Muhao Chen

Multi-view Knowledge Graph Embedding for Entity Alignment

2019 · arXiv (Cornell University)

We study the problem of embedding-based entity alignment between knowledge graphs (KGs). Previous works mainly focus on the relational structure of entities. Some further incorporate another type of features, such as attributes, for refinement. However, …

Examining Gender Bias in Languages with Grammatical Gender

2019 · arXiv (Cornell University)

Recent studies have shown that word embeddings exhibit gender bias inherited from the training corpora. However, most studies to date have focused on quantifying and mitigating such bias only in English. These analyses cannot be …

Analogous Process Structure Induction for Sub-event Sequence Prediction

2020 · arXiv (Cornell University)

Computational and cognitive studies of event understanding suggest that identifying, comprehending, and predicting events depend on having structured representations of a sequence of events and on conceptualizing (abstracting) its components into (soft) event categories. Thus, …

Contrastive Out-of-Distribution Detection for Pretrained Transformers

2021 · arXiv (Cornell University)

Pretrained Transformers achieve remarkable performance when training and test data are from the same distribution. However, in real-world scenarios, the model often faces out-of-distribution (OOD) instances that can cause severe semantic shift problems at inference …

Improving Factuality of Abstractive Summarization without Sacrificing Summary Quality

2023 · arXiv (Cornell University)

Improving factual consistency of abstractive summarization has been a widely studied topic. However, most of the prior works on training factuality-aware models have ignored the negative effect it has on summary quality. We propose EFACTSUM …

Primacy Effect of ChatGPT

2023

Instruction-tuned large language models (LLMs), such as ChatGPT, have led to promising zero-shot performance in discriminative natural language understanding (NLU) tasks. This involves querying the LLM using a prompt containing the question, and the candidate …

Vulnerability of Large Language Models to Output Prefix Jailbreaks: Impact of Positions on Safety

2024

Previous research on jailbreak attacks has mainly focused on optimizing the adversarial snippet content injected into input prompts to expose LLM security vulnerabilities. A significant portion of this research focuses on developing more complex, less …

Joint Constrained Learning for Event-Event Relation Extraction

2020

Understanding natural language involves recognizing how multiple event mentions structurally and temporally interact with each other. In this process, one can induce event complexes that organize multi-granular events with temporal order and membership relations interweaving …