Zobrazeno 1 - 10
of 84
pro vyhledávání: '"Talamadupula, Kartik"'
Retrieval augmented generation (RAG) systems augment how knowledge language models are by integrating external information sources such as Wikipedia, internal documents, scientific papers, or the open internet. RAG systems that rely on the open inter
Externí odkaz:
http://arxiv.org/abs/2408.11189
Autor:
Basu, Kinjal, Murugesan, Keerthiram, Chaudhury, Subhajit, Campbell, Murray, Talamadupula, Kartik, Klinger, Tim
Text-based games (TBGs) have emerged as an important collection of NLP tasks, requiring reinforcement learning (RL) agents to combine natural language understanding with reasoning. A key challenge for agents attempting to solve such tasks is to gener
Externí odkaz:
http://arxiv.org/abs/2403.10692
This study analyzes changes in the attention mechanisms of large language models (LLMs) when used to understand natural conversations between humans (human-human). We analyze three use cases of LLMs: interactions over web content, code, and mathemati
Externí odkaz:
http://arxiv.org/abs/2403.05045
Deep learning models, though having achieved great success in many different fields over the past years, are usually data hungry, fail to perform well on unseen samples, and lack of interpretability. Various prior knowledge often exists in the target
Externí odkaz:
http://arxiv.org/abs/2212.00017
Autor:
Weisz, Justin D., Muller, Michael, Ross, Steven I., Martinez, Fernando, Houde, Stephanie, Agarwal, Mayank, Talamadupula, Kartik, Richards, John T.
Generative machine learning models have recently been applied to source code, for use cases including translating code between programming languages, creating documentation from code, and auto-completing methods. Yet, state-of-the-art models often pr
Externí odkaz:
http://arxiv.org/abs/2202.07682
Autor:
Sun, Jiao, Liao, Q. Vera, Muller, Michael, Agarwal, Mayank, Houde, Stephanie, Talamadupula, Kartik, Weisz, Justin D.
What does it mean for a generative AI model to be explainable? The emergent discipline of explainable AI (XAI) has made great strides in helping people understand discriminative models. Less attention has been paid to generative models that produce a
Externí odkaz:
http://arxiv.org/abs/2202.04903
Autor:
Awad, Edmond, Levine, Sydney, Loreggia, Andrea, Mattei, Nicholas, Rahwan, Iyad, Rossi, Francesca, Talamadupula, Kartik, Tenenbaum, Joshua, Kleiman-Weiner, Max
Publikováno v:
Journal of Autonomous Agents and Multi-Agent Systems 38, 35 (2024)
One of the most remarkable things about the human moral mind is its flexibility. We can make moral judgments about cases we have never seen before. We can decide that pre-established rules should be broken. We can invent novel rules on the fly. Captu
Externí odkaz:
http://arxiv.org/abs/2201.07763
Autor:
Agarwal, Mayank, Talamadupula, Kartik, Martinez, Fernando, Houde, Stephanie, Muller, Michael, Richards, John, Ross, Steven I, Weisz, Justin D.
Translating source code from one programming language to another is a critical, time-consuming task in modernizing legacy applications and codebases. Recent work in this space has drawn inspiration from the software naturalness hypothesis by applying
Externí odkaz:
http://arxiv.org/abs/2110.05423
Text-based games (TBGs) have become a popular proving ground for the demonstration of learning-based agents that make decisions in quasi real-world settings. The crux of the problem for a reinforcement learning agent in such TBGs is identifying the o
Externí odkaz:
http://arxiv.org/abs/2106.05387
Autor:
Weisz, Justin D., Muller, Michael, Houde, Stephanie, Richards, John, Ross, Steven I., Martinez, Fernando, Agarwal, Mayank, Talamadupula, Kartik
Generative models have become adept at producing artifacts such as images, videos, and prose at human-like levels of proficiency. New generative techniques, such as unsupervised neural machine translation (NMT), have recently been applied to the task
Externí odkaz:
http://arxiv.org/abs/2104.03820