Toxicity judgments can depend on who is judging. We study whether persona prompting captures this variation by evaluating ten Indonesian-capable LLMs under four persona conditions on 7,524 IndoDiscourse posts, each labeled by at least one female and one male annotator, comprising 24,655 individual judgments. Persona cues substantially affect toxicity predictions, but their effects are model-specific, show no common direction, and are small between the two gender personas. Yet this steerability does not amount to perspective adoption: switching between gender personas does not selectively increase label agreement with the corresponding annotator group. Annotation-level mixed-effects models and annotator-level permutation tests likewise find no reliable female–male agreement gap. The apparent gap obtained from aggregated group labels instead follows from annotator label rates and aggregation choices.

Potentially idiomatic expressions (PIEs) carry meanings inherently tied to the everyday experience of a given language community. As such, they constitute an interesting challenge for assessing the linguistic (and to some extent cultural) capabilities of NLP systems. In this paper, we present XMPIE, a parallel multilingual and multimodal dataset of potentially idiomatic expressions. The dataset, containing 34 languages and over ten thousand items, allows comparative analyses of idiomatic patterns among language-specific realisations and preferences in order to gather insights about shared cultural aspects. This parallel dataset allows evaluation of language model performance for a given PIE in different languages and whether idiomatic understanding in one language can be transferred to another. Moreover, the dataset supports the study of PIEs across textual and visual modalities, to measure to what extent PIE understanding in one modality transfers or implies in understanding in another modality (text vs. image). The data was created by language experts, with both textual and visual components crafted under multilingual guidelines, and each PIE is accompanied by five images representing a spectrum from idiomatic to literal meanings, including semantically related and random distractors. The result is a high-quality benchmark for evaluating multilingual and multimodal idiomatic language understanding.

While the field of vision-language (VL) has achieved remarkable success in integrating visual and textual information across multiple languages and domains, there is no dedicated framework for assessing human-centric alignment in vision-language systems.

We offer two contributions to address this gap. First, we introduce Anthropogenic Regional Adaptation: a regional-adaptation framework that aims to optimize model relevance to specific regional contexts while ensuring the retention of global generalization capabilities. Second, we present a simple, but effective adaptation method named Geographical-generalization-made-easy (GG-EZ), which utilizes regional data filtering and model merging.

Through comprehensive ablations on 3 VL architectures: large vision-language models (LVLM), text-to-image diffusion models, and vision-language embedding models, and a case study in Southeast Asia (SEA) regional adaptation, we demonstrate the importance of Anthropogenic Regional Adaptation and GG-EZ, showing 5-15% gains in cultural relevance metrics across SEA while maintaining over 98% of global performance and even occasionally surpassing it.

Our findings establish Anthropogenic Regional Alignment as a foundational paradigm towards applicability of multimodal VL architectures in diverse regions and demonstrate a simple-yet-effective baseline method that optimizes regional value alignment while preserving global generalization.

Culture shapes how people interpret and navigate social interactions, yet existing Indonesian cultural commonsense benchmarks evaluate LLMs on short and isolated prompts, stripping away the dialogic context in which cultural nuances actually surface. We introduce CULTURETALK-ID, the first dialogue-based benchmark for cultural commonsense in Indonesian and its local languages, comprising 4,496 culturally grounded dialogues across 11 languages and 13 culturally salient topics, curated through a multi-stage human pipeline with native speakers to ensure authenticity. CULTURETALK-ID introduces three complementary tasks, namely dialogue-based multiple choice cultural commonsense reasoning, culturally faithful machine translation, and language steering, which jointly probe whether LLMs can understand, transfer, and generate culturally grounded language. Our results show that open-source models still underperform, particularly in the generation task and local language settings, highlighting a gap in their ability to capture and generate culturally grounded knowledge in conversational contexts.

Dialectal variation is a defining characteristic of many low-resource languages, yet most NLP approaches overlook this complexity—often assuming uniformity or arbitrarily selecting a single variant without reporting which dialect is used. This assumption severely limits the applicability of language technologies in real-world communication, especially for languages without unified orthography where dialects could differ in vocabulary and morphology. In this paper, we present the first comprehensive study of dialect processing for Indonesian local languages, a linguistically rich and underrepresented setting. We introduce IndoDialect, a high-quality conversational dataset comprising 14.2K conversations across four major local languages and eleven dialects, including five Javanese, two Minangkabau, two Sundanese, and two Dayak dialects. Building on this resource, we define three core tasks: (i) dialect-level language identification, (ii) machine translation across dialects, and (iii) dialect-controlled generation. Our experiments reveal that state-of-the-art multilingual models perform poorly in few-shot scenarios, excel at dialect identification after fine-tuning, but struggle with machine translation and dialect-controlled generation.

Idiomatic expressions pose a major challenge for multilingual NLP because their meanings shift between figurative and literal usage, often requiring context for accurate interpretation. Prior work has focused on high-resource languages typically evaluates isolated idiom-meaning questions, overlooking realistic discourse. We introduce MIDI, a multilingual idiom dataset spanning 3 high-, 3 medium-, and 12 low-resource languages, curated by native speakers. Unlike previous datasets, MIDI provides idioms embedded in both sentence-level and conversational contexts, capturing both literal and figurative readings. Benchmarking state-of-the-art models shows that idiom comprehension degrades in low-resource languages and that, in all resource tiers, literal interpretations are substantially harder than figurative ones. Conversational context improves performance but does not eliminate these disparities. Through controlled tests and interventions on hidden representations, we further separate memorization from reasoning, exposing core limitations of current models.

We investigate the robustness of Whisper-based automatic speech recognition (ASR) models for two major Indonesian regional languages: Javanese and Sundanese. While recent work has demonstrated strong ASR performance under clean conditions, their effectiveness in noisy environments remains unclear. To address this, we experiment with multiple training strategies, including synthetic noise augmentation and SpecAugment, and evaluate performance across a range of signal-to-noise ratios (SNRs). Our results show that noise-aware training substantially improves robustness, particularly for larger Whisper models. A detailed error analysis further reveals language-specific challenges, highlighting avenues for future improvements.

Culturally grounded commonsense reasoning is underexplored in low-resource languages due to scarce data and costly native annotation. We test whether large language models (LLMs) can generate culturally nuanced narratives for such settings. Focusing on Javanese and Sundanese, we compare three data creation strategies: (1) LLM-assisted stories prompted with cultural cues, (2) machine translation from Indonesian benchmarks, and (3) native-written stories. Human evaluation finds LLM stories match natives on cultural fidelity but lag in coherence and correctness. We fine-tune models on each dataset and evaluate on a human-authored test set for classification and generation. LLM-generated data yields higher downstream performance than machine-translated and Indonesian human-authored training data. We release a high-quality benchmark of culturally grounded commonsense stories in Javanese and Sundanese to support future work.

Despite Southeast Asia’s (SEA) extraordinary linguistic and cultural diversity, the region remains significantly underrepresented in vision-language (VL) research, resulting in AI models that inadequately capture SEA cultural nuances. To fill this gap, we present SEA-VL, an open-source initiative dedicated to developing culturally relevant high-quality datasets for SEA languages. By involving contributors from SEA countries, SEA-VL ensures better cultural relevance and diversity, fostering greater inclusivity of underrepresented languages and cultural depictions in VL research. Our methodology employed three approaches: community-driven crowdsourcing with SEA contributors, automated image crawling, and synthetic image generation. We evaluated each method’s effectiveness in capturing cultural relevance. We found that image crawling achieves approximately ~85% cultural relevance while being more cost- and time-efficient than crowdsourcing, whereas synthetic image generation failed to accurately reflect SEA cultural nuances and contexts. Collectively, we gathered 1.28 million SEA culturally relevant images, more than 50 times larger than other existing datasets. This work bridges the representation gap in SEA, establishes a foundation for developing culturally aware AI systems for this region, and provides a replicable framework for addressing representation gaps in other underrepresented regions.