126 citations · 279 across the 40 of their papers we have counts for
19 papers · 1 filter
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…
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…
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…
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…
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…
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…
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…
MM-Soc: Benchmarking Multimodal Large Language Models in Social Media Platforms
Yiqiao Jin, Minje Choi, Gaurav Verma +2
Social media platforms are hubs for multimodal information exchange, encompassing text, images, and videos, making it challenging for machines to comprehend the information or emot…
Better to Ask in English: Cross-Lingual Evaluation of Large Language Models for Healthcare Queries
Yiqiao Jin, Mohit Chandra, Gaurav Verma +3
Large language models (LLMs) are transforming the ways the general public accesses and consumes information. Their influence is particularly pronounced in pivotal sectors like heal…
Overview of Memotion 3: Sentiment and Emotion Analysis of Codemixed Hinglish Memes
Shreyash Mishra, S Suryavardan, Megha Chakraborty +9
Analyzing memes on the internet has emerged as a crucial endeavor due to the impact this multi-modal form of content wields in shaping online discourse. Memes have become a powerfu…
Findings of Factify 2: Multimodal Fake News Detection
S Suryavardan, Shreyash Mishra, Megha Chakraborty +9
With social media usage growing exponentially in the past few years, fake news has also become extremely prevalent. The detrimental impact of fake news emphasizes the need for rese…
Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding
Venkata Prabhakara Sarath Nookala, Gaurav Verma, Subhabrata Mukherjee +1
State-of-the-art few-shot learning (FSL) methods leverage prompt-based fine-tuning to obtain remarkable results for natural language understanding (NLU) tasks. While much of the pr…
Cross-Modal Attribute Insertions for Assessing the Robustness of Vision-and-Language Learning
Shivaen Ramshetty, Gaurav Verma, Srijan Kumar
The robustness of multimodal deep learning models to realistic changes in the input text is critical for their applicability to important tasks such as text-to-image retrieval and…
Factify 2: A Multimodal Fake News and Satire News Dataset
S Suryavardan, Shreyash Mishra, Parth Patwa +9
The internet gives the world an open platform to express their views and share their stories. While this is very valuable, it makes fake news one of our society's most pressing pro…
Memotion 3: Dataset on Sentiment and Emotion Analysis of Codemixed Hindi-English Memes
Shreyash Mishra, S Suryavardan, Parth Patwa +9
Memes are the new-age conveyance mechanism for humor on social media sites. Memes often include an image and some text. Memes can be used to promote disinformation or hatred, thus…