arXiv Computation and Language September 3, 2026 By Kaixuan Wang, Chenxin Diao, Jason T. Jacques, Zhongliang Guo, Shuai Zhao

HarmReduction: Benchmarking LLMs in Harm Reduction Information Provision to Support People Who Use Drugs

Read the original on arXiv Computation and Language →

The paper introduces HarmReduction, a benchmark for evaluating large language models (LLMs) on their ability to provide accurate and safe harm reduction information to people who use drugs (PWUD). The benchmark, HR-Basic, contains 2,160 question‑answer‑evidence pairs covering safety boundary checks, quantitative value provision, and polysubstance risk inference. Experiments show that even state‑of‑the‑art LLMs struggle with accuracy and can pose severe safety risks, underscoring the need for a dedicated evaluation framework.

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 Computation and Language.

arXiv Machine Learning

Aug 26

MPIB: A Benchmark for Medical Prompt Injection Attacks and Clinical Safety in LLMs

arXiv:2602.06268v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly integrated into clinical workflows. However, p...

By Junhyeok Lee, Han Jang, Kyu Sung Choi

llms rag multimodal benchmarks safety

arXiv AI

Jun 30

When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries

arXiv:2606. 28332v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for medical and health-related questions, yet their safety in high-risk medical scenarios remains poorly understood.

By Yige Li, Jun Sun, Wei Zhao, Zhe Li, Yutao Wu, Hanxun Huang, Xiang Zheng, Xingjun Ma

llms fine-tuning benchmarks safety

arXiv AI

Jun 17

First, do NOHARM: towards clinically safe large language models

arXiv:2512. 01241v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain poorly characterized.

By David Wu, Fateme Nateghi Haredasht, Saloni Kumar Maharaj, Priyank Jain, Jessica Tran, Matthew Gwiazdon, Arjun Rustagi, Jenelle Jindal, Jacob M. Koshy, Vinay Kadiyala, Anup Agarwal, Bassman Tappuni, Brianna French, Sirus Jesudasen, Christopher V. Cosgriff, Rebanta Chakraborty, Jillian Caldwell, Susan Ziolkowski, David J. Iberri, Robert Diep, Rahul S. Dalal, Kira L. Newman, Kristin Galetta, J. Carl Pallais, Nancy Wei, Kathleen M. Buchheit, David I. Hong, Vartan Pahalyants, Ernest Y. Lee, Allen Shih, Tamara B. Kaplan, Vishnu Ravi, Sarita Khemani, Thomas A. Buckley, April S. Liang, Daniel Shirvani, Advait Patil, Nicholas Marshall, Kanav Chopra, Joel Koh, Adi Badhwar, Anastasia Perez, Austin J. Schoeffler, Mahbuba Tusty, Chase M. Walton, Liam G. McCoy, David J. H. Wu, Yingjie Weng, Sumant Ranji, Kevin Schulman, Nigam H. Shah, Jason Hom, Arnold Milstein, Arjun K. Manrai, Adam Rodman, Jonathan H. Chen, Ethan Goh

llms benchmarks safety

arXiv AI

Jul 22

SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring

arXiv:2607. 18665v1 Announce Type: new Abstract: Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance.

By Chunxiao Li, Yuan Xiong, Lijun Li, Tianyi Du, Wenlong Zhang, Lei Bai, Jing Shao

llms rag agents benchmarks safety

arXiv AI

Oct 26

DeepSafe-SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring

DeepSafe‑SciHazard introduces a real‑world‑grounded benchmark for measuring scientific safety risks, comprising 2,400 hazardous and 600 oversafety questions across 12 disciplines. It defines a decomposed harm scoring system, DeHarm‑Score, that evaluates query severity, refusal behavior, and response‑level risk, further breaking down harm into executability and net‑new risk. An expert‑validation study shows DeHarm‑Score aligns 90.17% better with expert judgments than the best baseline, and the benchmark reveals that deep research agents score 32.3% higher on mean DeHarm‑Score than standard LLMs, highlighting a critical blind spot in current safety defenses.

By Chunxiao Li, Yuan Xiong, Lijun Li, Tianyi Du, Wenlong Zhang, Lei Bai, Jing Shao

llms rag agents benchmarks safety

Hugging Face Trending Papers

Jul 21

SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring

Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance. Existing benchmarks often rely on templated queries disconnected from real-world hazards, and employ LLM-as-a-Judge paradigms without domain grounding.

llms rag agents benchmarks safety

One email a morning, machine-written

Related stories

MPIB: A Benchmark for Medical Prompt Injection Attacks and Clinical Safety in LLMs

When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries

First, do NOHARM: towards clinically safe large language models

SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring

DeepSafe-SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring

SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring