LLMs make it easy to rewrite text in any style, be it more polite, persuasive, or more positive. We present a large-scale study of evaluation metrics for style and attribute transfer with a focus on content preservation; meaning content not attributed to the style shift is preserved. The de facto evaluation approach uses lexical or semantic similarity metrics often between source sentences and rewrites. While these metrics are not designed to distinguish between style or content differences, empirical meta-evaluation shows a reasonable correlation to human judgment. In fact, recent works find that LLMs prompted as evaluators are only comparable to semantic similarity metrics, even though intuitively, the LLM approach should better fit the task. To investigate this discrepancy, we benchmark 8 metrics for evaluating content preservation on existing datasets and additionally construct a new test set that better aligns with the meta-evaluation aim. Indeed, we then find that the empirical conclusion aligns with the intuition: content preservation metrics for style/attribute transfer must be conditional on the style shift. To support this, we propose a new efficient zero-shot evaluation method using the likelihood of the next token. We hope our meta-evaluation can foster more research on evaluating content preservation metrics, and also to ensure fair evaluation of methods for conducting style transfer.

Language style is necessary for AI systems to understand and generate diverse human language accurately. However, previous text style transfer primarily focused on sentence-level data-driven approaches, limiting exploration of potential problems in large language models (LLMs) and the ability to meet complex application needs. To overcome these limitations, we introduce a novel task called Public-Speaking Style Transfer (PSST), which aims to simulate humans to transform passage-level, official texts into a public-speaking style. Grounded in the analysis of real-world data from a linguistic perspective, we decompose public-speaking style into key sub-styles to pose challenges and quantify the style modeling capability of LLMs. For such intricate text style transfer, we further propose a fine-grained evaluation framework to analyze the characteristics and identify the problems of stylized texts. Comprehensive experiments suggest that current LLMs struggle to generate public speaking texts that align with human preferences, primarily due to excessive stylization and loss of semantic information.

Since the breakthrough of ChatGPT, large language models (LLMs) have garnered significant attention in the research community. With the development of LLMs, the question of text style transfer for conversational models has emerged as a natural extension, where chatbots may possess their own styles or even characters. However, standard evaluation metrics have not yet been established for this new settings. This paper aims to address this issue by proposing the LMStyle Benchmark, a novel evaluation framework applicable to chat-style text style transfer (C-TST), that can measure the quality of style transfer for LLMs in an automated and scalable manner. In addition to conventional style strength metrics, LMStyle Benchmark further considers a novel aspect of metrics called appropriateness, a high-level metrics take account of coherence, fluency and other implicit factors without the aid of reference samples. Our experiments demonstrate that the new evaluation methods introduced by LMStyle Benchmark have a higher correlation with human judgments in terms of appropriateness. Based on LMStyle Benchmark, we present a comprehensive list of evaluation results for popular LLMs, including LLaMA, Alpaca, and Vicuna, reflecting their stylistic properties, such as formality and sentiment strength, along with their appropriateness.

Unsupervised Text Style Transfer (UTST) has emerged as a critical task within the domain of Natural Language Processing (NLP), aiming to transfer one stylistic aspect of a sentence into another style without changing its semantics, syntax, or other attributes. This task is especially challenging given the intrinsic lack of parallel text pairings. Among existing methods for UTST tasks, attention masking approach and Large Language Models (LLMs) are deemed as two pioneering methods. However, they have shortcomings in generating unsmooth sentences and changing the original contents, respectively. In this paper, we investigate if we can combine these two methods effectively. We propose four ways of interactions, that are pipeline framework with tuned orders; knowledge distillation from LLMs to attention masking model; in-context learning with constructed parallel examples. We empirically show these multi-way interactions can improve the baselines in certain perspective of style strength, content preservation and text fluency. Experiments also demonstrate that simply conducting prompting followed by attention masking-based revision can consistently surpass the other systems, including supervised text style transfer systems. On Yelp-clean and Amazon-clean datasets, it improves the previously best mean metric by 0.5 and 3.0 absolute percentages respectively, and achieves new SOTA results.

Conventional text style transfer approaches focus on sentence-level style transfer without considering contextual information, and the style is described with attributes (e.g., formality). When applying style transfer in conversations such as task-oriented dialogues, existing approaches suffer from these limitations as context can play an important role and the style attributes are often difficult to define in conversations. In this paper, we introduce conversation style transfer as a few-shot learning problem, where the model learns to perform style transfer by observing only a few example dialogues in the target style. We propose a novel in-context learning approach to solve the task with style-free dialogues as a pivot. Human evaluation shows that by incorporating multi-turn context, the model is able to match the target style while having better appropriateness and semantic correctness compared to utterance/sentence-level style transfer. Additionally, we show that conversation style transfer can also benefit downstream tasks. For example, in multi-domain intent classification tasks, the F1 scores improve after transferring the style of training data to match the style of the test data.

We investigate the potential of ChatGPT as a multidimensional evaluator for the task of \emph{Text Style Transfer}, alongside, and in comparison to, existing automatic metrics as well as human judgements. We focus on a zero-shot setting, i.e. prompting ChatGPT with specific task instructions, and test its performance on three commonly-used dimensions of text style transfer evaluation: style strength, content preservation, and fluency. We perform a comprehensive correlation analysis for two transfer directions (and overall) at different levels. Compared to existing automatic metrics, ChatGPT achieves competitive correlations with human judgments. These preliminary results are expected to provide a first glimpse into the role of large language models in the multidimensional evaluation of stylized text generation.

To preserve anonymity and obfuscate their identity on online platforms users may morph their text and portray themselves as a different gender or demographic. Similarly, a chatbot may need to customize its communication style to improve engagement with its audience. This manner of changing the style of written text has gained significant attention in recent years. Yet these past research works largely cater to the transfer of single style attributes. The disadvantage of focusing on a single style alone is that this often results in target text where other existing style attributes behave unpredictably or are unfairly dominated by the new style. To counteract this behavior, it would be nice to have a style transfer mechanism that can transfer or control multiple styles simultaneously and fairly. Through such an approach, one could obtain obfuscated or written text incorporated with a desired degree of multiple soft styles such as female-quality, politeness, or formalness. In this work, we demonstrate that the transfer of multiple styles cannot be achieved by sequentially performing multiple single-style transfers. This is because each single style-transfer step often reverses or dominates over the style incorporated by a previous transfer step. We then propose a neural network architecture for fairly transferring multiple style attributes in a given text. We test our architecture on the Yelp data set to demonstrate our superior performance as compared to existing one-style transfer steps performed in a sequence.