Zobrazeno 1 - 10
of 200
pro vyhledávání: '"Rajamani, Sriram"'
Autor:
Gupta, Naman, Kirtania, Shashank, Gupta, Priyanshu, Kariya, Krishna, Gulwani, Sumit, Iyer, Arun, Parthasarathy, Suresh, Radhakrishna, Arjun, Rajamani, Sriram K., Soares, Gustavo
Large Language Models (LLMs) often generate incorrect or outdated information, especially in low-resource settings or when dealing with private data. To address this, Retrieval-Augmented Generation (RAG) uses external knowledge bases (KBs), but these
Externí odkaz:
http://arxiv.org/abs/2410.10584
Autor:
Wadhwa, Nalin, Pradhan, Jui, Sonwane, Atharv, Sahu, Surya Prakash, Natarajan, Nagarajan, Kanade, Aditya, Parthasarathy, Suresh, Rajamani, Sriram
As software projects progress, quality of code assumes paramount importance as it affects reliability, maintainability and security of software. For this reason, static analysis tools are used in developer workflows to flag code quality issues. Howev
Externí odkaz:
http://arxiv.org/abs/2309.12938
Autor:
Bairi, Ramakrishna, Sonwane, Atharv, Kanade, Aditya, C, Vageesh D, Iyer, Arun, Parthasarathy, Suresh, Rajamani, Sriram, Ashok, B., Shet, Shashank
Software engineering activities such as package migration, fixing errors reports from static analysis or testing, and adding type annotations or other specifications to a codebase, involve pervasively editing the entire repository of code. We formula
Externí odkaz:
http://arxiv.org/abs/2309.12499
Autor:
YM, Pradyumna, Ganesan, Vinod, Arumugam, Dinesh Kumar, Gupta, Meghna, Shadagopan, Nischith, Dixit, Tanay, Segal, Sameer, Kumar, Pratyush, Jain, Mohit, Rajamani, Sriram
Large Language Models (LLMs) have revolutionized programming and software engineering. AI programming assistants such as GitHub Copilot X enable conversational programming, narrowing the gap between human intent and code generation. However, prior li
Externí odkaz:
http://arxiv.org/abs/2309.09495
Autor:
Jain, Naman, Gandhi, Shubham, Sonwane, Atharv, Kanade, Aditya, Natarajan, Nagarajan, Parthasarathy, Suresh, Rajamani, Sriram, Sharma, Rahul
Static analysis tools are traditionally used to detect and flag programs that violate properties. We show that static analysis tools can also be used to perturb programs that satisfy a property to construct variants that violate the property. Using t
Externí odkaz:
http://arxiv.org/abs/2307.12465
Language models of code (LMs) work well when the surrounding code provides sufficient context. This is not true when it becomes necessary to use types, functionality or APIs defined elsewhere in the repository or a linked library, especially those no
Externí odkaz:
http://arxiv.org/abs/2306.10763
Autor:
Parthasarathy, Suresh, Pattanaik, Lincy, Khatry, Anirudh, Iyer, Arun, Radhakrishna, Arjun, Rajamani, Sriram, Raza, Mohammad
We propose a new approach to extracting data items or field values from semi-structured documents. Examples of such problems include extracting passenger name, departure time and departure airport from a travel itinerary, or extracting price of an it
Externí odkaz:
http://arxiv.org/abs/2204.05021
Autor:
Jain, Naman, Vaidyanath, Skanda, Iyer, Arun, Natarajan, Nagarajan, Parthasarathy, Suresh, Rajamani, Sriram, Sharma, Rahul
Large pre-trained language models such as GPT-3, Codex, and Google's language model are now capable of generating code from natural language specifications of programmer intent. We view these developments with a mixture of optimism and caution. On th
Externí odkaz:
http://arxiv.org/abs/2112.02969
Autor:
Natarajan, Nagarajan, Karthikeyan, Ajaykrishna, Jain, Prateek, Radicek, Ivan, Rajamani, Sriram, Gulwani, Sumit, Gehrke, Johannes
We formalize and study ``programming by rewards'' (PBR), a new approach for specifying and synthesizing subroutines for optimizing some quantitative metric such as performance, resource utilization, or correctness over a benchmark. A PBR specificatio
Externí odkaz:
http://arxiv.org/abs/2007.06835
Unlike traditional programs (such as operating systems or word processors) which have large amounts of code, machine learning tasks use programs with relatively small amounts of code (written in machine learning libraries), but voluminous amounts of
Externí odkaz:
http://arxiv.org/abs/1603.07292