@inproceedings{22827,
  abstract     = {Quantized training of Large Language Models (LLMs) remains an open challenge, as maintaining accuracy while performing all matrix multiplications in low precision has proven difficult. This is particularly the case when fine-tuning pre-trained models, which can have large weight, activation, and error (output gradient) outlier values that make lower-precision optimization difficult. To address this, we present HALO, a new quantization-aware training approach for Transformers that enables accurate and efficient low-precision training by combining 1) strategic placement of Hadamard rotations in both forward and backward passes, which mitigate outliers, 2) high-performance kernel support, and 3) FSDP integration for low-precision communication. Our approach ensures that all large matrix multiplications during the forward and backward passes are executed in lower precision. Applied to LLaMa models, HALO achieves near-full-precision-equivalent results during fine-tuning on various tasks, while delivering up to 1.41x end-to-end speedup for full fine-tuning on RTX 4090 GPUs. HALO efficiently supports both standard and parameter-efficient fine-tuning (PEFT). Our results demonstrate the first practical approach to fully quantized LLM fine-tuning that maintains accuracy in INT8 and FP6 precision, while delivering performance benefits.},
  author       = {Ashkboos, Saleh and Nikdan, Mahdi and Tabesh, Soroush and Lopez Castro, Roberto and Hoefler, Torsten and Alistarh, Dan-Adrian},
  booktitle    = {39th Conference on Neural Information Processing Systems},
  isbn         = {9798331338275},
  issn         = {1049-5258},
  location     = {San Diego, CA, United States},
  pages        = {131755--131780},
  publisher    = {Neural Information Processing Systems Foundation},
  title        = {{HALO: Hadamard-assisted lower-precision optimization for LLMs}},
  doi          = {10.52202/085713-3966},
  volume       = {38},
  year         = {2025},
}

@inproceedings{18117,
  abstract     = {We investigate parameter-efficient fine-tuning (PEFT) methods that can provide good accuracy under limited computational and memory budgets in the context of large language models (LLMs). We present a new PEFT method called Robust Adaptation (RoSA) inspired by robust principal component analysis that jointly trains low-rank
 and highly-sparse components on top of a set of fixed pretrained weights to efficiently approximate the performance of a full-fine-tuning (FFT) solution. Across a series of challenging generative tasks such as grade-school math and SQL query generation, which require fine-tuning for good performance, we show that RoSA outperforms LoRA, pure sparse fine-tuning, and alternative hybrid methods at the same parameter budget, and can even recover the performance of FFT on some tasks. We provide system support for RoSA to complement the training algorithm, specifically in the form of sparse GPU kernels which enable memory- and computationally-efficient training, and show that it is also compatible with low-precision base weights, resulting in the first joint representation combining quantization, low-rank and sparse approximations. Our code is available at https://github.com/IST-DASLab/RoSA.},
  author       = {Nikdan, Mahdi and Tabesh, Soroush and Crncevic, Elvir and Alistarh, Dan-Adrian},
  booktitle    = {Proceedings of the 41st International Conference on Machine Learning},
  issn         = {2640-3498},
  location     = {Vienna, Austria},
  pages        = {38187--38206},
  publisher    = {ML Research Press},
  title        = {{RoSA: Accurate parameter-efficient fine-tuning via robust adaptation}},
  volume       = {235},
  year         = {2024},
}

@unpublished{19063,
  abstract     = {Instruction-tuned Large Language Models (LLMs) show impressive results in numerous practical applications, but they lack essential safety features that are common in other areas of computer science, particularly an explicit separation of instructions and data. This makes them vulnerable to manipulations such as indirect prompt injections and generally unsuitable for safety-critical tasks. Surprisingly, there is currently no established definition or benchmark to quantify this phenomenon. In this work, we close this gap by introducing a formal measure for instruction-data separation and an empirical variant that is calculable from a model's outputs. We also present a new dataset, SEP, that allows estimating the measure for real-world models. Our results on various LLMs show that the problem of instruction-data separation is real: all models fail to achieve high separation, and canonical mitigation techniques, such as prompt engineering and fine-tuning, either fail to substantially improve separation or reduce model utility. The source code and SEP dataset are openly accessible at https://github.com/egozverev/Shold-It-Be-Executed-Or-Processed.
},
  author       = {Zverev, Egor and Abdelnabi, Sahar and Tabesh, Soroush and Fritz, Mario and Lampert, Christoph},
  booktitle    = {arXiv},
  title        = {{Can LLMs separate instructions from data? And what do we even mean by that?}},
  doi          = {10.48550/arXiv.2403.06833},
  year         = {2024},
}