iiit-delhi
Mathify: Evaluating Large Language Models on Mathematical Problem Solving Tasks
Anand, Avinash, Gupta, Mohit, Prasad, Kritarth, Singla, Navya, Sanjeev, Sanjana, Kumar, Jatin, Shivam, Adarsh Raj, Shah, Rajiv Ratn
The rapid progress in the field of natural language processing (NLP) systems and the expansion of large language models (LLMs) have opened up numerous opportunities in the field of education and instructional methods. These advancements offer the potential for tailored learning experiences and immediate feedback, all delivered through accessible and cost-effective services. One notable application area for this technological advancement is in the realm of solving mathematical problems. Mathematical problem-solving not only requires the ability to decipher complex problem statements but also the skill to perform precise arithmetic calculations at each step of the problem-solving process. However, the evaluation of the arithmetic capabilities of large language models remains an area that has received relatively little attention. In response, we introduce an extensive mathematics dataset called "MathQuest" sourced from the 11th and 12th standard Mathematics NCERT textbooks. This dataset encompasses mathematical challenges of varying complexity and covers a wide range of mathematical concepts. Utilizing this dataset, we conduct fine-tuning experiments with three prominent LLMs: LLaMA-2, WizardMath, and MAmmoTH. These fine-tuned models serve as benchmarks for evaluating their performance on our dataset. Our experiments reveal that among the three models, MAmmoTH-13B emerges as the most proficient, achieving the highest level of competence in solving the presented mathematical problems. Consequently, MAmmoTH-13B establishes itself as a robust and dependable benchmark for addressing NCERT mathematics problems.
- Asia > India > NCT > Delhi (0.06)
- South America > Uruguay > Maldonado > Maldonado (0.04)
- North America > United States > California > San Diego County > San Diego (0.04)
- Europe > Ireland > Leinster > County Dublin > Dublin (0.04)
- Research Report > New Finding (0.68)
- Research Report > Promising Solution (0.46)
Extramarks Partners With IIIT-Delhi To Promote AI Research In Edtech
With the aim to promote innovations in the edtech space using artificial intelligence, Noida-based edtech startup Extramarks has partnered with Indraprastha Institute of Information Technology Delhi (IIIT-Delhi). In this partnership, Extramarks will help IIIT-Delhi to set up an AI-based research laboratory in the computer science department to the institute. The laboratory will work to find new use cases of AI in the edtech segment. Explaining further how the partnership will work, the director of IIIT-Delhi Ranjan Bose said that with the help of Extramarks, the students will gain practical experience for their constructive research in the field of AI. Ritvik Kulshrestha, CEO of Extramarks Education, said that the company has already implemented AI in the schools where it is already offering digital learning programmes.
IIIT-Delhi to start M Tech programme with specialisation in Artificial Intelligence
For first time in the national capital, the Indraprastha Institute of Information Technology-Delhi will start a new M Tech programme with specialisation in Artificial Intelligence from the academic year starting in July 2018. "The programme will be research-oriented and focus on foundations and advances in Artificial Intelligence and Machine Learning," Mayank Vatsa, head of Infosys Centre for Artificial Intelligence at IIIT-Delhi, told PTI. Vatsa said it would be a first for Delhi. The programme will prepare graduates to undertake industry careers involving innovation and problem solving using Artificial Intelligence (AI) and Machine Learning (ML) technologies. The course will be spread over four semesters and the intake would be 20 students.
Precog Research Group @ IIIT-Delhi
We are a group of researchers who study, analyze, and build different aspects of social systems (e.g. By understanding and measuring complex networks, we try and build solutions for social good. Our work primarily derives from Data Science, Computational Social Science, Social Computing, Machine Learning, and Natural Language Processing.
Infy Arm Teams Up with IIIT-Delhi for Artificial Intelligence - The New Indian Express
BENGALURU: Infosys Foundation, the philanthropic arm of Infosys, on Monday announced that it will provide a corpus grant worth 24 crore over the next three years to the Indraprastha Institute of Information Technology (IIIT), Delhi to establish the Infosys Centre for Artificial Intelligence on its Okhla campus. The centre will initially be headed by Srikanth Saripalli, an expert in robotics and unmanned aerial vehicles (UAVs), currently spending his sabbatical at IIIT-Delhi. The centre will facilitate work on both fundamental and applied aspects of artificial intelligence (AI) and focus on areas such as robotics, machine learning, computer vision, AI for software systems, large-scale data analytics, among others. Several faculty members of IIIT-Delhi will be associated with the centre, and research will be conducted by PhD scholars, post-docs, students, and visiting researchers. The centre will start a specialised MTech course.
- Information Technology (1.00)
- Education (0.79)
Infosys Foundation to Provide Grants Worth INR 24 Crore to IIIT-Delhi for Research on Artificial Intelligence
New Delhi – April 04, 2016: Infosys Foundation, the philanthropic arm of Infosys, today announced that it will provide a corpus grant worth INR 24 crore over the next three years to the Indraprastha Institute of Information Technology (IIIT), Delhi to establish the Infosys Center for Artificial Intelligence in its Okhla campus. The center will initially be headed by Dr. Srikanth Saripalli, an expert in robotics and unmanned aerial vehicles (UAVs), currently spending his sabbatical at IIIT-Delhi. The center will facilitate work on both fundamental and applied aspects of Artificial Intelligence (AI) and focus on areas such as, robotics, machine learning, computer vision, AI for software systems, large-scale data analytics, etc. Several faculty members of IIIT-Delhi will be associated with the center, and research will be conducted by PhD scholars, post-docs, students, and visiting researchers. Sudha Murty, Chairperson, Infosys Foundation "Research is the backbone of our national scientific advancements – our collective aspiration. Research requires investments in time and effort. The objective of the Infosys Center for Artificial Intelligence is to facilitate research in Artificial Intelligence that will greatly benefit our society. The team, led by Dr. Saripalli, comprises some of the most skilled research experts. Our endeavor is to facilitate the creative exchange of ideas in collaboration with IIIT-Delhi and the government. We will also provide training opportunities for students and teachers in AI and robotics."