Nan Du

On the Generation of Medical Question-Answer Pairs

2018 · arXiv (Cornell University)

Question answering (QA) has achieved promising progress recently. However, answering a question in real-world scenarios like the medical domain is still challenging, due to the requirement of external knowledge and the insufficient quantity of high-quality …

R2D2: Relational Text Decoding with Transformers

2021 · arXiv (Cornell University)

We propose a novel framework for modeling the interaction between graphical structures and the natural language text associated with their nodes and edges. Existing approaches typically fall into two categories. On group ignores the relational …

Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers

2024

Although dominant in natural language processing, transformer-based models still struggle with long-sequence processing, due to the computational costs of their self-attention operations, which increase exponentially as the length of the input sequence grows.To address this …

ToolExpNet: Optimizing Multi-Tool Selection in LLMs with Similarity and Dependency-Aware Experience Networks

2025

Tool learning enhances Large Language Models' (LLMs) dynamic interaction with external tools, improving their ability to solve complex problems.However, current empirical methods, which primarily focus on isolated tools learning, still struggle with accurate multi-tool selection …

Joint Slot Filling and Intent Detection via Capsule Neural Networks

2019

Being able to recognize words as slots and detect the intent of an utterance has been a keen issue in natural language understanding. The existing works either treat slot filling and intent detection separately in …

PaLM: Scaling Language Modeling with Pathways

2022 · arXiv (Cornell University)

Large language models have been shown to achieve remarkable performance across a variety of natural language tasks using few-shot learning, which drastically reduces the number of task-specific training examples needed to adapt the model to …

Distributing Accountability, Not Capability: Phase Separation and the LLM Workflow Quadrant in Autonomous AI Agent Architectures

2022 · arXiv (Cornell University)

Autonomous AI agents in business deployments exhibit a recurring failure mode: when an incident occurs, responsibility cannot be redirected to a separable contributor. The dominant discourse treats this as a single phenomenon, addressed by sandboxing, …