Zobrazeno 1 - 10
of 68
pro vyhledávání: '"Kachuee, Mohammad"'
Task-orientated conversational agents interact with users and assist them via leveraging external APIs. A typical task-oriented conversational system can be broken down into three phases: external API selection, argument filling, and response generat
Externí odkaz:
http://arxiv.org/abs/2407.12016
Large Language Models (LLMs) have shown remarkable capabilities in tasks such as summarization, arithmetic reasoning, and question answering. However, they encounter significant challenges in the domain of moral reasoning and ethical decision-making,
Externí odkaz:
http://arxiv.org/abs/2405.12933
Autor:
Ovalle, Anaelia, Goldstein, Orpaz, Kachuee, Mohammad, Wu, Elizabeth S C, Hong, Chenglin, Holloway, Ian W, Sarrafzadeh, Majid
Publikováno v:
Journal of Medical Internet Research, Vol 23, Iss 4, p e22042 (2021)
BackgroundSocial media networks provide an abundance of diverse information that can be leveraged for data-driven applications across various social and physical sciences. One opportunity to utilize such data exists in the public health domain, where
Externí odkaz:
https://doaj.org/article/3c5c78d09679488f953e317dd49b1f7e
Current conversational AI systems based on large language models (LLMs) are known to generate unsafe responses, agreeing to offensive user input or including toxic content. Previous research aimed to alleviate the toxicity, by fine-tuning LLM with ma
Externí odkaz:
http://arxiv.org/abs/2402.08968
Large-scale conversational systems typically rely on a skill-routing component to route a user request to an appropriate skill and interpretation to serve the request. In such system, the agent is responsible for serving thousands of skills and inter
Externí odkaz:
http://arxiv.org/abs/2306.04823
Off-Policy reinforcement learning has been a driving force for the state-of-the-art conversational AIs leading to more natural humanagent interactions and improving the user satisfaction for goal-oriented agents. However, in large-scale commercial se
Externí odkaz:
http://arxiv.org/abs/2305.10528
Autor:
Kachuee, Mohammad, Lee, Sungjin
Recently, self-learning methods based on user satisfaction metrics and contextual bandits have shown promising results to enable consistent improvements in conversational AI systems. However, directly targeting such metrics by off-policy bandit learn
Externí odkaz:
http://arxiv.org/abs/2209.08429
Skill routing is an important component in large-scale conversational systems. In contrast to traditional rule-based skill routing, state-of-the-art systems use a model-based approach to enable natural conversations. To provide supervision signal req
Externí odkaz:
http://arxiv.org/abs/2204.07135
In many real-world machine learning applications, samples belong to a set of domains e.g., for product reviews each review belongs to a product category. In this paper, we study multi-domain imbalanced learning (MIL), the scenario that there is imbal
Externí odkaz:
http://arxiv.org/abs/2204.01916
The proliferation of edge networks creates islands of learning agents working on local streams of data. Transferring knowledge between these agents in real-time without exposing private data allows for collaboration to decrease learning time and incr
Externí odkaz:
http://arxiv.org/abs/2011.05961