collaborators

6 papers

cs.CL2025

Balancing Speciality and Versatility: A Coarse to Fine Framework for Mitigating Catastrophic Forgetting in Large Language Models

Hengyuan Zhang, Yanru Wu, Dawei Li +4

Aligned Large Language Models (LLMs) showcase remarkable versatility, capable of handling diverse real-world tasks. Meanwhile, aligned LLMs are also expected to exhibit speciality,…

cs.CL2024

Reward Difference Optimization For Sample Reweighting In Offline RLHF

Shiqi Wang, Zhengze Zhang, Rui Zhao +2

With the rapid advances in Large Language Models (LLMs), aligning LLMs with human preferences become increasingly important. Although Reinforcement Learning with Human Feedback (RL…

cs.CL2024

CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models

Jiawei Gu, Zacc Yang, Chuanghao Ding +2

Large Language Models (LLMs) excel in diverse tasks but often underperform in specialized fields due to limited domain-specific or proprietary corpus. Continual pre-training (CPT)…

cs.CV2024

SynthDoc: Bilingual Documents Synthesis for Visual Document Understanding

Chuanghao Ding, Xuejing Liu, Wei Tang +5

This paper introduces SynthDoc, a novel synthetic document generation pipeline designed to enhance Visual Document Understanding (VDU) by generating high-quality, diverse datasets…

cs.CL2024

SimCT: A Simple Consistency Test Protocol in LLMs Development Lifecycle

Fufangchen Zhao, Guoqiang Jin, Rui Zhao +2

In this work, we report our efforts to advance the standard operation procedure of developing Large Language Models (LLMs) or LLMs-based systems or services in industry. We introdu…

cs.CV2024

What Makes Good Few-shot Examples for Vision-Language Models?

Zhaojun Guo, Jinghui Lu, Xuejing Liu +3

Despite the notable advancements achieved by leveraging pre-trained vision-language (VL) models through few-shot tuning for downstream tasks, our detailed empirical study highlight…