Publications (14)
ConCodeEval: Evaluating Large Language Models for Code Constraints in Domain-Specific Languages
Mehant Kammakomati, Sameer Pimparkhede, Srikanth Tamilselvam +2
Recent work shows Large Language Models (LLMs) struggle to understand natural language constraints for various text generation tasks in zero- and few-shot settings. While, in the c…
Study on Kelvin Helmholtz shear flows subjected to differential rotation
Prince Kumar, Devendra Sharma
A numerical simulation of Kelvin-Helmholtz Instability (KHI) in parallel shear flows subjected to external rotation is carried out using a pseudo-spectral technique. The Coriolis f…
Collective excitations of rotating dusty plasma under quasi-localized charge approximation of strongly coupled systems
Prince Kumar, Devendra Sharma
Collective excitations of rotating dusty plasma are analyzed under the quasi localized charge approximation (QLCA) framework for strongly coupled systems by explicitly accounting f…
Precursor Solitons in Plasma Flow Past Charged Obstacles: Role of Obstacle Bias and Ion Temperature Anisotropy
Prince Kumar, S. K. Mishra
We investigate electrostatic ion-acoustic precursor solitons in a plasma flow past an absorbing charged obstacle using two-dimensional (2D) electrostatic PIC simulations. A key out…
ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries
Kishan Maharaj, Vitobha Munigala, Srikanth G. Tamilselvam +5
Recent advancements in large language models (LLMs) have significantly enhanced their ability to understand both natural language and code, driving their use in tasks like natural…
Read between the lines -- Functionality Extraction From READMEs
Prince Kumar, Srikanth Tamilselvam, Dinesh Garg
While text summarization is a well-known NLP task, in this paper, we introduce a novel and useful variant of it called functionality extraction from Git README files. Though this t…
Dust vortex flow analysis in weakly magnetized plasma
Prince Kumar, Devendra Sharma
Analysis of driven dust vortex flow is presented in a weakly magnetized plasma. The 2D hydrodynamic model is applied to the confined dust cloud in a non-uniform magnetic field in o…
Quasi-localized charge approximation approach for the nonlinear structures in strongly coupled Yukawa systems
Prince Kumar, Devendra Sharma
Strongly coupled systems occupying the transitional range between the Wigner crystal and fluid phases are most dynamic constituents of the nature. Highly localized but strongly int…
Training with Pseudo-Code for Instruction Following
Prince Kumar, Rudra Murthy, Riyaz Bhat +1
Despite rapid advances in the capabilities of Large Language Models (LLMs), they continue to struggle with following relatively simple and unambiguous instructions, particularly wh…
Prompting with Pseudo-Code Instructions
Mayank Mishra, Prince Kumar, Riyaz Bhat +3
Prompting with natural language instructions has recently emerged as a popular method of harnessing the capabilities of large language models. Given the inherent ambiguity present…
KCIF: Knowledge-Conditioned Instruction Following
Rudra Murthy, Praveen Venkateswaran, Prince Kumar +1
LLM evaluation benchmarks have traditionally separated the testing of knowledge/reasoning capabilities from instruction following. In this work, we study the interaction between kn…
DocCGen: Document-based Controlled Code Generation
Sameer Pimparkhede, Mehant Kammakomati, Srikanth Tamilselvam +3
Recent developments show that Large Language Models (LLMs) produce state-of-the-art performance on natural language (NL) to code generation for resource-rich general-purpose langua…
Modulational instability of a Yukawa fluid excitation under the Quasi-localization charged approximation (QLCA) framework
Sandip Dalui, Prince Kumar, Devendra Sharma
Collective response dynamics of a strongly coupled system departs from the continuum phase upon transition to the quasicrystalline phase, or formation of a Wigner lattice. The wave…
Divide and Conquer: An Ensemble Approach for Hostile Post Detection in Hindi
Varad Bhatnagar, Prince Kumar, Sairam Moghili +1
Recently the NLP community has started showing interest towards the challenging task of Hostile Post Detection. This paper present our system for Shared Task at Constraint2021 on "…