I Modelli Linguistici sono Ragionatori Nascosti: Sbloccare le Capacità di Ragionamento Latente tramite l'Auto-Ricompensa
Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding
November 6, 2024
Autori: Haolin Chen, Yihao Feng, Zuxin Liu, Weiran Yao, Akshara Prabhakar, Shelby Heinecke, Ricky Ho, Phil Mui, Silvio Savarese, Caiming Xiong, Huan Wang
cs.AI
Abstract
I grandi modelli linguistici (LLM) hanno dimostrato capacità impressionanti, ma faticano ancora con compiti di ragionamento complessi che richiedono più passaggi. Mentre i metodi basati su prompt come Chain-of-Thought (CoT) possono migliorare il ragionamento dei LLM durante l'inferenza, ottimizzare le capacità di ragionamento durante l'addestramento rimane una sfida. Presentiamo LaTent Reasoning Optimization (LaTRO), un framework basato su principi che formula il ragionamento come campionamento da una distribuzione latente e lo ottimizza tramite approcci variazionali. LaTRO consente ai LLM di migliorare contemporaneamente sia il loro processo di ragionamento che la capacità di valutare la qualità del ragionamento, senza richiedere feedback esterni o modelli di ricompensa. Convalidiamo LaTRO attraverso esperimenti sui set di dati GSM8K e ARC-Challenge utilizzando diverse architetture di modelli. Su GSM8K, LaTRO migliora l'accuratezza a zero-shot di una media del 12,5% rispetto ai modelli di base e del 9,6% rispetto al fine-tuning supervisionato attraverso Phi-3.5-mini, Mistral-7B e Llama-3.1-8B. I nostri risultati suggeriscono che i LLM preaddestrati possiedono capacità di ragionamento latenti che possono essere sbloccate e potenziate attraverso il nostro approccio di ottimizzazione proposto in modo di auto-miglioramento. Il codice di LaTRO è disponibile su https://github.com/SalesforceAIResearch/LaTRO.
English
Large language models (LLMs) have shown impressive capabilities, but still
struggle with complex reasoning tasks requiring multiple steps. While
prompt-based methods like Chain-of-Thought (CoT) can improve LLM reasoning at
inference time, optimizing reasoning capabilities during training remains
challenging. We introduce LaTent Reasoning Optimization (LaTRO), a principled
framework that formulates reasoning as sampling from a latent distribution and
optimizes it via variational approaches. LaTRO enables LLMs to concurrently
improve both their reasoning process and ability to evaluate reasoning quality,
without requiring external feedback or reward models. We validate LaTRO through
experiments on GSM8K and ARC-Challenge datasets using multiple model
architectures. On GSM8K, LaTRO improves zero-shot accuracy by an average of
12.5% over base models and 9.6% over supervised fine-tuning across
Phi-3.5-mini, Mistral-7B, and Llama-3.1-8B. Our findings suggest that
pre-trained LLMs possess latent reasoning capabilities that can be unlocked and
enhanced through our proposed optimization approach in a self-improvement
manner. The code of LaTRO is available at
https://github.com/SalesforceAIResearch/LaTRO.Summary
AI-Generated Summary
DeepSeek-R1: Incentivizzare la capacità di ragionamento nei LLM tramite Apprendimento per RinforzoDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via
Reinforcement Learning
DeepSeek-R1: Incentivizzare la capacità di ragionamento nei LLM tramite Apprendimento per Rinforzo
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via
Reinforcement Learning
DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, Aixin Liu, Bing Xue, Bingxuan Wang, Bochao Wu, Bei Feng, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Qu, Hui Li, Jianzhong Guo, Jiashi Li, Jiawei Wang, Jingchang Chen, Jingyang Yuan, Junjie Qiu, Junlong Li, J. L. Cai, Jiaqi Ni, Jian Liang, Jin Chen, Kai Dong, Kai Hu, Kaige Gao, Kang Guan, Kexin Huang, Kuai Yu, Lean Wang, Lecong Zhang, Liang Zhao, Litong Wang, Liyue Zhang, Lei Xu, Leyi Xia, Mingchuan Zhang, Minghua Zhang, Minghui Tang, Meng Li, Miaojun Wang, Mingming Li, Ning Tian, Panpan Huang, Peng Zhang, Qiancheng Wang, Qinyu Chen, Qiushi Du, Ruiqi Ge, Ruisong Zhang, Ruizhe Pan, Runji Wang, R. J. Chen, R. L. Jin, Ruyi Chen, Shanghao Lu, Shangyan Zhou, Shanhuang Chen, Shengfeng Ye, Shiyu Wang, Shuiping Yu, Shunfeng Zhou, Shuting Pan, S. S. Li, Shuang Zhou, Shaoqing Wu, Shengfeng Ye, Tao Yun, Tian Pei, Tianyu Sun, T. Wang, Wangding Zeng, Wanjia Zhao, Wen Liu, Wenfeng Liang, Wenjun Gao, Wenqin Yu, Wentao Zhang, W. L. Xiao, Wei An, Xiaodong Liu, Xiaohan Wang, Xiaokang Chen, Xiaotao Nie, Xin Cheng, Xin Liu, Xin Xie, Xingchao Liu, Xinyu Yang, Xinyuan Li, Xuecheng Su, Xuheng Lin, X. Q. Li, Xiangyue Jin, Xiaojin Shen, Xiaosha Chen, Xiaowen Sun, Xiaoxiang Wang, Xinnan Song, Xinyi Zhou, Xianzu Wang, Xinxia Shan, Y. K. Li, Y. Q. Wang, Y. X. Wei, Yang Zhang, Yanhong Xu, Yao Li, Yao Zhao, Yaofeng Sun, Yaohui Wang, Yi Yu, Yichao Zhang, Yifan Shi, Yiliang Xiong, Ying He, Yishi Piao, Yisong Wang, Yixuan Tan, Yiyang Ma, Yiyuan Liu, Yongqiang Guo, Yuan Ou, Yuduan Wang, Yue Gong, Yuheng Zou, Yujia He, Yunfan Xiong, Yuxiang Luo, Yuxiang You, Yuxuan Liu, Yuyang Zhou, Y. X. Zhu, Yanhong Xu, Yanping Huang, Yaohui Li, Yi Zheng, Yuchen Zhu, Yunxian Ma, Ying Tang, Yukun Zha, Yuting Yan, Z. Z. Ren, Zehui Ren, Zhangli Sha, Zhe Fu, Zhean Xu, Zhenda Xie, Zhengyan Zhang, Zhewen Hao, Zhicheng Ma, Zhigang Yan, Zhiyu Wu, Zihui Gu, Zijia Zhu, Zijun Liu, Zilin Li, Ziwei Xie, Ziyang Song, Zizheng Pan, Zhen Huang, Zhipeng Xu, Zhongyu Zhang, Zhen Zhang•Jan 22, 2025•3745
Rapporto Tecnico Qwen2.5Qwen2.5 Technical Report
Rapporto Tecnico Qwen2.5
Qwen2.5 Technical Report
Qwen, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, Kai Dang, Keming Lu, Keqin Bao, Kexin Yang, Le Yu, Mei Li, Mingfeng Xue, Pei Zhang, Qin Zhu, Rui Men, Runji Lin, Tianhao Li, Tingyu Xia, Xingzhang Ren, Xuancheng Ren, Yang Fan, Yang Su, Yichang Zhang, Yu Wan, Yuqiong Liu, Zeyu Cui, Zhenru Zhang, Zihan Qiu•Dec 19, 2024•36411
MiniMax-01: Scalare i modelli di base con attenzione lampeggianteMiniMax-01: Scaling Foundation Models with Lightning Attention
MiniMax-01: Scalare i modelli di base con attenzione lampeggiante
MiniMax-01: Scaling Foundation Models with Lightning Attention
MiniMax, Aonian Li, Bangwei Gong, Bo Yang, Boji Shan, Chang Liu, Cheng Zhu, Chunhao Zhang, Congchao Guo, Da Chen, Dong Li, Enwei Jiao, Gengxin Li, Guojun Zhang, Haohai Sun, Houze Dong, Jiadai Zhu, Jiaqi Zhuang, Jiayuan Song, Jin Zhu, Jingtao Han, Jingyang Li, Junbin Xie, Junhao Xu, Junjie Yan, Kaishun Zhang, Kecheng Xiao, Kexi Kang, Le Han, Leyang Wang, Lianfei Yu, Liheng Feng, Lin Zheng, Linbo Chai, Long Xing, Meizhi Ju, Mingyuan Chi, Mozhi Zhang, Peikai Huang, Pengcheng Niu, Pengfei Li, Pengyu Zhao, Qi Yang, Qidi Xu, Qiexiang Wang, Qin Wang, Qiuhui Li, Ruitao Leng, Shengmin Shi, Shuqi Yu, Sichen Li, Songquan Zhu, Tao Huang, Tianrun Liang, Weigao Sun, Weixuan Sun, Weiyu Cheng, Wenkai Li, Xiangjun Song, Xiao Su, Xiaodong Han, Xinjie Zhang, Xinzhu Hou, Xu Min, Xun Zou, Xuyang Shen, Yan Gong, Yingjie Zhu, Yipeng Zhou, Yiran Zhong, Yongyi Hu, Yuanxiang Fan, Yue Yu, Yufeng Yang, Yuhao Li, Yunan Huang, Yunji Li, Yunpeng Huang, Yunzhi Xu, Yuxin Mao, Zehan Li, Zekang Li, Zewei Tao, Zewen Ying, Zhaoyang Cong, Zhen Qin, Zhenhua Fan, Zhihang Yu, Zhuo Jiang, Zijia Wu•Jan 14, 2025•2846