Unmemorization in Large Language Models via Self-Distillation and
Deliberate Imagination
- URL: http://arxiv.org/abs/2402.10052v1
- Date: Thu, 15 Feb 2024 16:21:14 GMT
- Title: Unmemorization in Large Language Models via Self-Distillation and
Deliberate Imagination
- Authors: Yijiang River Dong, Hongzhou Lin, Mikhail Belkin, Ramon Huerta, Ivan
Vuli\'c
- Abstract summary: Large Language Models (LLMs) struggle with crucial issues of privacy violation and unwanted exposure of sensitive data.
We introduce a novel approach termed deliberate imagination in the context of LLM unlearning.
Our results demonstrate the usefulness of this approach across different models and sizes, and also with parameter-efficient fine-tuning.
- Score: 58.36408867180233
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: While displaying impressive generation capabilities across many tasks, Large
Language Models (LLMs) still struggle with crucial issues of privacy violation
and unwanted exposure of sensitive data. This raises an essential question: how
should we prevent such undesired behavior of LLMs while maintaining their
strong generation and natural language understanding (NLU) capabilities? In
this work, we introduce a novel approach termed deliberate imagination in the
context of LLM unlearning. Instead of trying to forget memorized data, we
employ a self-distillation framework, guiding LLMs to deliberately imagine
alternative scenarios. As demonstrated in a wide range of experiments, the
proposed method not only effectively unlearns targeted text but also preserves
the LLMs' capabilities in open-ended generation tasks as well as in NLU tasks.
Our results demonstrate the usefulness of this approach across different models
and sizes, and also with parameter-efficient fine-tuning, offering a novel
pathway to addressing the challenges with private and sensitive data in LLM
applications.
Related papers
- 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) - SNAP: Unlearning Selective Knowledge in Large Language Models with Negative Instructions [37.172662930947446]
Instruction-following large language models (LLMs) inadvertently disclose personal or copyrighted information.
We propose SNAP, an innovative framework designed to selectively unlearn information.
We evaluate our framework on various NLP benchmarks and demonstrate that our approach retains the original LLM capabilities.
arXiv Detail & Related papers (2024-06-18T06:54:05Z) - Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing [56.75702900542643]
We introduce AlphaLLM for the self-improvements of Large Language Models.
It integrates Monte Carlo Tree Search (MCTS) with LLMs to establish a self-improving loop.
Our experimental results show that AlphaLLM significantly enhances the performance of LLMs without additional annotations.
arXiv Detail & Related papers (2024-04-18T15:21:34Z) - Machine Unlearning in Large Language Models [8.14992136443131]
This paper introduces a novel machine unlearning framework into large language models.
Our objectives are to make LLMs not produce harmful, hallucinatory, or privacy-compromising responses.
Experimental results show that our approach effectively meets unlearning objectives without substantially compromising model performance.
arXiv Detail & Related papers (2024-02-03T05:14:56Z) - Rethinking Interpretability in the Era of Large Language Models [76.1947554386879]
Large language models (LLMs) have demonstrated remarkable capabilities across a wide array of tasks.
The capability to explain in natural language allows LLMs to expand the scale and complexity of patterns that can be given to a human.
These new capabilities raise new challenges, such as hallucinated explanations and immense computational costs.
arXiv Detail & Related papers (2024-01-30T17:38:54Z) - Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering.
The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored.
We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
arXiv Detail & Related papers (2023-12-26T07:24:46Z) - Mutual Enhancement of Large and Small Language Models with Cross-Silo
Knowledge Transfer [27.63746419563747]
Large language models (LLMs) are empowered with broad knowledge, but their task-specific performance is often suboptimal.
It necessitates fine-tuning LLMs with task-specific data, but such data may be inaccessible due to privacy concerns.
We propose a novel approach to enhance LLMs with smaller language models (SLMs) that are trained on clients using their private task-specific data.
arXiv Detail & Related papers (2023-12-10T09:52:32Z) - Check Your Facts and Try Again: Improving Large Language Models with
External Knowledge and Automated Feedback [127.75419038610455]
Large language models (LLMs) are able to generate human-like, fluent responses for many downstream tasks.
This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules.
arXiv Detail & Related papers (2023-02-24T18:48:43Z)
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.