---
title: "Kaixuan Huang — papers of 2024 — Elamur Research"
description: "Kaixuan Huang — papers of 2024: 2 papers on Elamur Research, the most cited first — what each work is about in our own words."
canonical: "https://research.elamur.ai/free/en/authors/kaixuan-huang/year/2024/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/kaixuan-huang/year/2024/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Kaixuan Huang](https://md.research.elamur.ai/free/en/authors/kaixuan-huang/) / 2024

# Kaixuan Huang — papers of 2024 — Elamur Research

2 papers · [all years of Kaixuan Huang](https://md.research.elamur.ai/free/en/authors/kaixuan-huang/#years)

- [SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal arXiv:2406.14598](https://md.research.elamur.ai/free/en/papers/xie-2024-sorry-bench-systematically-evaluating-large/) — Tinghao Xie, Xiangyu Qi, Yi Zeng, et al. · 2024 · 87 citations
- [Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications arXiv:2402.05162](https://md.research.elamur.ai/free/en/papers/wei-2024-assessing-brittleness-safety-alignment-pruning/) — Boyi Wei, Kaixuan Huang, Yangsibo Huang, et al. · 2024 · 66 citations