arXiv AI September 2, 2026 By Linhai Ma, Rita El Hachem, Mahatab El Hajj, Lilian Ghandour, Samah Fodeh

Assessing Suicide Risk in Arabic Crisis Helpline Calls: A Comparison of Arabic and English Large Language Models

The study evaluates large language models for assessing suicide risk in Arabic crisis helpline calls, comparing Arabic and English models. Using de‑identified transcripts from Lebanon’s National Lifeline, the researchers fine‑tuned instruction‑tuned LLMs and transformer encoders, achieving a macro‑F1 of 81.19 and ROC‑AUC of 90.61 for high‑risk calls in Arabic, and 85.00/92.59 in English. The results show that high‑risk calls are more distinguishable than at‑risk calls, and translating to English does not degrade performance, indicating potential for operator‑facing tools.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

MIT News AI

Sep 24

Estimating suicide risk from text

A new language‑processing tool has been developed to estimate suicide risk from natural language. By analyzing text, the tool can identify individuals at the highest risk. This capability could enable faster and more targeted interventions.

By Jennifer Michalowski | McGovern Institute for Brain Research

arXiv Computation and Language

Oct 12

DistressBench: Evaluating Multi-Dimensional Crisis Support in Large Language Models

The paper introduces DistressBench, a benchmark comprising 718 English clinician-authored conversations covering 23 self-harm subcategories, each evaluated against a weighted rubric across seven crisis-support dimensions. Models are scored by the fraction of criteria they satisfy, revealing that the best models meet 88.4% of weighted criteria while clinicians achieve 98.7%. The study highlights gaps in crisis response, notably that 35.3% of conversations where crisis is recognized fail to route users to human help, underscoring the need to evaluate models on supportive care rather than mere refusal.

By Drew Rein, Patrick Oathout, Vishal Kumar, Udari Madhushani Sehwag

llms benchmarks safety

arXiv Computation and Language

Sep 1

ArabicDialectSafety: A Dialect-Aware Benchmark for Arabic Content Safety Classification

arXiv:2608.01291v2 Announce Type: replace Abstract: We present ArabicDialectSafety, a human-curated Arabic safety dataset of 25,071 prompts covering six Arabic varieties: Modern Standard Arabic, Syri...

By Wajdi Zaghouani, Md. Rafiul Biswas, Kholoud Khalil Aldous, Mabrouka Bessghaier

llms fine-tuning benchmarks safety

arXiv AI

Sep 30

SalamahBench: Dialect and Category Level Safety Evaluation of Arabic Language Models

arXiv:2603.04410v3 Announce Type: replace-cross Abstract: While different stakeholders are trying to leverage Arabic Language Models (ALMs), safety alignment in ALMs remains largely underexplored, hi...

By Omar Abdelnasser, Fatemah Alharbi, Khaled Khasawneh, Ihsen Alouani, Mohammed E. Fouda

llms nlp benchmarks safety

arXiv AI

Aug 25

Redteaming Leading Arabic LLMs with ASAS

arXiv:2608.21985v1 Announce Type: new Abstract: As the adoption of large language models (LLMs) grows in Arabic-speaking regions, ensuring their safety and cultural alignment is increasingly critical...

By Fidaa Abed, Haidar Khan, M Saiful Bari, Babar Khan, Abdalghani Abujabal

llms benchmarks safety

arXiv Machine Learning

Oct 3

Explainable Suicide Risk Assessment on Social Media with Multi-Task QLoRA

The paper presents a system for the IEEE BigData 2026 Cup on Explainable Suicide Risk Assessment on Social Media. It tackles three tasks—risk-level classification, evidence phrase extraction, and multi-label factor identification—using Qwen2.5-Instruct models adapted with quantized low-rank adaptation (QLoRA) and an answer-masked causal language-model objective. The final system achieved a composite score of 0.7738, with 0.8089 on Task 1 and 0.6919 on Task 2, demonstrating that task‑specific training and tailored aggregation improve performance across the three tasks.

By Xuan Zhong Feng, Geoffrey Martin, Hexin Dong, Yifan Peng

fine-tuning efficiency benchmarks