---
title: "Long Phan — papers of 2024 — 4 papers, the most cited first"
description: "Long Phan — papers of 2024: 4 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/long-phan/year/2024/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/long-phan/year/2024/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Long Phan](https://md.research.elamur.ai/free/en/authors/long-phan/) / 2024

# Long Phan — papers of 2024 — 4 papers, the most cited first

4 papers · [all years of Long Phan](https://md.research.elamur.ai/free/en/authors/long-phan/#years)

- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal arXiv:2402.04249](https://md.research.elamur.ai/free/en/papers/mazeika-2024-harmbench-standardized-evaluation-framework-automated/) — Mantas Mazeika, Long Phan, Xuwang Yin, et al. · 2024 · 330 citations
- [The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning arXiv:2403.03218](https://md.research.elamur.ai/free/en/papers/li-2024-wmdp-benchmark-measuring-reducing-malicious/) — Nathaniel Li, Alexander Pan, Anjali Gopal, et al. · 2024 · 127 citations

**[Improving Alignment and Robustness with Circuit Breakers](https://md.research.elamur.ai/free/en/papers/zou-2024-improving-alignment-robustness-circuit-breakers/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Andy Zou, Long Phan, Justin Wang, et al.*2024 · 83 citations*

- [Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation arXiv:2402.14874](https://md.research.elamur.ai/free/en/papers/phan-2024-distillation-contrastive-decoding-improving-llms/) — Phuc Phan, Hieu Tran, Long Phan · 2024 · 7 citations