Zobrazeno 1 - 10
of 71
pro vyhledávání: '"Shridhar Kumar"'
Large Language Models (LLMs) can transfer their reasoning skills to smaller models by teaching them to generate the intermediate reasoning process required to solve multistep reasoning tasks. While LLMs can accurately solve reasoning tasks through a
Externí odkaz:
http://arxiv.org/abs/2410.18574
Tasks requiring deductive reasoning, especially those involving multiple steps, often demand adaptive strategies such as intermediate generation of rationales or programs, as no single approach is universally optimal. While Language Models (LMs) can
Externí odkaz:
http://arxiv.org/abs/2410.16128
Autor:
Lyu, Qing, Shridhar, Kumar, Malaviya, Chaitanya, Zhang, Li, Elazar, Yanai, Tandon, Niket, Apidianaki, Marianna, Sachan, Mrinmaya, Callison-Burch, Chris
Accurately gauging the confidence level of Large Language Models' (LLMs) predictions is pivotal for their reliable application. However, LLMs are often uncalibrated inherently and elude conventional calibration techniques due to their proprietary nat
Externí odkaz:
http://arxiv.org/abs/2402.13904
Autor:
Tarasov, Denis, Shridhar, Kumar
Large Language Models (LLMs) have demonstrated proficiency in their reasoning abilities, yet their large size presents scalability challenges and limits any further customization. In contrast, compact models offer customized training but often fall s
Externí odkaz:
http://arxiv.org/abs/2402.01812
Autor:
Shridhar, Kumar, Sinha, Koustuv, Cohen, Andrew, Wang, Tianlu, Yu, Ping, Pasunuru, Ram, Sachan, Mrinmaya, Weston, Jason, Celikyilmaz, Asli
In recent years, Large Language Models (LLMs) have demonstrated remarkable generative abilities, but can they judge the quality of their own generations? A popular concept, referred to as self-refinement, postulates that LLMs can detect and correct t
Externí odkaz:
http://arxiv.org/abs/2311.07961
Language models can solve complex reasoning tasks better by learning to generate rationales for their predictions. Often these models know how to solve a task but their auto-regressive decoding nature leads to incorrect results if they start incorrec
Externí odkaz:
http://arxiv.org/abs/2311.07945
Autor:
Shridhar, Kumar, Jhamtani, Harsh, Fang, Hao, Van Durme, Benjamin, Eisner, Jason, Xia, Patrick
Large language models (LLMs) can improve their accuracy on various tasks through iteratively refining and revising their output based on feedback. We observe that these revisions can introduce errors, in which case it is better to roll back to a prev
Externí odkaz:
http://arxiv.org/abs/2309.13075
Step-by-step reasoning approaches like chain of thought (CoT) have proved to be very effective in inducing reasoning capabilities in large language models. However, the success of the CoT approach is fundamentally tied to the model size, and billion
Externí odkaz:
http://arxiv.org/abs/2212.00193
Autor:
Shridhar, Kumar, Macina, Jakub, El-Assady, Mennatallah, Sinha, Tanmay, Kapur, Manu, Sachan, Mrinmaya
Socratic questioning is an educational method that allows students to discover answers to complex problems by asking them a series of thoughtful questions. Generation of didactically sound questions is challenging, requiring understanding of the reas
Externí odkaz:
http://arxiv.org/abs/2211.12835
We have recently witnessed a number of impressive results on hard mathematical reasoning problems with language models. At the same time, the robustness of these models has also been called into question; recent works have shown that models can rely
Externí odkaz:
http://arxiv.org/abs/2210.12023