Zobrazeno 1 - 10
of 71
pro vyhledávání: '"Bhagavatula, Chandra"'
Autor:
West, Peter, Bras, Ronan Le, Sorensen, Taylor, Lin, Bill Yuchen, Jiang, Liwei, Lu, Ximing, Chandu, Khyathi, Hessel, Jack, Baheti, Ashutosh, Bhagavatula, Chandra, Choi, Yejin
We present NovaCOMET, an open commonsense knowledge model, that combines the best aspects of knowledge and general task models. Compared to previous knowledge models, NovaCOMET allows open-format relations enabling direct application to reasoning tas
Externí odkaz:
http://arxiv.org/abs/2312.05979
Autor:
Lin, Bill Yuchen, Ravichander, Abhilasha, Lu, Ximing, Dziri, Nouha, Sclar, Melanie, Chandu, Khyathi, Bhagavatula, Chandra, Choi, Yejin
The alignment tuning process of large language models (LLMs) typically involves instruction learning through supervised fine-tuning (SFT) and preference tuning via reinforcement learning from human feedback (RLHF). A recent study, LIMA (Zhou et al. 2
Externí odkaz:
http://arxiv.org/abs/2312.01552
Large language models (LLMs) show amazing proficiency and fluency in the use of language. Does this mean that they have also acquired insightful linguistic knowledge about the language, to an extent that they can serve as an "expert linguistic annota
Externí odkaz:
http://arxiv.org/abs/2310.17793
Autor:
Qiu, Linlu, Jiang, Liwei, Lu, Ximing, Sclar, Melanie, Pyatkin, Valentina, Bhagavatula, Chandra, Wang, Bailin, Kim, Yoon, Choi, Yejin, Dziri, Nouha, Ren, Xiang
The ability to derive underlying principles from a handful of observations and then generalize to novel situations -- known as inductive reasoning -- is central to human intelligence. Prior work suggests that language models (LMs) often fall short on
Externí odkaz:
http://arxiv.org/abs/2310.08559
Autor:
Sorensen, Taylor, Jiang, Liwei, Hwang, Jena, Levine, Sydney, Pyatkin, Valentina, West, Peter, Dziri, Nouha, Lu, Ximing, Rao, Kavel, Bhagavatula, Chandra, Sap, Maarten, Tasioulas, John, Choi, Yejin
Publikováno v:
Vol. 38 No. 18: AAAI-24 Technical Tracks 18; 2024; 19937-19947
Human values are crucial to human decision-making. Value pluralism is the view that multiple correct values may be held in tension with one another (e.g., when considering lying to a friend to protect their feelings, how does one balance honesty with
Externí odkaz:
http://arxiv.org/abs/2309.00779
Autor:
Brahman, Faeze, Bhagavatula, Chandra, Pyatkin, Valentina, Hwang, Jena D., Li, Xiang Lorraine, Arai, Hirona J., Sanyal, Soumya, Sakaguchi, Keisuke, Ren, Xiang, Choi, Yejin
Procedural planning, which entails decomposing a high-level goal into a sequence of temporally ordered steps, is an important yet intricate task for machines. It involves integrating common-sense knowledge to reason about complex and often contextual
Externí odkaz:
http://arxiv.org/abs/2305.19472
Autor:
Dziri, Nouha, Lu, Ximing, Sclar, Melanie, Li, Xiang Lorraine, Jiang, Liwei, Lin, Bill Yuchen, West, Peter, Bhagavatula, Chandra, Bras, Ronan Le, Hwang, Jena D., Sanyal, Soumya, Welleck, Sean, Ren, Xiang, Ettinger, Allyson, Harchaoui, Zaid, Choi, Yejin
Transformer large language models (LLMs) have sparked admiration for their exceptional performance on tasks that demand intricate multi-step reasoning. Yet, these models simultaneously show failures on surprisingly trivial problems. This begs the que
Externí odkaz:
http://arxiv.org/abs/2305.18654
Autor:
Lin, Bill Yuchen, Fu, Yicheng, Yang, Karina, Brahman, Faeze, Huang, Shiyu, Bhagavatula, Chandra, Ammanabrolu, Prithviraj, Choi, Yejin, Ren, Xiang
We introduce SwiftSage, a novel agent framework inspired by the dual-process theory of human cognition, designed to excel in action planning for complex interactive reasoning tasks. SwiftSage integrates the strengths of behavior cloning and prompting
Externí odkaz:
http://arxiv.org/abs/2305.17390
Autor:
Pyatkin, Valentina, Hwang, Jena D., Srikumar, Vivek, Lu, Ximing, Jiang, Liwei, Choi, Yejin, Bhagavatula, Chandra
Context is everything, even in commonsense moral reasoning. Changing contexts can flip the moral judgment of an action; "Lying to a friend" is wrong in general, but may be morally acceptable if it is intended to protect their life. We present Clarify
Externí odkaz:
http://arxiv.org/abs/2212.10409
Autor:
Bhagavatula, Chandra, Hwang, Jena D., Downey, Doug, Bras, Ronan Le, Lu, Ximing, Qin, Lianhui, Sakaguchi, Keisuke, Swayamdipta, Swabha, West, Peter, Choi, Yejin
Commonsense capabilities of pre-trained language models dramatically improve with scale, leading many to believe that scale is the only winning recipe. But is it? Here, we investigate an alternative that a priori seems impossible: can smaller languag
Externí odkaz:
http://arxiv.org/abs/2212.09246