Zobrazeno 1 - 10
of 378
pro vyhledávání: '"Tanmay, Kumar"'
We study the effect of dark matter scalar and vector-mediated interactions on dark matter admixed neutron stars. In particular, we exploit the two-fluid formalism of Tolman-Oppenheimer-Volkoff equations as generic framework for dark matter admixed ne
Externí odkaz:
http://arxiv.org/abs/2407.16386
Autor:
Ahuja, Sanchit, Tanmay, Kumar, Chauhan, Hardik Hansrajbhai, Patra, Barun, Aggarwal, Kriti, Del Corro, Luciano, Mitra, Arindam, Dhamecha, Tejas Indulal, Awadallah, Ahmed, Choudhary, Monojit, Chaudhary, Vishrav, Sitaram, Sunayana
Despite the remarkable success of LLMs in English, there is a significant gap in performance in non-English languages. In order to address this, we introduce a novel recipe for creating a multilingual synthetic instruction tuning dataset, sPhinX, whi
Externí odkaz:
http://arxiv.org/abs/2407.09879
Ethical reasoning is a crucial skill for Large Language Models (LLMs). However, moral values are not universal, but rather influenced by language and culture. This paper explores how three prominent LLMs -- GPT-4, ChatGPT, and Llama2-70B-Chat -- perf
Externí odkaz:
http://arxiv.org/abs/2404.18460
Ultralight electrophilic scalar field can mediate a long-range force or radiate from a pulsar or a magnetar if the scalar field has a coupling with the Goldreich-Julian charge density or the net electron charge density of the star. The interaction of
Externí odkaz:
http://arxiv.org/abs/2404.18309
This paper explores the moral judgment and moral reasoning abilities exhibited by Large Language Models (LLMs) across languages through the Defining Issues Test. It is a well known fact that moral judgment depends on the language in which the questio
Externí odkaz:
http://arxiv.org/abs/2402.02135
Autor:
Kharyal, Chaitanya, Gottipati, Sai Krishna, Sinha, Tanmay Kumar, Das, Srijita, Taylor, Matthew E.
One of the final frontiers in the development of complex human - AI collaborative systems is the ability of AI agents to comprehend the natural language and perform tasks accordingly. However, training efficient Reinforcement Learning (RL) agents gro
Externí odkaz:
http://arxiv.org/abs/2401.02991
Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs
In this position paper, we argue that instead of morally aligning LLMs to specific set of ethical principles, we should infuse generic ethical reasoning capabilities into them so that they can handle value pluralism at a global scale. When provided w
Externí odkaz:
http://arxiv.org/abs/2310.07251
In this study, we measure the moral reasoning ability of LLMs using the Defining Issues Test - a psychometric instrument developed for measuring the moral development stage of a person according to the Kohlberg's Cognitive Moral Development Model. DI
Externí odkaz:
http://arxiv.org/abs/2309.13356
The interaction of neutrinos with ultralight scalar and vector dark matter backgrounds induce a modification of the neutrino dispersion relation. The effects of this modification are reviewed in the framework of asymmetric emission of neutrinos from
Externí odkaz:
http://arxiv.org/abs/2307.05229
Autor:
Aggarwal, Kriti, Khandelwal, Aditi, Tanmay, Kumar, Khan, Owais Mohammed, Liu, Qiang, Choudhury, Monojit, Chauhan, Hardik Hansrajbhai, Som, Subhojit, Chaudhary, Vishrav, Tiwary, Saurabh
Visual document understanding is a complex task that involves analyzing both the text and the visual elements in document images. Existing models often rely on manual feature engineering or domain-specific pipelines, which limit their generalization
Externí odkaz:
http://arxiv.org/abs/2305.14218