42 citations · 48 across the 10 of their papers we have counts for
10 papers
World Model-Guided Reinforcement Learning via Counterfactual User Engagement Simulation
Ang Li, Xin Xu, Bin Liang +4
Reinforcement learning for user-centric agents is limited by the cost, latency, and risk of collecting online feedback, as well as by the lack of counterfactual comparisons under t…
RexUniNLU: Recursive Method with Explicit Schema Instructor for Universal NLU
Chengyuan Liu, Shihang Wang, Fubang Zhao +5
Information Extraction (IE) and Text Classification (CLS) serve as the fundamental pillars of NLU, with both disciplines relying on analyzing input sequences to categorize outputs…
More Than Catastrophic Forgetting: Integrating General Capabilities For Domain-Specific LLMs
Chengyuan Liu, Yangyang Kang, Shihang Wang +5
The performance on general tasks decreases after Large Language Models (LLMs) are fine-tuned on domain-specific tasks, the phenomenon is known as Catastrophic Forgetting (CF). Howe…
Evolving Knowledge Distillation with Large Language Models and Active Learning
Chengyuan Liu, Yangyang Kang, Fubang Zhao +4
Large language models (LLMs) have demonstrated remarkable capabilities across various NLP tasks. However, their computational costs are prohibitively high. To address this issue, p…
Goal-Oriented Prompt Attack and Safety Evaluation for LLMs
Chengyuan Liu, Fubang Zhao, Lizhi Qing +4
Large Language Models (LLMs) presents significant priority in text understanding and generation. However, LLMs suffer from the risk of generating harmful contents especially while…
LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination
Kai Zhang, Yangyang Kang, Fubang Zhao +1
Large Language Models (LLMs), such as GPT3.5, have exhibited remarkable proficiency in comprehending and generating natural language. On the other hand, medical assistants hold the…
PPN: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts
Kaiwen Wei, Jie Yao, Jingyuan Zhang +6
Key Information Extraction (KIE) is a challenging multimodal task that aims to extract structured value semantic entities from visually rich documents. Although significant progres…
RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information Extraction
Chengyuan Liu, Fubang Zhao, Yangyang Kang +5
Universal Information Extraction (UIE) is an area of interest due to the challenges posed by varying targets, heterogeneous structures, and demand-specific schemas. However, previo…
Adjacency List Oriented Relational Fact Extraction via Adaptive Multi-task Learning
Fubang Zhao, Zhuoren Jiang, Yangyang Kang +2
Relational fact extraction aims to extract semantic triplets from unstructured text. In this work, we show that all of the relational fact extraction models can be organized accord…
Technical report on Conversational Question Answering
Ying Ju, Fubang Zhao, Shijie Chen +3
Conversational Question Answering is a challenging task since it requires understanding of conversational history. In this project, we propose a new system RoBERTa + AT +KD, which…