5 citations · 24 across the 19 of their papers we have counts for
20 papers
DICE: Decoupling Capability from Intervention Necessity in LLM Tutoring
Sayantan Pal, Kaiyi Ji, Rohini K. Srihari
Fluent guidance is not the same as useful intervention. LLM tutors are typically trained to generate the next teacher utterance, implicitly assuming that every student turn warrant…
GRID: Scaling Task-Agnostic Inference in Continual Prompt Tuning
Anushka Tiwari, Sayantan Pal, Rohini K. Srihari +1
Prompt-based continual learning (CL) offers a parameter-efficient way to adapt large language models (LLMs) across task sequences. However, existing methods often rely on task-awar…
ESC-Judge: A Framework for Comparing Emotional Support Conversational Agents
Navid Madani, Rohini Srihari
Large language models (LLMs) increasingly power mental-health chatbots, yet the field still lacks a scalable, theory-grounded way to decide which model is most effective to deploy.…
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…
A Recipe For Building a Compliant Real Estate Chatbot
Navid Madani, Anusha Bagalkotkar, Supriya Anand +3
In recent years, there has been significant effort to align large language models with human preferences. This work focuses on developing a chatbot specialized in the real estate d…
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…
Steering Conversational Large Language Models for Long Emotional Support Conversations
Navid Madani, Sougata Saha, Rohini Srihari
In this study, we address the challenge of enabling large language models (LLMs) to consistently adhere to emotional support strategies in extended conversations. We focus on the s…
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…
Consolidating Strategies for Countering Hate Speech Using Persuasive Dialogues
Sougata Saha, Rohini Srihari
Hateful comments are prevalent on social media platforms. Although tools for automatically detecting, flagging, and blocking such false, offensive, and harmful content online have…
Rudolf Christoph Eucken at SemEval-2023 Task 4: An Ensemble Approach for Identifying Human Values from Arguments
Sougata Saha, Rohini Srihari
The subtle human values we acquire through life experiences govern our thoughts and gets reflected in our speech. It plays an integral part in capturing the essence of our individu…
ArgU: A Controllable Factual Argument Generator
Sougata Saha, Rohini Srihari
Effective argumentation is essential towards a purposeful conversation with a satisfactory outcome. For example, persuading someone to reconsider smoking might involve empathetic,…
Domain Specific Question Answering Over Knowledge Graphs Using Logical Programming and Large Language Models
Navid Madani, Rohini K. Srihari, Kenneth Joseph
Answering questions over domain-specific graphs requires a tailored approach due to the limited number of relations and the specific nature of the domain. Our approach integrates c…
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…
Assessing Effectiveness of Using Internal Signals for Check-Worthy Claim Identification in Unlabeled Data for Automated Fact-Checking
Archita Pathak, Rohini K. Srihari
While recent work on automated fact-checking has focused mainly on verifying and explaining claims, for which the list of claims is readily available, identifying check-worthy clai…
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…
Self-Supervised Claim Identification for Automated Fact Checking
Archita Pathak, Mohammad Abuzar Shaikh, Rohini Srihari
We propose a novel, attention-based self-supervised approach to identify "claim-worthy" sentences in a fake news article, an important first step in automated fact-checking. We lev…
A Fuzzy Logic based Method for Efficient Retrieval of Vague and Uncertain Spatial Expressions in Text Exploiting the Granulation of the Spatial Event Queries
Kanagavalli. V. R, Raja. K
The arrangement of things in n-dimensional space is specified as Spatial. Spatial data consists of values that denote the location and shape of objects and areas on the earths surf…