activity
20242026
collaborators

8 papers

cs.CL2026

Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models

Zhaoyi Li, Jiatong Li, Gangwei Jiang +3

Chain-of-thought (CoT) reasoning has become the standard paradigm for enabling Large Language Models (LLMs) to solve complex problems. However, recent studies reveal a sharp perfor…

cs.CL2026

On the Role of Reasoning Patterns in the Generalization Discrepancy of Long Chain-of-Thought Supervised Fine-Tuning

Zhaoyi Li, Xiangyu Xi, Zhengyu Chen +6

Supervised Fine-Tuning (SFT) on long Chain-of-Thought (CoT) trajectories has become a pivotal phase in building large reasoning models. However, how CoT trajectories from different…

cs.AI2025

What Makes a Good Reasoning Chain? Uncovering Structural Patterns in Long Chain-of-Thought Reasoning

Gangwei Jiang, Yahui Liu, Zhaoyi Li +5

Recent advances in reasoning with large language models (LLMs) have popularized Long Chain-of-Thought (LCoT), a strategy that encourages deliberate and step-by-step reasoning befor…

cs.LG2025

Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning

Gangwei Jiang, Caigao Jiang, Zhaoyi Li +5

Catastrophic forgetting (CF) poses a significant challenge in machine learning, where a model forgets previously learned information upon learning new tasks. Despite the advanced c…

cs.CL2024

DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs

Haokun Lin, Haobo Xu, Yichen Wu +6

Quantization of large language models (LLMs) faces significant challenges, particularly due to the presence of outlier activations that impede efficient low-bit representation. Tra…

cs.CL2024

Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing

Weichuan Wang, Zhaoyi Li, Defu Lian +3

Large Language Models (LLMs) have recently revolutionized the NLP field, while they still fall short in some specific down-stream tasks. In the work, we focus on utilizing LLMs to…