Pluralis v0.1: Towards a Multicultural, Multimodal, Multilingual Benchmark for AI Risk and Reliability

Authors: Alicia Parrish, Rajat Shinde, Sanket Badhe, Xinyi Bai, Sree Bhargavi Balija, Hua-Rong Chu, Emilio Ferrara, Armstrong Foundjem, Rajat Ghosh, Aakash Gupta, Xuanli He, Ong Chen Hui, Minji Jung, Madhangi Karimanal, Faiza Khan Khattak, Boryoung Kim, Eugenia Kim, Liliya Lavitas, Seok Min Lim, Victor Lu, Jim Moirangthem, Dhivya Nagasubramanian, Deepak Pandita, Sita Rajagopal, Geetha Raju , et al. (35 additional authors not shown)

Abstract: Current AI safety evaluation and benchmarking frameworks predominantly rely on Western-centric culture-agnostic defaults that mask critical regional laws, socio-linguistic nuances, and cultural taboos, leaving Vision-Language Models (VLMs) vulnerable in global deployments. We introduce Pluralis v0.1: a novel multimodal, multi-regional, and multilingual dataset built from a culture-first perspectiv… ▽ More Current AI safety evaluation and benchmarking frameworks predominantly rely on Western-centric culture-agnostic defaults that mask critical regional laws, socio-linguistic nuances, and cultural taboos, leaving Vision-Language Models (VLMs) vulnerable in global deployments. We introduce Pluralis v0.1: a novel multimodal, multi-regional, and multilingual dataset built from a culture-first perspective. Spanning 6,448 prompts across six Asia-Pacific countries (Bangladesh, India, Korea, Pakistan, Singapore, Taiwan) and eight languages, Pluralis diverges from prior work by natively sourcing localized safety hazards rather than adapting Western datasets. Crucially, it introduces a multimodal evaluation paradigm: user text (e.g., "Should I gift this?") and an image referring to "this" (e.g., a clock) - both innocuous in isolation, but synergistically triggering specific legal or cultural violations. Pluralis disentangles universal safety violations from localized cultural appropriateness, establishing the latter as a first-class evaluation axis. To operationalize this, we present Judge-Pluralis, an agreement-gated LLM-as-a-Judge ensemble trained on examples classified in an empirically derived cultural taxonomy. Observing VLM behavior on a subset of the Pluralis surfaces recurring, locale-specific failure modes such as image misidentifications with downstream harm, missed item-context-locale interactions, and inadequate refusals. These failure modes vary systematically across locales and languages, exposing blind spots that globally averaged metrics conceal. Ultimately, Pluralis is not presented as a solved evaluation framework for cultural alignment, but rather as a first step and catalyst for future innovation. We call upon the research community to utilize this foundation to advance the science of multilingual, multicultural evaluation to better support AI cultural alignment globally. △ Less

Submitted 7 July, 2026; originally announced July 2026.

Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking

Authors: Songbo Hu, Yinhong Liu, Ej Zhou, Evgeniia Razumovskaia, Xiaobin Wang, Alexander Fraser, Ivan Vulić, Anna Korhonen

Abstract: Creating spoken dialogue datasets is methodologically challenging, and these challenges are amplified when the goal is to build multilingual, multi-parallel datasets at scale. This work introduces HEALTHDIAL, a large-scale, multilingual, and multi-parallel dataset for developing and evaluating retrieval-augmented generation (RAG)-based spoken dialogue systems. The dataset comprises 6,000 informati… ▽ More Creating spoken dialogue datasets is methodologically challenging, and these challenges are amplified when the goal is to build multilingual, multi-parallel datasets at scale. This work introduces HEALTHDIAL, a large-scale, multilingual, and multi-parallel dataset for developing and evaluating retrieval-augmented generation (RAG)-based spoken dialogue systems. The dataset comprises 6,000 information-seeking dialogues (1,500 per language) grounded in trusted content from the World Health Organization (WHO) and 163 hours of user speech recorded from native speakers of diverse dialects across four official WHO languages: Arabic, Chinese, English, and Spanish. Each speaker is annotated with demographic (e.g., gender, age) and sociolinguistic (e.g., primary language, region of origin) variables. We report benchmark results across key dialogue tasks, which reveal consistent performance disparities across languages, even among high-resource ones. To support future research, we release the dataset, a prototype system, and a toolkit for data collection and system evaluation. △ Less

Submitted 28 May, 2026; originally announced May 2026.

Going PLACES: Participatory Localized Red Teaming for Text-to-Image Safety in the Global South

Authors: Charvi Rastogi, Mukul Bhutani, Minsuk Kahng, Shamsuddeen Hassan Muhammad, Evgeniia Razumovskaia, Priyanka Suresh, Ibrahim Said Ahmad, Charu Kalia, Yaaseen Mahomed, Madhurima Maji, Minjae Lee, Alicia Parrish, Jessica Quaye, Vijay Janapa Reddi, Aishwarya Verma, Lora Aroyo

Abstract: Despite the global deployment of text-to-image (T2I) models, their safety frameworks are largely calibrated to a Western-centric default, creating significant vulnerabilities for the rest of the world. To embrace cultural pluralism and bring historically under-represented perspectives in T2I safety, we conduct localised community-centered red teaming studies in the Global South. Our two-fold appro… ▽ More Despite the global deployment of text-to-image (T2I) models, their safety frameworks are largely calibrated to a Western-centric default, creating significant vulnerabilities for the rest of the world. To embrace cultural pluralism and bring historically under-represented perspectives in T2I safety, we conduct localised community-centered red teaming studies in the Global South. Our two-fold approach prioritizes localization and participation, by focusing on secondary urban centers in these regions, and conducting community engagement and training workshops to contextualize local norms. As a result, we present PLACES, a dataset comprising over 26,000 examples of T2I model failures collected in partnership with universities in Ghana, Nigeria, and two regions of India (Karnataka and Punjab). Analysis of prompts collected reveals a wide-ranging diversity in socio-cultural and linguistic attributes, when compared to existing geography-agnostic crowdsourced red-teaming data. We observe unique adversarial patterns enabled by local cultural and linguistic nuances, and distinct clusters within region around specific themes, such as religion in India. Moreover, we uncover structural contextual gaps in existing safety frameworks by identifying novel harms showing normative dissonance (e.g., violating religious norms, ignoring local customs, and ominous symbolism). This work argues that expanding T2I safety requires moving beyond mere scale to incorporate deeply localised, participatory methodologies for data collection and contextualization. Content warning: This paper includes examples containing potentially harmful or offensive content. △ Less

Submitted 18 May, 2026; originally announced May 2026.

Analyzing and Adapting Large Language Models for Few-Shot Multilingual NLU: Are We There Yet?

Authors: Evgeniia Razumovskaia, Ivan Vulić, Anna Korhonen

Abstract: Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning (ICL) are three alternative, de facto standard approaches to few-shot learning. ICL has gained popularity recently with the advent of LLMs due to its simplicity and sample efficiency. Prior research has conducted only limited investigation into how these approaches work for multilingual few-shot learning, and… ▽ More Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning (ICL) are three alternative, de facto standard approaches to few-shot learning. ICL has gained popularity recently with the advent of LLMs due to its simplicity and sample efficiency. Prior research has conducted only limited investigation into how these approaches work for multilingual few-shot learning, and the focus so far has been mostly on their performance. In this work, we present an extensive and systematic comparison of the three approaches, testing them on 6 high- and low-resource languages, three different NLU tasks, and a myriad of language and domain setups. Importantly, performance is only one aspect of the comparison, where we also analyse the approaches through the optics of their computational, inference and financial costs. Our observations show that supervised instruction tuning has the best trade-off between performance and resource requirements. As another contribution, we analyse the impact of target language adaptation of pretrained LLMs and find that the standard adaptation approaches can (superficially) improve target language generation capabilities, but language understanding elicited through ICL does not improve and remains limited, with low scores especially for low-resource languages. △ Less

Submitted 4 March, 2024; originally announced March 2024.

$\textit{Dial BeInfo for Faithfulness}$: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuning

Authors: Evgeniia Razumovskaia, Ivan Vulić, Pavle Marković, Tomasz Cichy, Qian Zheng, Tsung-Hsien Wen, Paweł Budzianowski

Abstract: Factuality is a crucial requirement in information seeking dialogue: the system should respond to the user's queries so that the responses are meaningful and aligned with the knowledge provided to the system. However, most modern large language models suffer from hallucinations, that is, they generate responses not supported by or contradicting the knowledge source. To mitigate the issue and incre… ▽ More Factuality is a crucial requirement in information seeking dialogue: the system should respond to the user's queries so that the responses are meaningful and aligned with the knowledge provided to the system. However, most modern large language models suffer from hallucinations, that is, they generate responses not supported by or contradicting the knowledge source. To mitigate the issue and increase faithfulness of information-seeking dialogue systems, we introduce BeInfo, a simple yet effective method that applies behavioural tuning to aid information-seeking dialogue. Relying on three standard datasets, we show that models tuned with BeInfo} become considerably more faithful to the knowledge source both for datasets and domains seen during BeInfo-tuning, as well as on unseen domains, when applied in a zero-shot manner. In addition, we show that the models with 3B parameters (e.g., Flan-T5) tuned with BeInfo demonstrate strong performance on data from real `production' conversations and outperform GPT4 when tuned on a limited amount of such realistic in-domain dialogues. △ Less

Submitted 4 March, 2024; v1 submitted 16 November, 2023; originally announced November 2023.

SQATIN: Supervised Instruction Tuning Meets Question Answering for Improved Dialogue NLU

Authors: Evgeniia Razumovskaia, Goran Glavaš, Anna Korhonen, Ivan Vulić

Abstract: Task-oriented dialogue (ToD) systems help users execute well-defined tasks across a variety of domains (e.g., $\textit{flight booking}$ or $\textit{food ordering}$), with their Natural Language Understanding (NLU) components being dedicated to the analysis of user utterances, predicting users' intents ($\textit{Intent Detection}$, ID) and extracting values for informational slots (… ▽ More Task-oriented dialogue (ToD) systems help users execute well-defined tasks across a variety of domains (e.g., $\textit{flight booking}$ or $\textit{food ordering}$), with their Natural Language Understanding (NLU) components being dedicated to the analysis of user utterances, predicting users' intents ($\textit{Intent Detection}$, ID) and extracting values for informational slots ($\textit{Value Extraction}$, VE). In most domains, labelled NLU data is scarce, making sample-efficient learning -- enabled with effective transfer paradigms -- paramount. In this work, we introduce SQATIN, a new framework for dialog NLU based on (i) instruction tuning and (ii) question-answering-based formulation of ID and VE tasks. According to the evaluation on established NLU benchmarks, SQATIN sets the new state of the art in dialogue NLU, substantially surpassing the performance of current models based on standard fine-tuning objectives in both in-domain training and cross-domain transfer. SQATIN yields particularly large performance gains in cross-domain transfer, owing to the fact that our QA-based instruction tuning leverages similarities between natural language descriptions of classes (i.e., slots and intents) across domains. △ Less

Submitted 8 April, 2024; v1 submitted 15 November, 2023; originally announced November 2023.

Transfer-Free Data-Efficient Multilingual Slot Labeling

Authors: Evgeniia Razumovskaia, Ivan Vulić, Anna Korhonen

Abstract: Slot labeling (SL) is a core component of task-oriented dialogue (ToD) systems, where slots and corresponding values are usually language-, task- and domain-specific. Therefore, extending the system to any new language-domain-task configuration requires (re)running an expensive and resource-intensive data annotation process. To mitigate the inherent data scarcity issue, current research on multili… ▽ More Slot labeling (SL) is a core component of task-oriented dialogue (ToD) systems, where slots and corresponding values are usually language-, task- and domain-specific. Therefore, extending the system to any new language-domain-task configuration requires (re)running an expensive and resource-intensive data annotation process. To mitigate the inherent data scarcity issue, current research on multilingual ToD assumes that sufficient English-language annotated data are always available for particular tasks and domains, and thus operates in a standard cross-lingual transfer setup. In this work, we depart from this often unrealistic assumption. We examine challenging scenarios where such transfer-enabling English annotated data cannot be guaranteed, and focus on bootstrapping multilingual data-efficient slot labelers in transfer-free scenarios directly in the target languages without any English-ready data. We propose a two-stage slot labeling approach (termed TWOSL) which transforms standard multilingual sentence encoders into effective slot labelers. In Stage 1, relying on SL-adapted contrastive learning with only a handful of SL-annotated examples, we turn sentence encoders into task-specific span encoders. In Stage 2, we recast SL from a token classification into a simpler, less data-intensive span classification task. Our results on two standard multilingual TOD datasets and across diverse languages confirm the effectiveness and robustness of TWOSL. It is especially effective for the most challenging transfer-free few-shot setups, paving the way for quick and data-efficient bootstrapping of multilingual slot labelers for ToD. △ Less

Submitted 12 November, 2023; v1 submitted 22 May, 2023; originally announced May 2023.

Little Red Riding Hood Goes Around the Globe:Crosslingual Story Planning and Generation with Large Language Models

Authors: Evgeniia Razumovskaia, Joshua Maynez, Annie Louis, Mirella Lapata, Shashi Narayan

Abstract: Previous work has demonstrated the effectiveness of planning for story generation exclusively in a monolingual setting focusing primarily on English. We consider whether planning brings advantages to automatic story generation across languages. We propose a new task of cross-lingual story generation with planning and present a new dataset for this task. We conduct a comprehensive study of differen… ▽ More Previous work has demonstrated the effectiveness of planning for story generation exclusively in a monolingual setting focusing primarily on English. We consider whether planning brings advantages to automatic story generation across languages. We propose a new task of cross-lingual story generation with planning and present a new dataset for this task. We conduct a comprehensive study of different plans and generate stories in several languages, by leveraging the creative and reasoning capabilities of large pre-trained language models. Our results demonstrate that plans which structure stories into three acts lead to more coherent and interesting narratives, while allowing to explicitly control their content and structure. △ Less

Submitted 25 March, 2024; v1 submitted 20 December, 2022; originally announced December 2022.

MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue

Authors: Nikita Moghe, Evgeniia Razumovskaia, Liane Guillou, Ivan Vulić, Anna Korhonen, Alexandra Birch

Abstract: Task-oriented dialogue (TOD) systems have been widely deployed in many industries as they deliver more efficient customer support. These systems are typically constructed for a single domain or language and do not generalise well beyond this. To support work on Natural Language Understanding (NLU) in TOD across multiple languages and domains simultaneously, we constructed MULTI3NLU++, a multilingu… ▽ More Task-oriented dialogue (TOD) systems have been widely deployed in many industries as they deliver more efficient customer support. These systems are typically constructed for a single domain or language and do not generalise well beyond this. To support work on Natural Language Understanding (NLU) in TOD across multiple languages and domains simultaneously, we constructed MULTI3NLU++, a multilingual, multi-intent, multi-domain dataset. MULTI3NLU++ extends the English only NLU++ dataset to include manual translations into a range of high, medium, and low resource languages (Spanish, Marathi, Turkish and Amharic), in two domains (BANKING and HOTELS). Because of its multi-intent property, MULTI3NLU++ represents complex and natural user goals, and therefore allows us to measure the realistic performance of TOD systems in a varied set of the world's languages. We use MULTI3NLU++ to benchmark state-of-the-art multilingual models for the NLU tasks of intent detection and slot labelling for TOD systems in the multilingual setting. The results demonstrate the challenging nature of the dataset, particularly in the low-resource language setting, offering ample room for future experimentation in multi-domain multilingual TOD setups. △ Less

Submitted 19 June, 2023; v1 submitted 20 December, 2022; originally announced December 2022.

Cross-Lingual Dialogue Dataset Creation via Outline-Based Generation

Authors: Olga Majewska, Evgeniia Razumovskaia, Edoardo Maria Ponti, Ivan Vulić, Anna Korhonen

Abstract: Multilingual task-oriented dialogue (ToD) facilitates access to services and information for many (communities of) speakers. Nevertheless, the potential of this technology is not fully realised, as current datasets for multilingual ToD - both for modular and end-to-end modelling - suffer from severe limitations. 1) When created from scratch, they are usually small in scale and fail to cover many p… ▽ More Multilingual task-oriented dialogue (ToD) facilitates access to services and information for many (communities of) speakers. Nevertheless, the potential of this technology is not fully realised, as current datasets for multilingual ToD - both for modular and end-to-end modelling - suffer from severe limitations. 1) When created from scratch, they are usually small in scale and fail to cover many possible dialogue flows. 2) Translation-based ToD datasets might lack naturalness and cultural specificity in the target language. In this work, to tackle these limitations we propose a novel outline-based annotation process for multilingual ToD datasets, where domain-specific abstract schemata of dialogue are mapped into natural language outlines. These in turn guide the target language annotators in writing a dialogue by providing instructions about each turn's intents and slots. Through this process we annotate a new large-scale dataset for training and evaluation of multilingual and cross-lingual ToD systems. Our Cross-lingual Outline-based Dialogue dataset (termed COD) enables natural language understanding, dialogue state tracking, and end-to-end dialogue modelling and evaluation in 4 diverse languages: Arabic, Indonesian, Russian, and Kiswahili. Qualitative and quantitative analyses of COD versus an equivalent translation-based dataset demonstrate improvements in data quality, unlocked by the outline-based approach. Finally, we benchmark a series of state-of-the-art systems for cross-lingual ToD, setting reference scores for future work and demonstrating that COD prevents over-inflated performance, typically met with prior translation-based ToD datasets. △ Less

Submitted 31 January, 2022; originally announced January 2022.

Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems

Authors: Evgeniia Razumovskaia, Goran Glavaš, Olga Majewska, Edoardo M. Ponti, Anna Korhonen, Ivan Vulić

Abstract: In task-oriented dialogue (ToD), a user holds a conversation with an artificial agent to complete a concrete task. Although this technology represents one of the central objectives of AI and has been the focus of ever more intense research and development efforts, it is currently limited to a few narrow domains (e.g., food ordering, ticket booking) and a handful of languages (e.g., English, Chines… ▽ More In task-oriented dialogue (ToD), a user holds a conversation with an artificial agent to complete a concrete task. Although this technology represents one of the central objectives of AI and has been the focus of ever more intense research and development efforts, it is currently limited to a few narrow domains (e.g., food ordering, ticket booking) and a handful of languages (e.g., English, Chinese). This work provides an extensive overview of existing methods and resources in multilingual ToD as an entry point to this exciting and emerging field. We find that the most critical factor preventing the creation of truly multilingual ToD systems is the lack of datasets in most languages for both training and evaluation. In fact, acquiring annotations or human feedback for each component of modular systems or for data-hungry end-to-end systems is expensive and tedious. Hence, state-of-the-art approaches to multilingual ToD mostly rely on (zero- or few-shot) cross-lingual transfer from resource-rich languages (almost exclusively English), either by means of machine translation or multilingual representations. These approaches are currently viable only for typologically similar languages and languages with parallel / monolingual corpora available. On the other hand, their effectiveness beyond these boundaries is doubtful or hard to assess due to the lack of linguistically diverse benchmarks (especially for natural language generation and end-to-end evaluation). To overcome this limitation, we draw parallels between components of the ToD pipeline and other NLP tasks, which can inspire solutions for learning in low-resource scenarios. Finally, we list additional challenges that multilinguality poses for related areas (such as speech and human-centred evaluation), and indicate future directions that hold promise to further expand language coverage and dialogue capabilities of current ToD systems. △ Less

Submitted 25 May, 2022; v1 submitted 17 April, 2021; originally announced April 2021.

Pretraining Methods for Dialog Context Representation Learning

Authors: Shikib Mehri, Evgeniia Razumovskaia, Tiancheng Zhao, Maxine Eskenazi

Abstract: This paper examines various unsupervised pretraining objectives for learning dialog context representations. Two novel methods of pretraining dialog context encoders are proposed, and a total of four methods are examined. Each pretraining objective is fine-tuned and evaluated on a set of downstream dialog tasks using the MultiWoz dataset and strong performance improvement is observed. Further eval… ▽ More This paper examines various unsupervised pretraining objectives for learning dialog context representations. Two novel methods of pretraining dialog context encoders are proposed, and a total of four methods are examined. Each pretraining objective is fine-tuned and evaluated on a set of downstream dialog tasks using the MultiWoz dataset and strong performance improvement is observed. Further evaluation shows that our pretraining objectives result in not only better performance, but also better convergence, models that are less data hungry and have better domain generalizability. △ Less

Submitted 3 June, 2019; v1 submitted 2 June, 2019; originally announced June 2019.

Beyond Turing: Intelligent Agents Centered on the User

Authors: Maxine Eskenazi, Shikib Mehri, Evgeniia Razumovskaia, Tiancheng Zhao

Abstract: Most research on intelligent agents centers on the agent and not on the user. We look at the origins of agent-centric research for slot-filling, gaming and chatbot agents. We then argue that it is important to concentrate more on the user. After reviewing relevant literature, some approaches for creating and assessing user-centric systems are proposed. Most research on intelligent agents centers on the agent and not on the user. We look at the origins of agent-centric research for slot-filling, gaming and chatbot agents. We then argue that it is important to concentrate more on the user. After reviewing relevant literature, some approaches for creating and assessing user-centric systems are proposed. △ Less

Submitted 18 March, 2019; v1 submitted 19 January, 2019; originally announced January 2019.