Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

no code implementations • 18 Sep 2024 • An Yang, Beichen Zhang, Binyuan Hui, Bofei Gao, Bowen Yu, Chengpeng Li, Dayiheng Liu, Jianhong Tu, Jingren Zhou, Junyang Lin, Keming Lu, Mingfeng Xue, Runji Lin, Tianyu Liu, Xingzhang Ren, Zhenru Zhang

This RM is then applied to the iterative evolution of data in supervised fine-tuning (SFT).

GSM8K Math +2

Towards a Unified View of Preference Learning for Large Language Models: A Survey

1 code implementation • 4 Sep 2024 • Bofei Gao, Feifan Song, Yibo Miao, Zefan Cai, Zhe Yang, Liang Chen, Helan Hu, Runxin Xu, Qingxiu Dong, Ce Zheng, Wen Xiao, Ge Zhang, Daoguang Zan, Keming Lu, Bowen Yu, Dayiheng Liu, Zeyu Cui, Jian Yang, Lei Sha, Houfeng Wang, Zhifang Sui, Peiyi Wang, Tianyu Liu, Baobao Chang

Finally, based on our unified perspective, we explore the challenges and future research directions for aligning large language models with human preferences.

LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback

1 code implementation • 20 Jun 2024 • Bofei Gao, Zefan Cai, Runxin Xu, Peiyi Wang, Ce Zheng, Runji Lin, Keming Lu, Dayiheng Liu, Chang Zhou, Wen Xiao, Junjie Hu, Tianyu Liu, Baobao Chang

To mitigate the aforementioned insufficiency of binary labels, we introduce step-wise natural language feedbacks as rationale labels (i. e., the correctness of the current step and the explanations).

Binary Classification GSM8K +2

PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

1 code implementation • 4 Jun 2024 • Zefan Cai, Yichi Zhang, Bofei Gao, Yuliang Liu, Tianyu Liu, Keming Lu, Wayne Xiong, Yue Dong, Baobao Chang, Junjie Hu, Wen Xiao

Our experimental evaluations, utilizing the LongBench benchmark, show that PyramidKV matches the performance of models with a full KV cache while retaining only 12% of the KV cache, thus significantly reducing memory usage.

Coarse-to-Fine Dual Encoders are Better Frame Identification Learners

1 code implementation • 20 Oct 2023 • Kaikai An, Ce Zheng, Bofei Gao, Haozhe Zhao, Baobao Chang

Recent researches measure the similarity or matching score between targets and candidate frames by modeling frame definitions.

Contrastive Learning Representation Learning +1

Guiding AMR Parsing with Reverse Graph Linearization

1 code implementation • 13 Oct 2023 • Bofei Gao, Liang Chen, Peiyi Wang, Zhifang Sui, Baobao Chang

Abstract Meaning Representation (AMR) parsing aims to extract an abstract semantic graph from a given sentence.

Abstract Meaning Representation AMR Parsing +1

A Two-Stage Method for Chinese AMR Parsing

1 code implementation • 29 Sep 2022 • Liang Chen, Bofei Gao, Baobao Chang

In this paper, we provide a detailed description of our system at CAMRP-2022 evaluation.

AMR Parsing Vocal Bursts Valence Prediction