Zobrazeno 1 - 10
of 137
pro vyhledávání: '"Song, Linfeng"'
There is a growing trend of teaching large language models (LLMs) to solve mathematical problems through coding. Existing studies primarily focus on prompting powerful, closed-source models to generate seed training data followed by in-domain data au
Externí odkaz:
http://arxiv.org/abs/2408.15565
Autor:
Zhang, Yuheng, Yu, Dian, Peng, Baolin, Song, Linfeng, Tian, Ye, Huo, Mingyue, Jiang, Nan, Mi, Haitao, Yu, Dong
Reinforcement Learning with Human Feedback (RLHF) has achieved great success in aligning large language models (LLMs) with human preferences. Prevalent RLHF approaches are reward-based, following the Bradley-Terry (BT) model assumption, which may not
Externí odkaz:
http://arxiv.org/abs/2407.00617
Autor:
Wang, Ante, Song, Linfeng, Tian, Ye, Peng, Baolin, Yu, Dian, Mi, Haitao, Su, Jinsong, Yu, Dong
Recent research suggests that tree search algorithms (e.g. Monte Carlo Tree Search) can dramatically boost LLM performance on complex mathematical reasoning tasks. However, they often require more than 10 times the computational resources of greedy d
Externí odkaz:
http://arxiv.org/abs/2407.00320
Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they still struggle with scenarios that involves complex reasoning and planning. Recent work proposed advanced prompting techniques and the necessity of fine-tuning
Externí odkaz:
http://arxiv.org/abs/2404.12253
Large language models (LLMs) exhibit impressive natural language capabilities but suffer from hallucination -- generating content ungrounded in the realities of training data. Recent work has focused on decoding techniques to improve factuality durin
Externí odkaz:
http://arxiv.org/abs/2404.09338
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 7, Pp 19-31 (2019)
It is intuitive that semantic representations can be useful for machine translation, mainly because they can help in enforcing meaning preservation and handling data sparsity (many sentences correspond to one meaning) of machine translation models. O
Externí odkaz:
https://doaj.org/article/86d54844cecd4a84ace6a747a8e54b02
Autor:
Wang, Ante, Song, Linfeng, Tian, Ye, Peng, Baolin, Jin, Lifeng, Mi, Haitao, Su, Jinsong, Yu, Dong
Calibration, which establishes the correlation between accuracy and model confidence, is important for LLM development. We design three off-the-shelf calibration methods based on self-consistency (Wang et al., 2022) for math reasoning tasks. Evaluati
Externí odkaz:
http://arxiv.org/abs/2403.09849
Knowledge-based, open-domain dialogue generation aims to build chit-chat systems that talk to humans using mined support knowledge. Many types and sources of knowledge have previously been shown to be useful as support knowledge. Even in the era of l
Externí odkaz:
http://arxiv.org/abs/2403.03496
Autor:
Huang, Jianheng, Cui, Leyang, Wang, Ante, Yang, Chengyi, Liao, Xinting, Song, Linfeng, Yao, Junfeng, Su, Jinsong
Large language models (LLMs) suffer from catastrophic forgetting during continual learning. Conventional rehearsal-based methods rely on previous training data to retain the model's ability, which may not be feasible in real-world applications. When
Externí odkaz:
http://arxiv.org/abs/2403.01244
The most common training pipeline for large language models includes pretraining, finetuning and aligning phases, with their respective resulting models, such as the pretrained model and the finetuned model. Finetuned and aligned models show improved
Externí odkaz:
http://arxiv.org/abs/2402.17982