Research

Publications

Peer-reviewed papers and manuscripts in progress. My name is highlighted in author lists; it also appears as Amireza Vishte in some publication records. Longer research write-ups live on the blog.

Google Scholar

2025

Workshop2025

Psychological Health Chatbot, Detecting and Assisting Patients in their Path to Recovery

Sadegh Jafari, Mohammad Erfan Zare, Amireza Vishte, Mirzae Melike, Zahra Amiri, Sima Mohammadparast, Sauleh Eetemadi

Proceedings of the 1st Workshop on NLP for Languages Using Arabic Script (AbjadNLP @ COLING 2025), pp. 64–77, ACL

A Persian-language mental-health chatbot that detects signs of psychological distress and supports users on their path to recovery, built on transformer-based NLP with a dedicated data-collection, training, and evaluation pipeline.

View publication PDF

In progress2025

The Sentinel's Dilemma: Guarding AI from Hidden Threats

Amirreza Vishteh

Survey manuscript — backdoor attacks and defenses for large language models

A survey mapping how hidden triggers are implanted into LLMs during training and fine-tuning, what attackers can achieve with them, and the detection and defense strategies emerging in response.

View publication