Papers by Zhuowen Han
ERRV: Eliciting Efficient Reasoning through Reasoning Vectors for Policy Optimization in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing efforts to improve reasoning efficiency of large language models focus on modifying the reinforcement learning reward, such as adding length penalties. |
| Approach: | They propose a training framework that elicits efficient reasoning through reasoning vectors and a framework that allows the model to generate high-quality responses during reinforcement learning. |
| Outcome: | The proposed framework reduces reasoning length by 30% while maintaining stability, while retaining high accuracy. |
Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning (RL)-based post-training often improves the reasoning performance of large language models beyond the training domain, while supervised fine-tuning (SFT) frequently leads to general capabilities forgetting. |
| Approach: | They propose a feature-level mechanistic analysis methodology to probe RL generalization using a controlled experimental setup. |
| Outcome: | The proposed method identifies a compact, task-agnostic set of features that directly mediate generalization across diverse tasks. |
Neuronal Insights into LLM Attacks: Targeted Neuron Tuning for Precise and Robust Vulnerability Patching (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing gradient-based attribution methods are inapplicable to adversarial attacks . et al.: Targeted neuron tuning improves model robustness against jailbreak attacks despite the model's vulnerability to jailbreak. |
| Approach: | They propose a gradient-based method to identify key neurons sensitive to adversarial behaviors in open-ended generation tasks. |
| Outcome: | The proposed method detects key neurons sensitive to adversarial behaviors in open-ended tasks. |
Towards a Unified Paradigm of Concept Editing in Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Concept editing aims to control specific concepts in large language models (LLMs) however, there is a lack of rigorous theoretical analysis and a unified perspective to systematically understand and compare these methods. |
| Approach: | They propose a paradigm where conceptual injection is aligned at the neuron level. |
| Outcome: | The proposed paradigm offers a clear framework and valuable insights for advancing interpretability and controlled generation in large language models. |
Praetor: A Fine-Grained Generative LLM Evaluator with Instance-Level Customizable Evaluation Criteria (2025.acl-long)
Copied to clipboard
Yongqi Leng, Renren Jin, Yue Chen, Zhuowen Han, Ling Shi, Jianxiang Peng, Lei Yang, Juesi Xiao, Deyi Xiong
| Challenge: | Existing evaluation methods are inadequate to evaluate large language models (LLMs). |
| Approach: | They propose a fine-grained generative LLM evaluator with instance-level customazable evaluation criteria that can be used to evaluate large language models. |
| Outcome: | The proposed model outperforms existing LLM evaluators and instruction-tuned LLMs on multiple benchmarks and sets new SOTA results. |
From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan (2026.acl-long)
Copied to clipboard
Lei Yang, Leiyu Pan, Bojian Xiong, Renren Jin, Shaowei Zhang, Yue Chen, Ling Shi, Jiang Zhou, Junru Wu, Zhen Wang, Jianxiang Peng, Juesi Xiao, Tianyu Dong, Zhuowen Han, Zhuo Chen, Yuqi Ren, Deyi Xiong
| Challenge: | Large language models have achieved remarkable success across a wide range of tasks, yet their performance remains heavily biased toward high-resource languages. |
| Approach: | They propose a pipeline for advancing Tibetan language modeling through multilingual continual pre-training with Tibetan, Chinese, and English. |
| Outcome: | The proposed model outperforms open-source and Tibetan-focused models on diverse tasks. |
Revisiting Entropy in Reinforcement Learning for Large Reasoning Models (2026.findings-acl)
Copied to clipboard
Renren Jin, Pengzhi Gao, Yuqi Ren, Zhuowen Han, Tongxuan Zhang, Wuwei Huang, Wei Liu, Jian Luan, Deyi Xiong
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) has emerged as a paradigm for enhancing the reasoning capabilities of large language models. |
| Approach: | They propose a positive-advantage reweighting approach that regulates model entropy by adjusting the loss weights assigned to tokens with positive advantages during RLVR training. |
| Outcome: | The proposed approach regulates model entropy by adjusting loss weights assigned to tokens with positive advantages during RLVR training while maintaining competitive performance. |