activity
20232026
most citedImproving Alignment and Robustness with Circuit Breakers

7 citations · 10 across the 5 of their papers we have counts for

collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2025

Jailbreak Distillation: Renewable Safety Benchmarking

Jingyu Zhang, Ahmed Elgohary, Xiawei Wang +5

Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a no…

cs.CL2024

Does Refusal Training in LLMs Generalize to the Past Tense?

Maksym Andriushchenko, Nicolas Flammarion

Refusal training is widely used to prevent LLMs from generating harmful, undesirable, or illegal outputs. We reveal a curious generalization gap in the current refusal training app…

cs.CL2024

Is In-Context Learning Sufficient for Instruction Following in LLMs?

Hao Zhao, Maksym Andriushchenko, Francesco Croce +1

In-context learning (ICL) allows LLMs to learn from examples without changing their weights: this is a particularly promising capability for long-context LLMs that can potentially…

cs.CL2024

Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs

Javier Rando, Francesco Croce, Kryštof Mitka +4

Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work ha…

cs.CL2024

Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning

Hao Zhao, Maksym Andriushchenko, Francesco Croce +1

There is a consensus that instruction fine-tuning of LLMs requires high-quality data, but what are they? LIMA (NeurIPS 2023) and AlpaGasus (ICLR 2024) are state-of-the-art methods…