Sarvnaz Karimi

Artificial intelligence for science – Adoption trends and future development pathways.

Stefan Hajkowicz, Claire Naughtin, Conrad Sanderson, Emma Schleiger et autres

The Second Workshop on Evaluation of Multimodal Generation

Wei Emma Zhang, Xiang Dai, Sarvnaz Karimi, Desmond Elliott et autres

Multimodal generation and retrieval systems are increasingly central to modern information retrieval, powering retrieval-augmented generation (RAG), multimodal search, recommendation, and knowledge intensive applications. Despite rapid progress in multimodal large language models (MLLMs), robust and principled evaluation of multimodal generation and retrieval remains …

au, dk, us (code pays fourni par la source)

RegionSLM: Region-aware Question Answering on Document Screenshots

Chao Wang, Hehe Fan, Huichen Yang, Sarvnaz Karimi et autres

Real-world document question-answering that relies on screenshots, such as bills and forms, requires evidence that is often spatially localised and visually cluttered. However, most Screenshot Language Models (SLMs) encode the entire page holistically and rely on implicit attention to ''find'' relevant content, …

au, cn (code pays fourni par la source)

Natural language processing methods to classify unplanned returns following dental extractions

Farhana Pethani, Jonathan K. Kummerfeld, Albert Yaacoub, Xiang Dai et autres

Information about the reasons why patients return after a dental extraction could be used in quality-of-care indicators in dentistry, but these reasons are typically not recorded in a structured form in dental records. Our aim was to determine whether information in dental …

au (code pays fourni par la source)

CT-bias: a Dataset for Auditing the Impact of Patients' Sensitive Information on Clinical Trial Matching

Maciej Rybinski, Aditya Joshi, Sarvnaz Karimi, Nathan Inkiriwang

Medical advances are rooted in insights gathered from clinical trials. Technology plays an increasing role in the clinical trial recruitment: patients can use specialised platforms to search for clinical trials, and clinical trials recruiters search through patient records to find eligible patients. …

au, es (code pays fourni par la source)

CT-bias: a Dataset for Auditing the Impact of Patients' Sensitive Information on Clinical Trial Matching

Maciej Rybinski, Aditya Joshi, Sarvnaz Karimi, Nathan Inkiriwang

Medical advances are rooted in insights gathered from clinical trials. Technology plays an increasing role in the clinical trial recruitment: patients can use specialised platforms to search for clinical trials, and clinical trials recruiters search through patient records to find eligible patients. …

au, es (code pays fourni par la source)

CTcl – Cross-Lingual Clinical Trial Matching dataset

Maciej Rybinski, Necva Bölücü, Georgios Peikos, Aditya Joshi et autres

The success of clinical trials depends on the recruitment of patients who match strict inclusion criteria. The development of effective patient to clinical trial matching systems depends on benchmarking datasets that support systematic evaluation. Apart from resources that are created in English …

au, es, pl, it, tr (code pays fourni par la source)

CTcl – Cross-Lingual Clinical Trial Matching dataset

Maciej Rybinski, Necva Bölücü, Georgios Peikos, Aditya Joshi et autres

The success of clinical trials depends on the recruitment of patients who match strict inclusion criteria. The development of effective patient to clinical trial matching systems depends on benchmarking datasets that support systematic evaluation. Apart from resources that are created in English …

au, es, pl, it, tr (code pays fourni par la source)

Predicting patient returns due to complications and recommending follow-up appointments after a dental extraction using machine learning

Farhana Pethani, Jonathan K. Kummerfeld, Xiang Dai, Dr Mike Conway et autres

After a dental extraction, knowing which patients are at higher risk of return due to complications may help plan a better treatment approach and lead to targeted follow-up appointments. The objective of this study was to predict which patients are at higher …

au (code pays fourni par la source)

CSIRO-LT at SemEval-2026 Task 2: In-the-Wild Valence and Arousal Forecasting on Ecological Text Time Series

Jiyu Chen, Necva Bölücü, Sarvnaz Karimi, Diego Mollá et autres

Predicting emotional valence and arousal in text is challenging due to the continuous, dynamic, and context-dependent nature of emotions.The SemEval 2026 Task 2: Predicting Variation in Emotional Valence and Arousal over Time from Ecological Essays shared task investigates longitudinal affect prediction from …

au (code pays fourni par la source)

CAIRNS: Balancing Readability and Scientific Accuracy in Climate Adaptation Question Answering

Aditya A. Joshi, Sarvnaz Karimi

Climate adaptation strategies are proposed in response to climate change. They are practised in agriculture to sustain food production. These strategies can be found in unstructured data (for example, scientific literature from the Elsevier website) or structured (heterogeneous climate data via government …

To Labor is Not to Suffer: Exploration of Polarity Association Bias in LLMs for Sentiment Analysis

Association for Computational Linguistics 2025, Jiyu Chen, Sarvnaz Karimi, Diego Mollá et autres

Large language models (LLMs) are widely used for modeling sentiment trends on social media text. We examine whether LLMs have a polarity association bias---positive or negative---when encountering specific types of lexical word mentions. Such polarity association bias could lead to the wrong …

au (code pays fourni par la source)