5 citations · 13 across the 10 of their papers we have counts for
10 papers
Beyond Discrete Personas: Personality Modeling Through Journal Intensive Conversations
Sayantan Pal, Souvik Das, Rohini K. Srihari
Large Language Models (LLMs) have significantly improved personalized conversational capabilities. However, existing datasets like Persona Chat, Synthetic Persona Chat, and Blended…
Mitigating Clickbait: An Approach to Spoiler Generation Using Multitask Learning
Sayantan Pal, Souvik Das, Rohini K. Srihari
This study introduces 'clickbait spoiling', a novel technique designed to detect, categorize, and generate spoilers as succinct text responses, countering the curiosity induced by…
Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models
Souvik Das, Lifeng Jin, Linfeng Song +3
Large language models (LLMs) exhibit impressive natural language capabilities but suffer from hallucination -- generating content ungrounded in the realities of training data. Rece…
Improving Dialog Safety using Socially Aware Contrastive Learning
Souvik Das, Rohini K. Srihari
State-of-the-art conversational AI systems raise concerns due to their potential risks of generating unsafe, toxic, unethical, or dangerous content. Previous works have developed d…
Diving Deep into Modes of Fact Hallucinations in Dialogue Systems
Souvik Das, Sougata Saha, Rohini K. Srihari
Knowledge Graph(KG) grounded conversations often use large pre-trained models and usually suffer from fact hallucination. Frequently entities with no references in knowledge source…
Using Multi-Encoder Fusion Strategies to Improve Personalized Response Selection
Souvik Das, Sougata Saha, Rohini K. Srihari
Personalized response selection systems are generally grounded on persona. However, there exists a co-relation between persona and empathy, which is not explored well in these syst…
Proto: A Neural Cocktail for Generating Appealing Conversations
Sougata Saha, Souvik Das, Elizabeth Soper +2
In this paper, we present our Alexa Prize Grand Challenge 4 socialbot: Proto. Leveraging diverse sources of world knowledge, and powered by a suite of neural and rule-based natural…
Medical Literature Mining and Retrieval in a Conversational Setting
Souvik Das, Sougata Saha, Rohini K. Srihari
The Covid-19 pandemic has caused a spur in the medical research literature. With new research advances in understanding the virus, there is a need for robust text mining tools whic…
Similarity Based Label Smoothing For Dialogue Generation
Sougata Saha, Souvik Das, Rohini Srihari
Generative neural conversational systems are generally trained with the objective of minimizing the entropy loss between the training "hard" targets and the predicted logits. Often…
A multi-agent evolutionary robotics framework to train spiking neural networks
Souvik Das, Anirudh Shankar, Vaneet Aggarwal
A novel multi-agent evolutionary robotics (ER) based framework, inspired by competitive evolutionary environments in nature, is demonstrated for training Spiking Neural Networks (S…