linear attention mechanisms using fixed-size hidden states. However, linear…
TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection
Bohan Yang, Yijun Gong, Zhi Zhang +3
When a language model hallucinates, the final answer is wrong, but the mistake is not necessarily invisible inside the model. Different internal pathways may remain uncertain, disa…
Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO
Zhiyuan Zeng, Jiameng Huang, Zhangyue Yin +8
Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation in large language models, and GRPO-style training is…
In-Place Test-Time Training
Guhao Feng, Shengjie Luo, Kai Hua +4
The static ``train then deploy" paradigm fundamentally limits Large Language Models (LLMs) from dynamically adapting their weights in response to continuous streams of new informat…
Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining
Zhiyuan Zeng, Yichi Zhang, Yong Shan +11
While Large Language Models (LLMs) have achieved remarkable success in code generation, they often struggle with the deep, long-horizon reasoning required for complex software engi…
The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning
Qiguang Chen, Yantao Du, Ziniu Li +10
Large language models (LLMs) often fail to learn effective long chain-of-thought (Long CoT) reasoning from human or non-Long-CoT LLMs imitation. To understand this, we propose that…