34 citations · 34 across the 10 of their papers we have counts for
11 papers
On the Geometry of On-Policy Distillation
Zhennan Shen, Yanshu Li, Qingyu Yin +6
On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood. We characterize the trajectory of O…
Finding RELIEF: Shaping Reasoning Behavior without Reasoning Supervision via Belief Engineering
Chak Tou Leong, Dingwei Chen, Heming Xia +4
Large reasoning models (LRMs) have achieved remarkable success in complex problem-solving, yet they often suffer from computational redundancy or reasoning unfaithfulness. Current…
Evaluating Parameter Efficient Methods for RLVR
Qingyu Yin, Yulun Wu, Zhennan Shen +6
We systematically evaluate Parameter-Efficient Fine-Tuning (PEFT) methods under the paradigm of Reinforcement Learning with Verifiable Rewards (RLVR). RLVR incentivizes language mo…
Probing the Difficulty Perception Mechanism of Large Language Models
Sunbowen Lee, Qingyu Yin, Chak Tou Leong +5
Large language models (LLMs) are increasingly deployed on complex reasoning tasks, yet little is known about their ability to internally evaluate problem difficulty, which is an es…
Induction Head Toxicity Mechanistically Explains Repetition Curse in Large Language Models
Shuxun Wang, Qingyu Yin, Chak Tou Leong +2
Repetition curse is a phenomenon where Large Language Models (LLMs) generate repetitive sequences of tokens or cyclic sequences. While the repetition curse has been widely observed…
Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region
Chak Tou Leong, Qingyu Yin, Jian Wang +1
The safety alignment of large language models (LLMs) remains vulnerable, as their initial behavior can be easily jailbroken by even relatively simple attacks. Since infilling a fix…
Constrain Alignment with Sparse Autoencoders
Qingyu Yin, Chak Tou Leong, Minjun Zhu +7
The alignment of large language models (LLMs) with human preferences remains a key challenge. While post-training techniques like Reinforcement Learning from Human Feedback (RLHF)…
Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning
Qingyu Yin, Xuzheng He, Luoao Deng +5
Fine-tuning and in-context learning (ICL) are two prevalent methods in imbuing large language models with task-specific knowledge. It is commonly believed that fine-tuning can surp…
A Multilingual Dataset and Empirical Validation for the Mutual Reinforcement Effect in Information Extraction
Chengguang Gan, Sunbowen Lee, Qingyu Yin +9
The Mutual Reinforcement Effect (MRE) describes a phenomenon in information extraction where word-level and sentence-level tasks can mutually improve each other when jointly modele…
StableMask: Refining Causal Masking in Decoder-only Transformer
Qingyu Yin, Xuzheng He, Xiang Zhuang +4
The decoder-only Transformer architecture with causal masking and relative position encoding (RPE) has become the de facto choice in language modeling. Despite its exceptional perf…
Scientific Large Language Models: A Survey on Biological & Chemical Domains
Qiang Zhang, Keyang Ding, Tianwen Lyv +22
Large Language Models (LLMs) have emerged as a transformative power in enhancing natural language comprehension, representing a significant stride toward artificial general intelli…