Fine-tuning pre-trained language models, particularly large language models,
demands extensive computing resources and can result in varying performance
outcomes across different domains and datasets. This paper examines the
approach of integrating multiple models from diverse training scenarios into a
unified model. This unified model excels across various data domains and
exhibits the ability to generalize well on out-of-domain data. We propose a
knowledge fusion method named Evolver, inspired by evolutionary algorithms,
which does not need further training or additional training data. Specifically,
our method involves aggregating the weights of different language models into a
population and subsequently generating offspring models through mutation and
crossover operations. These offspring models are then evaluated against their
parents, allowing for the preservation of those models that show enhanced
performance on development datasets. Importantly, our model evolving strategy
can be seamlessly integrated with existing model merging frameworks, offering a
versatile tool for model enhancement. Experimental results on mainstream
language models (i.e., encoder-only, decoder-only, encoder-decoder) reveal that
Evolver outperforms previous state-of-the-art models by large margins. The code
is publicly available at {this https URL}.

本研究提出了一种名为 Evolver 的知识融合方法，它可以将不同语言模型的权重进行集成，通过进化算法生成新的模型并与父模型进行评估，达到在不同数据领域通用且性能优越的目的，这种方法与现有模型合并框架无缝集成，为模型增强提供了一种多功能工具。

基于语言模型权重演化的知识融合

Knowledge Fusion By Evolving Weights of Language Models

In this work, we aim to enhance the system robustness of end-to-end automatic
speech recognition (ASR) against adversarially-noisy speech examples. We focus
on a rigorous and empirical "closed-model adversarial robustness" setting
(e.g., on-device or cloud applications). The adversarial noise is only
generated by closed-model optimization (e.g., evolutionary and zeroth-order
estimation) without accessing gradient information of a targeted ASR model
directly. We propose an advanced Bayesian neural network (BNN) based
adversarial detector, which could model latent distributions against adaptive
adversarial perturbation with divergence measurement. We further simulate
deployment scenarios of RNN Transducer, Conformer, and wav2vec-2.0 based ASR
systems with the proposed adversarial detection system. Leveraging the proposed
BNN based detection system, we improve detection rate by +2.77 to +5.42%
(relative +3.03 to +6.26%) and reduce the word error rate by 5.02 to 7.47% on
LibriSpeech datasets compared to the current model enhancement methods against
the adversarial speech examples.

本文使用先进的贝叶斯神经网络来检测对抗性噪声干扰下的自动语音识别系统，实验结果表明，该检测系统相对于当前现有的增强方法，可以提高 2.77% 至 5.42% 的检测率，并且可以将单词错误率降低 5.02% 至 7.47%。