Spelling variation (e.g. funnnn vs. fun) can influence the social perception of texts and their writers: we often have various associations with different forms of writing (is the text informal? does the writer seem young?). In this study, we focus on the social perception of spelling variation in online writing in English and study to what extent this perception is aligned between humans and large language models (LLMs). Building on sociolinguistic methodology, we compare LLM and human ratings on three key social attributes of spelling variation (formality, carefulness, age). We find generally strong correlations in the ratings between humans and LLMs. However, notable differences emerge when we analyze the distribution of ratings and when comparing between different types of spelling variation.

Achieving human-level translations requires leveraging context to ensure coherence and handle complex phenomena like pronoun disambiguation. Sparsity of contextually rich examples in the standard training data has been hypothesized as the reason for the difficulty of context utilization. In this work, we systematically validate this claim in both single- and multilingual settings by constructing training datasets with a controlled proportions of contextually relevant examples. We demonstrate a strong association between training data sparsity and model performance confirming sparsity as a key bottleneck. Importantly, we reveal that improvements in one contextual phenomenon do no generalize to others. While we observe some cross-lingual transfer, it is not significantly higher between languages within the same sub-family. Finally, we propose and empirically evaluate two training strategies designed to leverage the available data. These strategies improve context utilization, resulting in accuracy gains of up to 6 and 8 percentage points on the ctxPro evaluation in single- and multilingual settings respectively.

Large Language Models (LLMs), which simulate human users, are frequently employed to evaluate chatbots in applications such as tutoring and customer service. Effective evaluation necessitates a high degree of human-like diversity within these simulations. In this paper, we demonstrate that conversations generated by GPT-4o mini, when used as simulated human participants, systematically differ from those between actual humans across multiple linguistic features. These features include topic variation, lexical attributes, and both the average behavior and diversity (variance) of the language used. To address these discrepancies, we propose an approach that automatically generates prompts for user simulations by incorporating features derived from real human interactions, such as age, gender, emotional tone, and the topics discussed. We assess our approach using differential language analysis combined with deep linguistic inquiry. Our method of prompt optimization, tailored to target specific linguistic features, shows significant improvements. Specifically, it enhances the human-likeness of LLM chatbot conversations, increasing their linguistic diversity. On average, we observe a 54 percent reduction in the error of average features between human and LLM-generated conversations. This method of constructing chatbot sets with human-like diversity holds great potential for enhancing the evaluation process of user-facing bots.

This study investigates the influence of Japanese honorifics on the responses of large language models (LLMs) when explaining the law of conservation of momentum. We analyzed the outputs of six state-of-the-art AI models, including variations of ChatGPT, Coral, and Gemini, using 14 different honorific forms. Our findings reveal that honorifics significantly affect the quality, consistency, and formality of AI-generated responses, demonstrating LLMs' ability to interpret and adapt to social context cues embedded in language. Notable variations were observed across different models, with some emphasizing historical context and derivations, while others focused on intuitive explanations. The study highlights the potential for using honorifics to adjust the depth and complexity of AI-generated explanations in educational contexts. Furthermore, the responsiveness of AI models to cultural linguistic elements underscores the importance of considering cultural factors in AI development for educational applications. These results open new avenues for research in AI-assisted education and cultural adaptation in AI systems, with significant implications for personalizing learning experiences and developing culturally sensitive AI tools for global education.

In this paper, we examine the collaborative dynamics between humans and language models (LMs), where the interactions typically involve LMs proposing text segments and humans editing or responding to these proposals. Productive engagement with LMs in such scenarios necessitates that humans discern effective text-based interaction strategies, such as editing and response styles, from historical human-LM interactions. This objective is inherently causal, driven by the counterfactual `what-if' question: how would the outcome of collaboration change if humans employed a different text editing/refinement strategy? A key challenge in answering this causal inference question is formulating an appropriate causal estimand: the conventional average treatment effect (ATE) estimand is inapplicable to text-based treatments due to their high dimensionality. To address this concern, we introduce a new causal estimand -- Incremental Stylistic Effect (ISE) -- which characterizes the average impact of infinitesimally shifting a text towards a specific style, such as increasing formality. We establish the conditions for the non-parametric identification of ISE. Building on this, we develop CausalCollab, an algorithm designed to estimate the ISE of various interaction strategies in dynamic human-LM collaborations. Our empirical investigations across three distinct human-LM collaboration scenarios reveal that CausalCollab effectively reduces confounding and significantly improves counterfactual estimation over a set of competitive baselines.

Style is an integral component of text that expresses a diverse set of information, including interpersonal dynamics (e.g. formality) and the author's emotions or attitudes (e.g. disgust). Humans often employ multiple styles simultaneously. An open question is how large language models can be explicitly controlled so that they weave together target styles when generating text: for example, to produce text that is both negative and non-toxic. Previous work investigates the controlled generation of a single style, or else controlled generation of a style and other attributes. In this paper, we expand this into controlling multiple styles simultaneously. Specifically, we investigate various formulations of multiple style rewards for a reinforcement learning (RL) approach to controlled multi-style generation. These reward formulations include calibrated outputs from discriminators and dynamic weighting by discriminator gradient magnitudes. We find that dynamic weighting generally outperforms static weighting approaches, and we explore its effectiveness in 2- and 3-style control, even compared to strong baselines like plug-and-play model. All code and data for RL pipelines with multiple style attributes will be publicly available.

Customizing machine translation models to comply with desired attributes (e.g., formality or grammatical gender) is a well-studied topic. However, most current approaches rely on (semi-)supervised data with attribute annotations. This data scarcity bottlenecks democratizing such customization possibilities to a wider range of languages, particularly lower-resource ones. This gap is out of sync with recent progress in pretrained massively multilingual translation models. In response, we transfer the attribute controlling capabilities to languages without attribute-annotated data with an NLLB-200 model as a foundation. Inspired by techniques from controllable generation, we employ a gradient-based inference-time controller to steer the pretrained model. The controller transfers well to zero-shot conditions, as it operates on pretrained multilingual representations and is attribute -- rather than language-specific. With a comprehensive comparison to finetuning-based control, we demonstrate that, despite finetuning's clear dominance in supervised settings, the gap to inference-time control closes when moving to zero-shot conditions, especially with new and distant target languages. The latter also shows stronger domain robustness. We further show that our inference-time control complements finetuning. A human evaluation on a real low-resource language, Bengali, confirms our findings. Our code is https://github.com/dannigt/attribute-controller-transfer

Formality plays a significant role in language communication, especially in low-resource languages such as Hindi, Japanese and Korean. These languages utilise formal and informal expressions to convey messages based on social contexts and relationships. When a language translation technique is used to translate from a source language that does not pertain the formality (e.g. English) to a target language that does, there is a missing information on formality that could be a challenge in producing an accurate outcome. This research explores how this issue should be resolved when machine learning methods are used to translate from English to languages with formality, using Hindi as the example data. This was done by training a bilingual model in a formality-controlled setting and comparing its performance with a pre-trained multilingual model in a similar setting. Since there are not a lot of training data with ground truth, automated annotation techniques were employed to increase the data size. The primary modeling approach involved leveraging transformer models, which have demonstrated effectiveness in various natural language processing tasks. We evaluate the official formality accuracy(ACC) by comparing the predicted masked tokens with the ground truth. This metric provides a quantitative measure of how well the translations align with the desired outputs. Our study showcases a versatile translation strategy that considers the nuances of formality in the target language, catering to diverse language communication needs and scenarios.

As Large Language Models (LLMs) have advanced, they have brought forth new challenges, with one of the prominent issues being LLM hallucination. While various mitigation techniques are emerging to address hallucination, it is equally crucial to delve into its underlying causes. Consequently, in this preliminary exploratory investigation, we examine how linguistic factors in prompts, specifically readability, formality, and concreteness, influence the occurrence of hallucinations. Our experimental results suggest that prompts characterized by greater formality and concreteness tend to result in reduced hallucination. However, the outcomes pertaining to readability are somewhat inconclusive, showing a mixed pattern.