11 citations · 23 across the 13 of their papers we have counts for
14 papers
BrailleBench: Investigating Multi-Criteria Braille Comprehension in Large Language Models
Jinghan Zhang, Fengran Mo, Zhiyu Chen +3
Although Large language models (LLMs) mediate access to knowledge and computational assistance, their capabilities should benefit vulnerable groups in the same way. However, it is…
Data-Efficient Symbolic Regression via Foundation Model Distillation
Wangyang Ying, Jinghan Zhang, Haoyue Bai +5
Discovering interpretable mathematical equations from observed data (a.k.a. equation discovery or symbolic regression) is a cornerstone of scientific discovery, enabling transparen…
Galaxy: A Cognition-Centered Framework for Proactive, Privacy-Preserving, and Self-Evolving LLM Agents
Chongyu Bao, Ruimin Dai, Yangbo Shen +4
Intelligent personal assistants (IPAs) such as Siri and Google Assistant are designed to enhance human capabilities and perform tasks on behalf of users. The emergence of LLM agent…
Distilling Empathy from Large Language Models
Henry J. Xie, Jinghan Zhang, Xinhao Zhang +1
The distillation of knowledge from Large Language Models (LLMs) into Smaller Language Models (SLMs), preserving the capabilities and performance of LLMs while reducing model size,…
Diversity-oriented Data Augmentation with Large Language Models
Zaitian Wang, Jinghan Zhang, Xinhao Zhang +3
Data augmentation is an essential technique in natural language processing (NLP) for enriching training datasets by generating diverse samples. This process is crucial for improvin…
LEKA:LLM-Enhanced Knowledge Augmentation
Xinhao Zhang, Jinghan Zhang, Fengran Mo +3
Humans excel in analogical learning and knowledge transfer and, more importantly, possess a unique understanding of identifying appropriate sources of knowledge. From a model's per…
Scoring with Large Language Models: A Study on Measuring Empathy of Responses in Dialogues
Henry J. Xie, Jinghan Zhang, Xinhao Zhang +1
In recent years, Large Language Models (LLMs) have become increasingly more powerful in their ability to complete complex tasks. One such task in which LLMs are often employed is s…
Dynamic Weight Adjusting Deep Q-Networks for Real-Time Environmental Adaptation
Xinhao Zhang, Jinghan Zhang, Wujun Si +1
Deep Reinforcement Learning has shown excellent performance in generating efficient solutions for complex tasks. However, its efficacy is often limited by static training modes and…
Enhancing Risk Assessment in Transformers with Loss-at-Risk Functions
Jinghan Zhang, Henry Xie, Xinhao Zhang +1
In the financial field, precise risk assessment tools are essential for decision-making. Recent studies have challenged the notion that traditional network loss functions like Mean…
Blind Spot Navigation in Large Language Model Reasoning with Thought Space Explorer
Jinghan Zhang, Fengran Mo, Tharindu Cyril Weerasooriya +4
Large language models have shown strong reasoning capabilities through chain-structured methods such as Chain-of-Thought. Recent studies optimize thought structures by generating p…
Prototypical Reward Network for Data-Efficient RLHF
Jinghan Zhang, Xiting Wang, Yiqiao Jin +3
The reward model for Reinforcement Learning from Human Feedback (RLHF) has proven effective in fine-tuning Large Language Models (LLMs). Notably, collecting human feedback for RLHF…
Retrieval-Augmented Feature Generation for Domain-Specific Classification
Xinhao Zhang, Jinghan Zhang, Fengran Mo +4
Feature generation can significantly enhance learning outcomes, particularly for tasks with limited data. An effective way to improve feature generation is to expand the current fe…
Dynamic and Adaptive Feature Generation with LLM
Xinhao Zhang, Jinghan Zhang, Banafsheh Rekabdar +3
The representation of feature space is a crucial environment where data points get vectorized and embedded for subsequent modeling. Thus the efficacy of machine learning (ML) algor…
TFWT: Tabular Feature Weighting with Transformer
Xinhao Zhang, Zaitian Wang, Lu Jiang +3
In this paper, we propose a novel feature weighting method to address the limitation of existing feature processing methods for tabular data. Typically the existing methods assume…