Zobrazeno 1 - 10
of 2 779
pro vyhledávání: '"Yu, Jane"'
Autor:
Prasad, Archiki, Yuan, Weizhe, Pang, Richard Yuanzhe, Xu, Jing, Fazel-Zarandi, Maryam, Bansal, Mohit, Sukhbaatar, Sainbayar, Weston, Jason, Yu, Jane
Self-alignment, whereby models learn to improve themselves without human annotation, is a rapidly growing research area. However, existing techniques often fail to improve complex reasoning tasks due to the difficulty of assigning correct rewards. An
Externí odkaz:
http://arxiv.org/abs/2411.04109
The rapid development and deployment of Generative AI in social settings raise important questions about how to optimally personalize them for users while maintaining accuracy and realism. Based on a Facebook public post-comment dataset, this study e
Externí odkaz:
http://arxiv.org/abs/2410.01708
Autor:
Lupidi, Alisia, Gemmell, Carlos, Cancedda, Nicola, Dwivedi-Yu, Jane, Weston, Jason, Foerster, Jakob, Raileanu, Roberta, Lomeli, Maria
Large Language Models still struggle in challenging scenarios that leverage structured data, complex reasoning, or tool usage. In this paper, we propose Source2Synth: a new method that can be used for teaching LLMs new skills without relying on costl
Externí odkaz:
http://arxiv.org/abs/2409.08239
Autor:
Wang, Tianlu, Kulikov, Ilia, Golovneva, Olga, Yu, Ping, Yuan, Weizhe, Dwivedi-Yu, Jane, Pang, Richard Yuanzhe, Fazel-Zarandi, Maryam, Weston, Jason, Li, Xian
Model-based evaluation is at the heart of successful model development -- as a reward model for training, and as a replacement for human evaluation. To train such evaluators, the standard approach is to collect a large amount of human preference judg
Externí odkaz:
http://arxiv.org/abs/2408.02666
Information Retrieval (IR) systems are designed to deliver relevant content, but traditional systems may not optimize rankings for fairness, neutrality, or the balance of ideas. Consequently, IR can often introduce indexical biases, or biases in the
Externí odkaz:
http://arxiv.org/abs/2406.04298
The accurate evaluation of differential treatment in language models to specific groups is critical to ensuring a positive and safe user experience. An ideal evaluation should have the properties of being robust, extendable to new groups or attribute
Externí odkaz:
http://arxiv.org/abs/2404.06619
Autor:
Havrilla, Alex, Du, Yuqing, Raparthy, Sharath Chandra, Nalmpantis, Christoforos, Dwivedi-Yu, Jane, Zhuravinskyi, Maksym, Hambro, Eric, Sukhbaatar, Sainbayar, Raileanu, Roberta
Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from feedback (
Externí odkaz:
http://arxiv.org/abs/2403.04642
Dense retrievers compress source documents into (possibly lossy) vector representations, yet there is little analysis of what information is lost versus preserved, and how it affects downstream tasks. We conduct the first analysis of the information
Externí odkaz:
http://arxiv.org/abs/2402.15925
Autor:
Mekala, Dheeraj, Weston, Jason, Lanchantin, Jack, Raileanu, Roberta, Lomeli, Maria, Shang, Jingbo, Dwivedi-Yu, Jane
Teaching language models to use tools is an important milestone towards building general assistants, but remains an open problem. While there has been significant progress on learning to use specific tools via fine-tuning, language models still strug
Externí odkaz:
http://arxiv.org/abs/2402.14158
Autor:
Havrilla, Alex, Raparthy, Sharath, Nalmpantis, Christoforus, Dwivedi-Yu, Jane, Zhuravinskyi, Maksym, Hambro, Eric, Raileanu, Roberta
State-of-the-art language models can exhibit impressive reasoning refinement capabilities on math, science or coding tasks. However, recent work demonstrates that even the best models struggle to identify \textit{when and where to refine} without acc
Externí odkaz:
http://arxiv.org/abs/2402.10963