4 papers
Safe to Serve: Aligning Instruction-Tuned Models for Safety and Helpfulness
Avinash Amballa, Durga Sandeep Saluru, Gayathri Akkinapalli +2
Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning and text generation. However, these models can inadvertently generate unsafe or biased r…
Quasi-random Multi-Sample Inference for Large Language Models
Aditya Parashar, Aditya Vikram Singh, Avinash Amballa +2
Large language models (LLMs) are often equipped with multi-sample decoding strategies. An LLM implicitly defines an arithmetic code book, facilitating efficient and embarrassingly…
Automated Model Selection for Tabular Data
Avinash Amballa, Gayathri Akkinapalli, Manas Madine +2
Structured data in the form of tabular datasets contain features that are distinct and discrete, with varying individual and relative importances to the target. Combinations of one…
Targeted Attacks on Timeseries Forecasting
Yuvaraj Govindarajulu, Avinash Amballa, Pavan Kulkarni +1
Real-world deep learning models developed for Time Series Forecasting are used in several critical applications ranging from medical devices to the security domain. Many previous w…