Purifying Large Language Models by Ensembling a Small Language Model
- URL: http://arxiv.org/abs/2402.14845v1
- Date: Mon, 19 Feb 2024 14:00:39 GMT
- Title: Purifying Large Language Models by Ensembling a Small Language Model
- Authors: Tianlin Li, Qian Liu, Tianyu Pang, Chao Du, Qing Guo, Yang Liu, Min
Lin
- Abstract summary: We propose a simple and easily implementable method for purifying LLMs from the negative effects caused by uncurated data.
We empirically confirm the efficacy of ensembling LLMs with benign and small language models (SLMs)
- Score: 39.57304668057076
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The emerging success of large language models (LLMs) heavily relies on
collecting abundant training data from external (untrusted) sources. Despite
substantial efforts devoted to data cleaning and curation, well-constructed
LLMs have been reported to suffer from copyright infringement, data poisoning,
and/or privacy violations, which would impede practical deployment of LLMs. In
this study, we propose a simple and easily implementable method for purifying
LLMs from the negative effects caused by uncurated data, namely, through
ensembling LLMs with benign and small language models (SLMs). Aside from
theoretical guarantees, we perform comprehensive experiments to empirically
confirm the efficacy of ensembling LLMs with SLMs, which can effectively
preserve the performance of LLMs while mitigating issues such as copyright
infringement, data poisoning, and privacy violations.
Related papers
- Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization [12.885866125783618]
Large Language Models (LLMs) tend to produce inaccurate responses to specific queries.
We construct an adversarial dataset, named as $textbfADT (Adrial dataset for Tokenizer)$ to challenge LLMs' tokenization.
Our empirical results reveal that our ADT is highly effective on challenging the tokenization of leading LLMs, including GPT-4o, Llama-3, Qwen2.5-max and so on.
arXiv Detail & Related papers (2024-05-27T11:39:59Z) - How Much are LLMs Contaminated? A Comprehensive Survey and the LLMSanitize Library [68.10605098856087]
With the rise of Large Language Models (LLMs) in recent years, new opportunities are emerging, but also new challenges, and contamination is quickly becoming critical.
Business applications and fundraising in AI have reached a scale at which a few percentage points gained on popular question-answering benchmarks could translate into dozens of millions of dollars.
It is becoming harder and harder to keep track of the data that LLMs have seen; if not impossible with closed-source models like GPT-4 and Claude-3 not divulging any information on the training set.
arXiv Detail & Related papers (2024-03-31T14:32:02Z) - Unmemorization in Large Language Models via Self-Distillation and
Deliberate Imagination [58.36408867180233]
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.
arXiv Detail & Related papers (2024-02-15T16:21:14Z) - 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) - Breaking the Silence: the Threats of Using LLMs in Software Engineering [12.368546216271382]
Large Language Models (LLMs) have gained considerable traction within the Software Engineering (SE) community.
This paper initiates an open discussion on potential threats to the validity of LLM-based research.
arXiv Detail & Related papers (2023-12-13T11:02:19Z) - Mind's Mirror: Distilling Self-Evaluation Capability and Comprehensive Thinking from Large Language Models [20.28989820878285]
Large language models (LLMs) have achieved remarkable advancements in natural language processing.
The massive scale and computational demands of these models present formidable challenges when considering their practical deployment in resource-constrained environments.
arXiv Detail & Related papers (2023-11-15T18:56:23Z) - Assessing the Reliability of Large Language Model Knowledge [78.38870272050106]
Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks.
How do we evaluate the capabilities of LLMs to consistently produce factually correct answers?
We propose MOdel kNowledge relIabiliTy scORe (MONITOR), a novel metric designed to directly measure LLMs' factual reliability.
arXiv Detail & Related papers (2023-10-15T12:40:30Z) - Survey on Factuality in Large Language Models: Knowledge, Retrieval and
Domain-Specificity [61.54815512469125]
This survey addresses the crucial issue of factuality in Large Language Models (LLMs)
As LLMs find applications across diverse domains, the reliability and accuracy of their outputs become vital.
arXiv Detail & Related papers (2023-10-11T14:18:03Z)
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.