PhD Thesis Proposal - Nan Xu

Committee Members: Xuezhe Ma (chair), Muhao Chen, Jonathan May, Ram Nevatia, Daniel O’Leary    
 
 
Title: Decoding Recipes for Coherent and Factual Text Generation   
 
 
Abstract: While Large language models (LLMs) have demonstrated increasing power in generating texts, they have also called upon studies on their degeneration problems such as repetition, incoherence, hallucination, etc. My PhD thesis outlines my research aiming to tackle these challenges from the perspective of decoding, which is train-free and driven by models' own understanding of seen and generated texts. Specifically, I focus on 1) reducing undesired repetitions and off-topic generations by analyzing probability distribution of decoding steps for open-ended text generation and 2) mitigating hallucinations by studying models' uncertainty against user prompts for false-premise question answering.    Motivated by the emergent ability of Large Vision Language Models (LVLMs) to perceive and understand visual signals, I will also introduce my proposal to mitigate hallucinations with effective decoding strategies given multimodal inputs.     
 
 
Venue: RTH 306 and Zoom https://usc.zoom.us/j/97468606369?pwd=a2ovTlYweE1neGpTMHFtUlNrcVVnQT09    
 
 
Date: 04/30/2024, 4:30-6:30PM

Location: Ronald Tutor Hall of Engineering (RTH) - 306

Audiences: Everyone Is Invited

Contact: Ellecia Williams