Differentially Private Decoding in Large Language Models
- URL: http://arxiv.org/abs/2205.13621v1
- Date: Thu, 26 May 2022 20:50:58 GMT
- Title: Differentially Private Decoding in Large Language Models
- Authors: Jimit Majmudar, Christophe Dupuy, Charith Peris, Sami Smaili, Rahul
Gupta, Richard Zemel
- Abstract summary: We propose a simple, easy to interpret, and computationally lightweight perturbation mechanism to be applied to an already trained model at the decoding stage.
Our perturbation mechanism is model-agnostic and can be used in conjunction with any Large Language Model.
- Score: 14.221692239892207
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recent large-scale natural language processing (NLP) systems use a
pre-trained Large Language Model (LLM) on massive and diverse corpora as a
headstart. In practice, the pre-trained model is adapted to a wide array of
tasks via fine-tuning on task-specific datasets. LLMs, while effective, have
been shown to memorize instances of training data thereby potentially revealing
private information processed during pre-training. The potential leakage might
further propagate to the downstream tasks for which LLMs are fine-tuned. On the
other hand, privacy-preserving algorithms usually involve retraining from
scratch, which is prohibitively expensive for LLMs. In this work, we propose a
simple, easy to interpret, and computationally lightweight perturbation
mechanism to be applied to an already trained model at the decoding stage. Our
perturbation mechanism is model-agnostic and can be used in conjunction with
any LLM. We provide theoretical analysis showing that the proposed mechanism is
differentially private, and experimental results showing a privacy-utility
trade-off.
Related papers
- zsLLMCode: An Effective Approach for Functional Code Embedding via LLM with Zero-Shot Learning [6.976968804436321]
Large language models (LLMs) have the capability of zero-shot learning, which does not require training or fine-tuning.
We propose zsLLMCode, a novel approach that generates functional code embeddings using LLMs.
arXiv Detail & Related papers (2024-09-23T01:03:15Z) - SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts.
We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM.
We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
arXiv Detail & Related papers (2024-07-16T04:41:58Z) - Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression [40.4998607679863]
Large Language Models (LLMs) often suffer from catastrophic forgetting when post-pretrained or supervised fine-tuned (SFT) on domain-specific data.
This paper focuses on TG-SFT, which can synthetically generate SFT data for the instruction tuning steps.
arXiv Detail & Related papers (2024-06-17T09:17:40Z) - Verbalized Machine Learning: Revisiting Machine Learning with Language Models [63.10391314749408]
We introduce the framework of verbalized machine learning (VML)
VML constrains the parameter space to be human-interpretable natural language.
We empirically verify the effectiveness of VML, and hope that VML can serve as a stepping stone to stronger interpretability.
arXiv Detail & Related papers (2024-06-06T17:59:56Z) - AXOLOTL: Fairness through Assisted Self-Debiasing of Large Language
Model Outputs [20.772266479533776]
AXOLOTL is a novel post-processing framework that operates agnostically across tasks and models.
It identifies biases, proposes resolutions, and guides the model to self-debias its outputs.
This approach minimizes computational costs and preserves model performance.
arXiv Detail & Related papers (2024-03-01T00:02:37Z) - Characterizing Truthfulness in Large Language Model Generations with
Local Intrinsic Dimension [63.330262740414646]
We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs)
We suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations.
arXiv Detail & Related papers (2024-02-28T04:56:21Z) - Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models [52.98743860365194]
We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN)
At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself.
This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents.
arXiv Detail & Related papers (2024-01-02T18:53:13Z) - Evaluating and Explaining Large Language Models for Code Using Syntactic
Structures [74.93762031957883]
This paper introduces ASTxplainer, an explainability method specific to Large Language Models for code.
At its core, ASTxplainer provides an automated method for aligning token predictions with AST nodes.
We perform an empirical evaluation on 12 popular LLMs for code using a curated dataset of the most popular GitHub projects.
arXiv Detail & Related papers (2023-08-07T18:50:57Z) - LLM-Pruner: On the Structural Pruning of Large Language Models [65.02607075556742]
Large language models (LLMs) have shown remarkable capabilities in language understanding and generation.
We tackle the compression of LLMs within the bound of two constraints: being task-agnostic and minimizing the reliance on the original training dataset.
Our method, named LLM-Pruner, adopts structural pruning that selectively removes non-critical coupled structures.
arXiv Detail & Related papers (2023-05-19T12:10:53Z) - Privately Fine-Tuning Large Language Models with Differential Privacy [10.485556506301549]
Pre-trained Large Language Models (LLMs) are an integral part of modern AI that have led to breakthrough performances in complex AI tasks.
Differential privacy (DP) provides a rigorous framework that allows adding noise in the process of training or fine-tuning LLMs.
We present ewtune, a DP framework for fine-tuning LLMs based on Edgeworth accountant with finite-sample privacy guarantees.
arXiv Detail & Related papers (2022-10-26T21:18:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.