Picture for Vibhor Agarwal

Vibhor Agarwal

MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models

Add code
Sep 29, 2024
Viaarxiv icon

CodeMirage: Hallucinations in Code Generated by Large Language Models

Add code
Aug 14, 2024
Viaarxiv icon

Decentralised Moderation for Interoperable Social Networks: A Conversation-based Approach for Pleroma and the Fediverse

Add code
Apr 03, 2024
Viaarxiv icon

"Which LLM should I use?": Evaluating LLMs for tasks performed by Undergraduate Computer Science Students in India

Add code
Jan 22, 2024
Viaarxiv icon

GASCOM: Graph-based Attentive Semantic Context Modeling for Online Conversation Understanding

Add code
Oct 21, 2023
Viaarxiv icon

HateRephrase: Zero- and Few-Shot Reduction of Hate Intensity in Online Posts using Large Language Models

Add code
Oct 21, 2023
Viaarxiv icon

AI in the Gray: Exploring Moderation Policies in Dialogic Large Language Models vs. Human Answers in Controversial Topics

Add code
Aug 28, 2023
Viaarxiv icon

AnnoBERT: Effectively Representing Multiple Annotators' Label Choices to Improve Hate Speech Detection

Add code
Jan 10, 2023
Viaarxiv icon

A Graph-Based Context-Aware Model to Understand Online Conversations

Add code
Nov 16, 2022
Viaarxiv icon

GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates

Add code
Feb 16, 2022
Figure 1 for GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates
Figure 2 for GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates
Figure 3 for GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates
Figure 4 for GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates
Viaarxiv icon