9 citations · 10 across the 11 of their papers we have counts for
12 papers
Beyond Distribution Matching: Selective Margin Preservation for Supervised Fine-Tuning
Yuxuan Wang, Guangxiang Zhao, Xinyu Tan +6
Supervised fine-tuning (SFT) changes logit margins among non-target tokens at teacher-forced prefixes. Matching a local reference distribution keeps those probabilities and also pe…
VEPO: Variable Entropy Policy Optimization for Low-Resource Language Foundation Models
Chonghan Liu, Yimin Du, Qi An +8
Large language models frequently exhibit suboptimal performance on low resource languages, primarily due to inefficient subword segmentation and systemic training data imbalances.…
Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following
Chenyang Wang, Liang Wen, Shousheng Jia +2
While advancements in the reasoning abilities of LLMs have significantly enhanced their performance in solving mathematical problems, coding tasks, and general puzzles, their effec…
Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training
Jianfeng Si, Lin Sun, Zhewen Tan +1
Current methods for content safety in Large Language Models (LLMs), such as Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), often rely on multi-…
Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design
Lin Sun, Weihong Lin, Jinzhu Wu +8
Reasoning models represented by the Deepseek-R1-Distill series have been widely adopted by the open-source community due to their strong performance in mathematics, science, progra…
360-LLaMA-Factory: Plug & Play Sequence Parallelism for Long Post-Training
Haosheng Zou, Xiaowei Lv, Shousheng Jia +3
Adding sequence parallelism into LLaMA-Factory, we open-sourced 360-LLaMA-Factory at https://github.com/Qihoo360/360-LLaMA-Factory. 360-LLaMA-Factory has received wide recognition…
Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models
Zonghao Ying, Deyue Zhang, Zonglei Jing +7
Multi-turn jailbreak attacks simulate real-world human interactions by engaging large language models (LLMs) in iterative dialogues, exposing critical safety vulnerabilities. Howev…
Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
Liang Wen, Yunke Cai, Fenrui Xiao +11
This paper introduces Light-R1, an open-source suite for training long reasoning models using reproducible and cost-effective methodology. Given the proprietary nature of data used…
TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation
Lin Sun, Guangxiang Zhao, Xiaoqi Jian +18
The challenge of reducing the size of Large Language Models (LLMs) while maintaining their performance has gained significant attention. However, existing methods, such as model di…
Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision
Dawei Zhu, Xiyu Wei, Guangxiang Zhao +7
Recent advances in Large Language Models (LLMs) have highlighted the challenge of handling long-context tasks, where models need to reason over extensive input contexts to aggregat…
Large Language Models Badly Generalize across Option Length, Problem Types, and Irrelevant Noun Replacements
Guangxiang Zhao, Saier Hu, Xiaoqi Jian +5
In this paper, we propose a ``Generalization Stress Test" to assess Large Language Models' (LLMs) generalization ability under slight and controlled perturbations, including option…
CCMB: A Large-scale Chinese Cross-modal Benchmark
Chunyu Xie, Heng Cai, Jincheng Li +11
Vision-language pre-training (VLP) on large-scale datasets has shown premier performance on various downstream tasks. In contrast to plenty of available benchmarks with English cor…