News

TriageSim is now published at Interspeech 2026.

Two papers accepted to the EMNLP 2026 main conference: our survey From Triage to Discharge, and DiaLLM, which investigates the robustness-generation gap in English dialect adaptation.

Retell, Reward, Repeat, on reinforcement learning for narrative theory-informed story retelling, published at INLG 2026.

Preprint: LLMs Anchor on Chief Complaint and Fail to Integrate Evidence in Sequential Clinical Triage is on arXiv.

PAREDA, a multi-accent speech dataset of NLP research discussions, published at SPEAKABLE @ LREC 2026.

Preprint: From Triage to Discharge: A Survey of NLP Tasks, Methods, and Open Challenges in the Emergency Department is now available.

A Taxonomy-Driven Case Study of Australian Web Resources Against Technology-Facilitated Abuse published in the ACISP 2026 proceedings.

TriageSim, a conversational emergency triage simulation framework built from electronic health records, released as a Python package with a project site.

Far Out, which evaluates LMs on slang in Australian and Indian English, accepted to VarDial @ EACL 2026.

Preprint: A Taxonomy-Driven Case Study of Australian Web Resources Against Technology-Facilitated Abuse is on arXiv.

Nek Minit, which uses pragmatic metacognitive prompting for explainable sarcasm detection of Australian and Indian English, accepted to ALTA 2025, with a Best Paper Honorable Mention.

BESSTIE, a benchmark for sentiment and sarcasm across varieties of English, accepted to Findings of ACL 2025. Dataset on HuggingFace.

Started my Ph.D. at the UNSW-NLP group, UNSW Sydney, advised by Aditya Joshi, Padmanesan Narasimhan, and Salil Kanhere.

My paper on low-rank dialect adapters for decoder models is accepted to NAACL 2025 (Short Papers).

My paper on evaluating dialect robustness of LMs via conversation understanding is published at SUMEval @ COLING 2025.

Started as a Research Assistant at the School of Computer Science and Engineering, UNSW Sydney.