We present a prompt-engineering-based text-augmentation approach applied to a
language-queried audio source separation (LASS) task. To enhance the
performance of LASS, the proposed approach utilizes large language models
(LLMs) to generate multiple captions corresponding to each sentence of the
training dataset. To this end, we first perform experiments to identify the
most effective prompts for caption augmentation with a smaller number of
captions. A LASS model trained with these augmented captions demonstrates
improved performance on the DCASE 2024 Task 9 validation set compared to that
trained without augmentation. This study highlights the effectiveness of
LLM-based caption augmentation in advancing language-queried audio source
separation.

我们提出了一种基于提示工程的文本增强方法，应用于语言查询音频源分离（LASS）任务。该方法利用大型语言模型生成与训练数据集每个句子对应的多个字幕来增强 LASS 的性能。实验结果表明，使用这些增强的字幕训练的 LASS 模型在 DCASE 2024 任务 9 验证集上表现出了比没有增强的模型更好的性能。该研究突出了基于语言模型的字幕增强在推动语言查询音频源分离方面的有效性。

基于大型语言模型的字幕增强技术提升的语言查询音频源分离性能：DCASE Challenge 2024 任务 9

Performance Improvement of Language-Queried Audio Source Separation  Based on Caption Augmentation From Large Language Models for DCASE Challenge  2024 Task 9

While most existing works on LLM prompt-engineering focus only on how to
select a better set of data samples inside one single prompt input (In-Context
Learning or ICL), why can't we design and leverage multiple prompt inputs
together to further improve the LLM performance? In this work, we propose
In-Context Sampling (ICS), a low-resource LLM prompt-engineering technique to
produce the most confident prediction results by optimizing the construction of
multiple ICL prompt inputs. Extensive experiments with two SOTA LLMs (FlanT5-XL
and Mistral-7B) on three NLI datasets (e-SNLI, Multi-NLI, and ANLI) illustrate
that ICS can consistently enhance LLM's prediction performance and confidence.
An ablation study suggests that a diversity-based ICS strategy may further
improve LLM's performance, which sheds light on a new yet promising future
research direction.

本文介绍了一种低资源的 LLM 提示工程技术，名为 In-Context Sampling（ICS），通过优化构建多个 ICL 提示输入以获得最有信心的预测结果；在两个 SOTA LLMs（FlanT5-XL 和 Mistral-7B）以及三个 NLI 数据集（e-SNLI、Multi-NLI 和 ANLI）上进行的大量实验表明，ICS 可以始终提高 LLM 的预测性能和置信度，并且消融研究表明多样化的 ICS 策略可能进一步改善 LLM 的性能，为未来的研究方向提供了新的有前途的思路。

更多样本还是更多提示输入？探索用于 LLM 少样本提示工程的有效上下文抽样

More Samples or More Prompt Inputs? Exploring Effective In-Context  Sampling for LLM Few-Shot Prompt Engineering

Novel architectures have recently improved generative image synthesis leading
to excellent visual quality in various tasks. Of particular note is the field
of ``AI-Art'', which has seen unprecedented growth with the emergence of
powerful multimodal models such as CLIP. By combining speech and image
synthesis models, so-called ``prompt-engineering'' has become established, in
which carefully selected and composed sentences are used to achieve a certain
visual style in the synthesized image. In this note, we present an alternative
approach based on retrieval-augmented diffusion models (RDMs). In RDMs, a set
of nearest neighbors is retrieved from an external database during training for
each training instance, and the diffusion model is conditioned on these
informative samples. During inference (sampling), we replace the retrieval
database with a more specialized database that contains, for example, only
images of a particular visual style. This provides a novel way to prompt a
general trained model after training and thereby specify a particular visual
style. As shown by our experiments, this approach is superior to specifying the
visual style within the text prompt. We open-source code and model weights at
this https URL .

通过检索增强的扩散模型，我们提出了一种替代性方法，改进了生成图像合成技术，优于基于文本提示的视觉样式规定。

带有检索增强扩散模型的文本引导艺术图片生成

Text-Guided Synthesis of Artistic Images with Retrieval-Augmented  Diffusion Models

Coreference resolution -- which is a crucial task for understanding discourse
and language at large -- has yet to witness widespread benefits from large
language models (LLMs). Moreover, coreference resolution systems largely rely
on supervised labels, which are highly expensive and difficult to annotate,
thus making it ripe for prompt engineering. In this paper, we introduce a
QA-based prompt-engineering method and discern \textit{generative}, pre-trained
LLMs' abilities and limitations toward the task of coreference resolution. Our
experiments show that GPT-2 and GPT-Neo can return valid answers, but that
their capabilities to identify coreferent mentions are limited and
prompt-sensitive, leading to inconsistent results.

通过问题引导的工程方法，我们测试了更大的模型对 coreference resolution 任务的可行性，研究表明，GPT-2 和 GPT-Neo 可以返回有效的答案，但其识别 coreferent mentions 的能力受到提示敏感性的限制，导致结果不一致。