94 citations · 230 across the 14 of their papers we have counts for
15 papers
Improving Alignment and Robustness with Circuit Breakers
Andy Zou, Long Phan, Justin Wang +7
AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interr…
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Nathaniel Li, Alexander Pan, Anjali Gopal +54
The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and che…
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Mantas Mazeika, Long Phan, Xuwang Yin +9
Automated red teaming holds substantial promise for uncovering and mitigating the risks associated with the malicious use of large language models (LLMs), yet the field lacks a sta…
Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation
Phuc Phan, Hieu Tran, Long Phan
We propose a straightforward approach called Distillation Contrastive Decoding (DCD) to enhance the reasoning capabilities of Large Language Models (LLMs) during inference. In cont…
Representation Engineering: A Top-Down Approach to AI Transparency
Andy Zou, Long Phan, Sarah Chen +18
In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights f…
Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages
Zheng-Xin Yong, Ruochen Zhang, Jessica Zosa Forde +12
While code-mixing is a common linguistic practice in many parts of the world, collecting high-quality and low-cost code-mixed data remains a challenge for natural language processi…
MTet: Multi-domain Translation for English and Vietnamese
Chinh Ngo, Trieu H. Trinh, Long Phan +5
We introduce MTet, the largest publicly available parallel corpus for English-Vietnamese translation. MTet consists of 4.2M high-quality training sentence pairs and a multi-domain…
Enriching Biomedical Knowledge for Low-resource Language Through Large-Scale Translation
Long Phan, Tai Dang, Hieu Tran +4
Biomedical data and benchmarks are highly valuable yet very limited in low-resource languages other than English such as Vietnamese. In this paper, we make use of a state-of-the-ar…
ViT5: Pretrained Text-to-Text Transformer for Vietnamese Language Generation
Long Phan, Hieu Tran, Hieu Nguyen +1
We present ViT5, a pretrained Transformer-based encoder-decoder model for the Vietnamese language. With T5-style self-supervised pretraining, ViT5 is trained on a large corpus of h…
VieSum: How Robust Are Transformer-based Models on Vietnamese Summarization?
Hieu Nguyen, Long Phan, James Anibal +2
Text summarization is a challenging task within natural language processing that involves text generation from lengthy input sequences. While this task has been widely studied in E…
SPBERT: An Efficient Pre-training BERT on SPARQL Queries for Question Answering over Knowledge Graphs
Hieu Tran, Long Phan, James Anibal +2
In this paper, we propose SPBERT, a transformer-based language model pre-trained on massive SPARQL query logs. By incorporating masked language modeling objectives and the word str…
CoTexT: Multi-task Learning with Code-Text Transformer
Long Phan, Hieu Tran, Daniel Le +4
We present CoTexT, a pre-trained, transformer-based encoder-decoder model that learns the representative context between natural language (NL) and programming language (PL). Using…
SciFive: a text-to-text transformer model for biomedical literature
Long N. Phan, James T. Anibal, Hieu Tran +4
In this report, we introduce SciFive, a domain-specific T5 model that has been pre-trained on large biomedical corpora. Our model outperforms the current SOTA methods (i.e. BERT, B…
Hierarchical Transformer Encoders for Vietnamese Spelling Correction
Hieu Tran, Cuong V. Dinh, Long Phan +1
In this paper, we propose a Hierarchical Transformer model for Vietnamese spelling correction problem. The model consists of multiple Transformer encoders and utilizes both charact…
Leveraging Transfer Learning for Reliable Intelligence Identification on Vietnamese SNSs (ReINTEL)
Trung-Hieu Tran, Long Phan, Truong-Son Nguyen +1
This paper proposed several transformer-based approaches for Reliable Intelligence Identification on Vietnamese social network sites at VLSP 2020 evaluation campaign. We exploit bo…