Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Dong, Xiangjue"'
Large Language Models (LLMs) can generate biased responses. Yet previous direct probing techniques contain either gender mentions or predefined gender stereotypes, which are challenging to comprehensively collect. Hence, we propose an indirect probin
Externí odkaz:
http://arxiv.org/abs/2402.11190
Autor:
Parashar, Shubham, Lin, Zhiqiu, Liu, Tian, Dong, Xiangjue, Li, Yanan, Ramanan, Deva, Caverlee, James, Kong, Shu
Vision-language models (VLMs) excel in zero-shot recognition but their performance varies greatly across different visual concepts. For example, although CLIP achieves impressive accuracy on ImageNet (60-80%), its performance drops below 10% for more
Externí odkaz:
http://arxiv.org/abs/2401.12425
Language models (LMs) can be manipulated by adversarial attacks, which introduce subtle perturbations to input data. While recent attack methods can achieve a relatively high attack success rate (ASR), we've observed that the generated adversarial ex
Externí odkaz:
http://arxiv.org/abs/2311.08598
Large Language Models (LLMs) can generate biased and toxic responses. Yet most prior work on LLM gender bias evaluation requires predefined gender-related phrases or gender stereotypes, which are challenging to be comprehensively collected and are li
Externí odkaz:
http://arxiv.org/abs/2311.00306
Pre-trained Language Models are widely used in many important real-world applications. However, recent studies show that these models can encode social biases from large pre-training corpora and even amplify biases in downstream applications. To addr
Externí odkaz:
http://arxiv.org/abs/2310.12490
As powerful tools for representation learning on graphs, graph neural networks (GNNs) have played an important role in applications including social networks, recommendation systems, and online web services. However, GNNs have been shown to be vulner
Externí odkaz:
http://arxiv.org/abs/2308.15614
A key component of modern conversational systems is the Dialogue State Tracker (or DST), which models a user's goals and needs. Toward building more robust and reliable DSTs, we introduce a prompt-based learning approach to automatically generate eff
Externí odkaz:
http://arxiv.org/abs/2306.04535
Question Generation (QG) is a fundamental NLP task for many downstream applications. Recent studies on open-book QG, where supportive answer-context pairs are provided to models, have achieved promising progress. However, generating natural questions
Externí odkaz:
http://arxiv.org/abs/2210.06781
Publikováno v:
IEEE Transactions on Knowledge and Data Engineering (2023)
Recent years have witnessed the rapid development of concept map generation techniques due to their advantages in providing well-structured summarization of knowledge from free texts. Traditional unsupervised methods do not generate task-oriented con
Externí odkaz:
http://arxiv.org/abs/2110.15720
Autor:
Finch, Sarah E., Finch, James D., Ahmadvand, Ali, Ingyu, Choi, Dong, Xiangjue, Qi, Ruixiang, Sahijwani, Harshita, Volokhin, Sergey, Wang, Zihan, Wang, Zihao, Choi, Jinho D.
Inspired by studies on the overwhelming presence of experience-sharing in human-human conversations, Emora, the social chatbot developed by Emory University, aims to bring such experience-focused interaction to the current field of conversational AI.
Externí odkaz:
http://arxiv.org/abs/2009.04617