HTTP/2 200 content-type: text/html date: Tue, 30 Dec 2025 22:40:50 GMT last-modified: Sat, 27 Dec 2025 22:44:09 GMT content-encoding: gzip x-amz-server-side-encryption: AES256 x-amz-version-id: GbKOdspY8yguAC8JvtT5ZptEaj7UqAbD server: AmazonS3 etag: W/"6acf80c7574238d4bc9fa5569a4f01de" vary: accept-encoding x-cache: Miss from cloudfront via: 1.1 345f496d00ae1b7643706de6cdfc0808.cloudfront.net (CloudFront) x-amz-cf-pop: BOM78-P5 x-amz-cf-id: ynk7q7AuuC2hCyXzf_pZlrYTZMIgkt18ty9VyZX4PrHxZLb8-Cj4pQ==

Xiang Dai (戴翔)

[CV-full]     [CV-1 page]     [Publications]

I am currently a research scientist at CSIRO Data61. Previously, I received my PhD degree at University of Sydney under the supervision of Sarvnaz Karimi, Ben Hachey, and Cecile Paris. After that, I was a Postdoc at University of Copenhagen, working with Desmond Elliott.

My research interests lie in natural language processing and digital health. Some topics I focus on include:

• extracting entities and their relations from raw text [ACL 19, 20, COLING 20, AACL 23, IPM 24];
• pre-training domain-specific language representation models [NAACL 19; EMNLP 20, 21];
• evaluating outputs of generative models, including LLMs [ACL 24; EMNLP 24a, 24b];
• applying NLP techniques to the medical domain [JMIR 21; CIKM 21; TOCHI 23; JBI 24].

Additionally, I have worked on topics such as long document processing [EMNLP 22], multilingual NLP [EACL 23], and multimodal learning [ACL 25; EMNLP 25].

News

• 2025-08: Sim's paper 'The More, The Better? A Critical Study of Multimodal Context in Radiology Report Summarization' was accepted to Findings of EMNLP 2025.
• 2025-07: We are organizing a shared task at ALTA 2025, focusing on normalizing adverse drug event descriptions in social media posts to MedDRA.
• 2025-06: I received an Early Career Researcher Award from the Analytics and Decision Sciences program at Data61.
• 2025-05: I gave a guest lecture at Macquarie University on domain-specific VLMs.
• 2025-05: Sim's paper 'Can VLMs Actually See and Read? A Survey on Modality Collapse in Vision-Language Models' was accepted to Findings of ACL 2025.
• 2025-04: I gave a guest lecture at the University of New South Wales on active adverse event surveillance.
• 2025-01: I became a member of the ALTA (Australasian Language Technology Association) executive committee for 2025-2026.
• 2024-11: Our paper 'MultiADE: A Multi-domain Benchmark for Adverse Drug Event Extraction' was accepted to Journal of Biomedical Informatics.
• 2024-09: Two papers were accepted to Findings of EMNLP 2024: 'A Critical Look at Meta-evaluating Summarization Evaluation Metrics' and 'Understanding Faithfulness and Reasoning of Large Language Models on Plain Biomedical Summaries'.
• 2024-07: Necva's paper 'An Adaptive Approach to Noisy Annotations in Scientific Information Extraction' was accepted to Information Processing and Management.
• (more)

Email

dai (dot) xiang (dot) au (at) gmail.com

dai (dot) dai (at) csiro.au

Calendar

Also, you can find me from , Google scholar, Semantic scholar and WeChat.

I look like this.