Zobrazeno 1 - 10
of 60
pro vyhledávání: '"Astudillo, Ramon"'
Autor:
Lee, Young-Suk, Gunasekara, Chulaka, Contractor, Danish, Astudillo, Ramón Fernandez, Florian, Radu
We introduce a technique for multi-document grounded multi-turn synthetic dialog generation that incorporates three main ideas. First, we control the overall dialog flow using taxonomy-driven user queries that are generated with Chain-of-Thought (CoT
Externí odkaz:
http://arxiv.org/abs/2409.11500
Autor:
Don-Yehiya, Shachar, Burtenshaw, Ben, Astudillo, Ramon Fernandez, Osborne, Cailean, Jaiswal, Mimansa, Kuo, Tzu-Sheng, Zhao, Wenting, Shenfeld, Idan, Peng, Andi, Yurochkin, Mikhail, Kasirzadeh, Atoosa, Huang, Yangsibo, Hashimoto, Tatsunori, Jernite, Yacine, Vila-Suero, Daniel, Abend, Omri, Ding, Jennifer, Hooker, Sara, Kirk, Hannah Rose, Choshen, Leshem
Human feedback on conversations with language language models (LLMs) is central to how these systems learn about the world, improve their capabilities, and are steered toward desirable and safe behaviors. However, this feedback is mostly collected by
Externí odkaz:
http://arxiv.org/abs/2408.16961
Autor:
Ramji, Keshav, Lee, Young-Suk, Astudillo, Ramón Fernandez, Sultan, Md Arafat, Naseem, Tahira, Munawar, Asim, Florian, Radu, Roukos, Salim
It is often desirable for Large Language Models (LLMs) to capture multiple objectives when providing a response. In document-grounded response generation, for example, agent responses are expected to be relevant to a user's query while also being gro
Externí odkaz:
http://arxiv.org/abs/2403.00827
We introduce a structured chain-of-thought (SCoT) prompting approach to generating content-grounded multi-turn question-answer conversations using a pre-trained large language model (LLM). At the core of our proposal is a structured breakdown of the
Externí odkaz:
http://arxiv.org/abs/2402.11770
BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback
Autor:
Pandey, Gaurav, Nandwani, Yatin, Naseem, Tahira, Mishra, Mayank, Xu, Guangxuan, Raghu, Dinesh, Joshi, Sachindra, Munawar, Asim, Astudillo, Ramón Fernandez
Distribution matching methods for language model alignment such as Generation with Distributional Control (GDC) and Distributional Policy Gradient (DPG) have not received the same level of attention in reinforcement learning from human feedback (RLHF
Externí odkaz:
http://arxiv.org/abs/2402.02479
Autor:
Lee, Young-Suk, Sultan, Md Arafat, El-Kurdi, Yousef, Munawar, Tahira Naseem Asim, Florian, Radu, Roukos, Salim, Astudillo, Ramón Fernandez
Publikováno v:
EMNLP 2023
Using in-context learning (ICL) for data generation, techniques such as Self-Instruct (Wang et al., 2023) or the follow-up Alpaca (Taori et al., 2023) can train strong conversational agents with only a small amount of human supervision. One limitatio
Externí odkaz:
http://arxiv.org/abs/2310.13961
Autor:
Crouse, Maxwell, Abdelaziz, Ibrahim, Astudillo, Ramon, Basu, Kinjal, Dan, Soham, Kumaravel, Sadhana, Fokoue, Achille, Kapanipathi, Pavan, Roukos, Salim, Lastras, Luis
Autonomous, goal-driven agents powered by LLMs have recently emerged as promising tools for solving challenging problems without the need for task-specific finetuned models that can be expensive to procure. Currently, the design and implementation of
Externí odkaz:
http://arxiv.org/abs/2310.08535
Autor:
Crouse, Maxwell, Astudillo, Ramon, Naseem, Tahira, Chaudhury, Subhajit, Kapanipathi, Pavan, Roukos, Salim, Gray, Alexander
We introduce Logical Offline Cycle Consistency Optimization (LOCCO), a scalable, semi-supervised method for training a neural semantic parser. Conceptually, LOCCO can be viewed as a form of self-learning where the semantic parser being trained is use
Externí odkaz:
http://arxiv.org/abs/2305.20018
The sliding window approach provides an elegant way to handle contexts of sizes larger than the Transformer's input window, for tasks like language modeling. Here we extend this approach to the sequence-to-sequence task of document parsing. For this,
Externí odkaz:
http://arxiv.org/abs/2305.17273
Autor:
Crouse, Maxwell, Kapanipathi, Pavan, Chaudhury, Subhajit, Naseem, Tahira, Astudillo, Ramon, Fokoue, Achille, Klinger, Tim
Nearly all general-purpose neural semantic parsers generate logical forms in a strictly top-down autoregressive fashion. Though such systems have achieved impressive results across a variety of datasets and domains, recent works have called into ques
Externí odkaz:
http://arxiv.org/abs/2305.04346