126 citations · 279 across the 40 of their papers we have counts for
44 papers
UniSD: Towards a Unified Self-Distillation Framework for Large Language Models
Yiqiao Jin, Yiyang Wang, Lucheng Fu +7
Self-distillation (SD) offers a promising path for adapting large language models (LLMs) without relying on stronger external teachers. However, SD in autoregressive LLMs remains c…
AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent
Yinyi Luo, Yiqiao Jin, Weichen Yu +6
While large language model (LLM) multi-agent systems achieve superior reasoning performance through iterative debate, practical deployment is limited by their high computational co…
CALM-IT: Enhancing Synthetic Motivational Interviewing Dialogue Quality with Conversational Dynamics
Viet Cuong Nguyen, Nhi Yen Nguyen, Kristin A. Candan +5
Conversational dynamics describe how rapport, emotion, and goals change over a dialogue. These changes are important in therapeutic conversations, where they can influence when and…
SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding
Yiqiao Jin, Rachneet Kaur, Zhen Zeng +2
Multi-page visual documents such as manuals, brochures, presentations, and posters convey key information through layout, colors, icons, and cross-slide references. While multimoda…
Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings
Kartik Sharma, Yiqiao Jin, Rakshit Trivedi +1
Large language models (LLMs) acquire knowledge across diverse domains such as science, history, and geography encountered during generative pre-training. However, due to their stoc…
ROBAD: Robust Adversary-aware Local-Global Attended Bad Actor Detection Sequential Model
Bing He, Mustaque Ahamad, Srijan Kumar
Detecting bad actors is critical to ensure the safety and integrity of internet platforms. Several deep learning-based models have been developed to identify such users. These mode…
SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
Yiqiao Jin, Kartik Sharma, Vineeth Rakesh +4
Retrieval-augmented Generation (RAG) extends large language models (LLMs) with external knowledge but faces key challenges: restricted effective context length and redundancy in re…
Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts
Kartik Sharma, Yiqiao Jin, Vineeth Rakesh +4
As large language models (LLMs) are deployed in safety-critical settings, it is essential to ensure that their responses comply with safety standards. Prior research has revealed t…
The Influence of Text Variation on User Engagement in Cross-Platform Content Sharing
Yibo Hu, Yiqiao Jin, Meng Ye +2
In today's cross-platform social media landscape, understanding factors that drive engagement for multimodal content, especially text paired with visuals, remains complex. This stu…
A Framework for Situating Innovations, Opportunities, and Challenges in Advancing Vertical Systems with Large AI Models
Gaurav Verma, Jiawei Zhou, Mohit Chandra +2
Large artificial intelligence (AI) models have garnered significant attention for their remarkable, often "superhuman", performance on standardized benchmarks. However, when these…
A Thousand Words or An Image: Studying the Influence of Persona Modality in Multimodal LLMs
Julius Broomfield, Kartik Sharma, Srijan Kumar
Large language models (LLMs) have recently demonstrated remarkable advancements in embodying diverse personas, enhancing their effectiveness as conversational agents and virtual as…
Personalized Layer Selection for Graph Neural Networks
Kartik Sharma, Vineeth Rakesh, Yingtong Dou +2
Graph Neural Networks (GNNs) combine node attributes over a fixed granularity of the local graph structure around a node to predict its label. However, different nodes may relate t…
UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models
Sejoon Oh, Yiqiao Jin, Megha Sharma +4
Multimodal large language models (MLLMs) have revolutionized vision-language understanding but remain vulnerable to multimodal jailbreak attacks, where adversarial inputs are metic…
Do Large Language Models Align with Core Mental Health Counseling Competencies?
Viet Cuong Nguyen, Mohammad Taher, Dongwan Hong +8
The rapid evolution of Large Language Models (LLMs) presents a promising solution to the global shortage of mental health professionals. However, their alignment with essential cou…
MedHalu: Hallucinations in Responses to Healthcare Queries by Large Language Models
Vibhor Agarwal, Yiqiao Jin, Mohit Chandra +3
Large language models (LLMs) are starting to complement traditional information seeking mechanisms such as web search. LLM-powered chatbots like ChatGPT are gaining prominence amon…
Adversarial Text Rewriting for Text-aware Recommender Systems
Sejoon Oh, Gaurav Verma, Srijan Kumar
Text-aware recommender systems incorporate rich textual features, such as titles and descriptions, to generate item recommendations for users. The use of textual features helps mit…
A Community-Centric Perspective for Characterizing and Detecting Anti-Asian Violence-Provoking Speech
Gaurav Verma, Rynaa Grover, Jiawei Zhou +4
Violence-provoking speech -- speech that implicitly or explicitly promotes violence against the members of the targeted community, contributed to a massive surge in anti-Asian crim…
Supporters and Skeptics: LLM-based Analysis of Engagement with Mental Health (Mis)Information Content on Video-sharing Platforms
Viet Cuong Nguyen, Mini Jain, Abhijat Chauhan +7
Over one in five adults in the US lives with a mental illness. In the face of a shortage of mental health professionals and offline resources, online short-form video content has g…
Empowering Interdisciplinary Insights with Dynamic Graph Embedding Trajectories
Yiqiao Jin, Andrew Zhao, Yeon-Chang Lee +3
We developed DyGETViz, a novel framework for effectively visualizing dynamic graphs (DGs) that are ubiquitous across diverse real-world systems. This framework leverages recent adv…
SVD-AE: Simple Autoencoders for Collaborative Filtering
Seoyoung Hong, Jeongwhan Choi, Yeon-Chang Lee +2
Collaborative filtering (CF) methods for recommendation systems have been extensively researched, ranging from matrix factorization and autoencoder-based to graph filtering-based m…
Corrective or Backfire: Characterizing and Predicting User Response to Social Correction
Bing He, Yingchen Ma, Mustaque Ahamad +1
Online misinformation poses a global risk with harmful implications for society. Ordinary social media users are known to actively reply to misinformation posts with counter-misinf…
FINEST: Stabilizing Recommendations by Rank-Preserving Fine-Tuning
Sejoon Oh, Berk Ustun, Julian McAuley +1
Modern recommender systems may output considerably different recommendations due to small perturbations in the training data. Changes in the data from a single user will alter the…
Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space
Gaurav Verma, Minje Choi, Kartik Sharma +3
Multimodal large language models (MLLMs) like LLaVA and GPT-4(V) enable general-purpose conversations about images with the language modality. As off-the-shelf MLLMs may have limit…
Towards Fair Graph Anomaly Detection: Problem, Benchmark Datasets, and Evaluation
Neng Kai Nigel Neo, Yeon-Chang Lee, Yiqiao Jin +2
The Fair Graph Anomaly Detection (FairGAD) problem aims to accurately detect anomalous nodes in an input graph while avoiding biased predictions against individuals from sensitive…