Linguistics

This paper presents Mwando, a virtual educational assistant designed to support the teaching and preservation of shiKomori, the language of the Comoros Islands. The system covers the four main dialectal variants (shiNgazidja, shiMwali, shiNdzuani and shiMaore) through a knowledge base constructed from phrases, proverbs, dictionaries and grammar lessons. A multi-agent architecture combining vector search, a knowledge graph and web search fallback enables accurate and context-aware responses. Evaluation on 500 queries demonstrates strong performance on vocabulary lookup and grammar explanations, while qualitative case studies illustrate both capabilities and current limitations. This work represents an initial step toward computational support for shiKomori and provides a blueprint for developing AI-powered educational tools for other low-resource languages.

Instruction tuning has become the standard method for adapting large language models to follow human intent, yet existing instruction datasets are dominated by English-language general-knowledge tasks and lack coverage of specialized pedagogical domains. This paper presents IKS-Instruct, a dataset of 24,795 instruction-response pairs for teaching language models to deliver educational content grounded in Indian Knowledge Systems (IKS). The dataset spans seven languages (English, Hindi, Sanskrit, Tamil, Telugu, Kannada, and Malayalam), covers 41 pedagogical techniques from the Vedic oral and mathematical traditions, and is aligned with the Central Board of Secondary Education (CBSE) curriculum for classes 6 through 12. The pairs are derived from six source types: classical text corpora (Bhagavad Gita, Thirukkural, Sangam literature, Vedic texts), curriculum-aligned pedagogical templates, Vedic mathematical sutra demonstrations, bilingual instruction pairs, technique-grounded multi-turn dialogues, and cross-tradition comparative analyses. Quality is assessed through a multi-judge evaluation framework in which independent language models score responses on 12 dimensions including technique fidelity, pedagogical quality, factual accuracy, and IKS cultural depth. Under a uniform five-judge external panel (median aggregation over 1,201 stratified items), the strongest IKS-Instruct fine-tune of a compact 7B model reaches a median judge score of 6.39, within 0.15 of a strong general-purpose reference model (Nemotron-Nano at 6.54) at a fraction of its deployment cost, while the base model without IKS fine-tuning scores near zero on the IKS-specific dimensions. Model quality does not increase monotonically with data curation, a result we report together with the corresponding data-quality gains.

Standard subword tokenization algorithms such as Byte-Pair Encoding (BPE) and SentencePiece are trained predominantly on modern language corpora and produce inefficient segmentations when applied to classical Indian languages. Sanskrit, Tamil, and other classical Indic languages exhibit agglutinative morphology, productive sandhi (phonological fusion at word boundaries), and domain-specific vocabularies absent from general-purpose training data. This paper presents BHARATI, a set of SentencePiece BPE tokenizers trained on a balanced 781 MB corpus spanning seven languages (English, Hindi, Sanskrit, Tamil, Telugu, Kannada, and Malayalam) with native script support for all languages. We describe three successive tokenizer versions: v1 (English and Sanskrit only, with broken byte-fallback for Tamil), v2 (four-language support with byte-level fallback for southern languages), and v3 (full seven-language native subword coverage). Subword fertility analysis demonstrates that v3 averages 2.6 tokens per Indian Knowledge System (IKS) technical term, compared to 5.25 tokens per term with GPT-2's tokenizer and 3.75 tokens with the multilingual SentencePiece baseline, with the largest gains on a set of reserved IKS terms that are represented as single tokens by construction. On a held-out test set of 490 IKS-domain sentences (70 per language across seven languages, released with the measurement script), v3 reduces sequence length by roughly 90% relative to GPT-2 and byte-level encoding (which lack native Indic subwords) and by approximately 25% relative to the mBART-50 multilingual baseline, averaged across the six Indic languages, directly translating to increased effective context length for downstream language models. The tokenizer models (32,000 vocabulary), training scripts, and evaluation benchmarks are released under open licenses.

Large Language Models (LLMs) have transformed conversational AI, yet high-quality multilingual code-mixed dialogue resources remain scarce, particularly for Indic languages where speakers naturally alternate between English and their native language in both native-script and Romanized forms. We present IndicTalk, one of the largest multilingual Indic code-mixed conversational corpora, comprising over 13,28,604 event-grounded multi-turn conversations across 18 language varieties covering 9 Indic languages. The corpus is generated through a fully automated pipeline that combines real-world news grounding, persona-conditioned dialogue generation using multilingual LLMs, and automatic quality validation. Extensive linguistic, automatic, and human evaluations demonstrate that IndicTalk produces fluent, coherent, and naturally code-mixed conversations across both script variants. We will release IndicTalk to support the development and evaluation of multilingual conversational AI for underrepresented Indic languages. The dataset is available at: https://huggingface.co/datasets/LingoIITGN/IndicTalk .

Over fourty years after the initial publication of "Implications of Theories of Language for Information Systems" in MIS Quaterly, Lyytinen reflects about the origins of his publication and the developments in this area of research over the past decades. In the here presented interview, Lyytinen discusses the linguistic core of information systems also in light of recent trends and developments in the field, especially with regards to large language models and generative AI. Future research directions following a linguistic perspective on Information Systems (IS) research are outlined.

Cross-lingual mismatch remains a key source of overall degradation in modern speaker verification. The TidyVoice2026 Challenge targets this setting with text-independent verification, comprising 3,666 training and 808 development speakers in 40 languages and 2,200 evaluation speakers in 38 unseen languages, without language labels at test time. Starting from the official SimAM-ResNet34 baseline pretrained on VoxBlink2 and VoxCeleb2 and fine-tuned on TidyVoice, we revisit Nuisance Attribute Projection (NAP) as a simple language-normalization step in the embedding space. We estimate a compact language subspace from cross-language same-speaker differences and project embeddings onto its orthogonal complement before cosine scoring with Adaptive Symmetric score normalization. This reduces development EER from 2.97% with cosine and 2.70% with AS-Norm to 2.18% and yields a Codabench evaluation score of 8.40, showing that simple back-end language normalization can rival more complex systems.

Mathematical Word Problems (MWPs) are an important benchmark for evaluating natural language understanding and quantitative reasoning. Despite recent progress in high resource languages, Bengali remains underexplored due to the limited availability of large scale annotated datasets. In this work, we introduce PatiGonit22K, an expanded Bengali MWP dataset containing 22,441 problems, developed by extending the original PatiGonit dataset with a substantially larger collection of complex mathematical problems. The dataset includes both simple and multi operation equations, providing a balanced benchmark for evaluating mathematical reasoning across different difficulty levels. Each problem is carefully translated, annotated, culturally adapted, and verified to ensure linguistic consistency and mathematical correctness. By increasing both the scale and complexity of Bengali MWPs, PatiGonit22K provides a more comprehensive resource for future research on mathematical reasoning and educational NLP applications in low resource languages.

We present a systematic study of healthcare-domain cross-lingual transfer to address the scarcity of biomedical NMT resources for Arabic-script languages. We use Arabic and Persian as higher-resource pivots to improve translation for \textbf{four severely low-resource} targets: Dari (Afghan Persian, a standardised variety of Persian), Pashto, Sorani Kurdish (Central Kurdish, a major standardized variety of Kurdish), and Urdu (closely related to Hindi). Using LoRA fine-tuning on small decoder-only LLMs, we train \textit{domain-specific pivot adapters} and evaluate \textbf{three transfer strategies}: few-shot in-context learning, minimal supervised adaptation, and, to the best of our knowledge, for the first time in this setting, zero-data LoRA adapter merging. Supervised adaptation with just 500 sentences achieves near pivot-language quality for Dari (CHrF++ 41.01) and meaningful gains for Urdu (28.88), while adapter merging reaches within 3.5 CHrF++ of supervised adaptation for Dari at zero additional cost. Pashto and Sorani Kurdish remain insufficient for high-stakes clinical deployment exposing the limits of cross-lingual transfer when structural distance from the pivots is too great. LoRA adapter merging works surprisingly well for closely related languages, even without target-language biomedical data.

Surprisal theory holds that the human processing difficulty of a linguistic unit in context is an affine function of its surprisal under some language model. I argue this claim is a tautology without further constraint: for any non-negative difficulty measure over units in context, there exists a language model whose surprisal is an affine function of it under mild technical conditions. Therefore, because any pattern of difficulty is consistent with some language model, without an additional constraint on the language model, surprisal theory makes no falsifiable predictions. The tautology was long obscured by an assumption implicit in two decades of psycholinguistic work---that the relevant language model is the distribution that generated the training corpus, so that improving corpus fit improves predictions of human behavior. Recent empirical work has undermined this assumption, demonstrating that better corpus models can be worse predictors of processing difficulty. I conclude that breaking the tautology requires a rationalist intervention, i.e., the relevant language model must be derived from a non-empirically motivated model of the comprehender, which could be based on, for instance, memory constraints or processing goals, and that, thus, does not depend on the behavioral data surprisal theory is meant to explain.

We present DONDO, a family of open, permissively licensed automatic speech recognition (ASR) base models for African languages, built on the w2v-BERT 2.0 self-supervised speech encoder. DONDO comprises twenty-one monolingual models and five multilingual models spanning twenty-seven language varieties across Ghana, Sierra Leone, Nigeria, Senegal, Kenya and Zimbabwe. Models are fine-tuned primarily on read speech drawn from religious texts, which offer broad, license-clear and orthographically consistent coverage for languages that otherwise lack transcribed audio. We describe a two-step (and, for one family, three-step) learning-rate-annealed fine-tuning procedure that first adapts a shared multilingual model at a high learning rate and then anneals it to recover, and in several cases surpass, strong monolingual baselines. We further describe a lightweight language-conditioning mechanism that injects a one-hot language identity as a sequence of prefix frames prepended to the acoustic features, allowing a single multilingual checkpoint to be steered to a target language at inference. Across the five multilingual families the annealed models reach average word error rates (WER) of 10-13%, closing most of the gap to monolingual models while covering many languages in a single checkpoint. All models are released on the Hugging Face KhayaAI organisation under the Apache-2.0 license (attribution only) so that others may fine-tune them freely, including for commercial use. We provide a conservative estimate that the languages covered are spoken by on the order of one hundred million first-language speakers, and by substantially more when second-language use is included.

Quiz rooms, trivia nights, and quiz shows challenge human knowledge across a wide range of topics, from canonical facts to everyday culture. In this paper, we examine whether large language models (LLMs) can perform competitively in such settings, using quiz-style questions to test them on both common and niche topics. We introduce TriviaRoomQA, a multilingual benchmark designed to evaluate everyday, culturally grounded, and long-tail knowledge across 288 topics. The benchmark contains 3,300 parallel multiple-choice questions in six European languages and additional 5,340 French-only questions for a more fine-grained case study. We evaluate 30 open-weight LLMs from European, Asian, and North American providers, covering models from 7 to 70B parameters. We find that models are strong on knowledge-intensive topics such as history, geography, and mathematics, but substantially weaker on everyday popular-culture topics such as celebrities, music, movies, and news. Moreover, model performance varies across languages even for the same underlying questions, suggesting that access to factual knowledge is not always language-independent. In sum, our dataset and experiments demonstrate an important knowledge gap which is not captured by existing academic-based saturated benchmarks.

This study investigates vowel-inherent spectral change (VISC) in spontaneous conversational Mandarin. Using the generalized additive model and word embeddings from distributional semantics, we show that, when controlling for variables such as vowel duration, gender, speaker identity, co-articulation, vowel identity, and utterance position, vowel formant trajectory dynamics have word-specific components that are tied to their meaning in context: The F1 and F2 trajectories of words can be predicted from their contextualized embeddings with an accuracy that substantially exceeds a permutation baseline. Challenging modular cognitive models of speech production, these results indicate that, words' semantics co-determine the fine details of their articulation.

Phonetic forced alignment is a key technique in phonetic research, yet existing alignment systems lack specialized models for low-resource language varieties. We address this by training text-dependent and text-independent aligners for Chengdu Mandarin using a 17-hour corpus and a custom G2P dictionary. We trained a text-dependent GMM-HMM model (Chengdu-MFA) and fine-tuned a pretrained audio encoder on frame classification with Chengdu-MFA's pseudo label for text-independent alignment (Chengdu-FC). Evaluation on an expert-annotated test set show that both methods significantly outperform Standard Mandarin baselines. Chengdu-MFA reduced average phone boundary differences by 31.8%, while Chengdu-FC achieved a 61.2% reduction. This work establishes a practical bootstrapping pipeline for developing accurate aligners for under-resourced varieties without labor- and time-intensive manual annotation.

Slang is a central component of everyday language, reflecting linguistic creativity, social identity, and cultural change, yet its dy- namic and non-standard nature makes it difficult to model computationally. We present the first large-scale computational study of slang.gr, a crowdsourced lexicon of Greek non-standard language, combining lexical content, user-generated tags, and interaction data. To enable the systematic analysis, we map noisy folksonomic tags to a structured multi-layer taxonomy capturing both semantic categories and sociolinguistic metadata. Using this representation, we analyze the linguistic structure of Greek slang and the behavior of its contributor community. We find that slang is strongly centered on person-related and evaluative language, exhibits high morphological creativity, and is shaped by highly skewed participation with short user lifespans and overlapping communities. Building on these signals, we introduce a community-based confidence score for definitions that integrates user roles, interaction patterns, and moderation signals. Our results show that taxonomy-based representations improve interpretability while retaining meaningful aspects of behavioral structure, enabling a more structured and interpretable analysis of confidence signals. Overall, this work establishes slang.gr as a computational resource for non-standard Greek and provides a foundation for sociolinguistic NLP, bias analysis, and the study of informal language in LLMs.

Culture is lived through conversation, 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.

Grievance is one of the warning signs analysts look for when assessing threats of violence. It is increasingly measured at scale from online text, most often with word-level lexicons like the Grievance Dictionary that score by matching weighted terms. Such matching is a fast and transparent proxy, but it cannot resolve whether a term is asserted, quoted, negated, or condemned. These lexicons are also often evaluated on pools enriched with the very examples they retrieve, so a high score partly reflects agreement with the lexicon's own selection rule. Examining a five-language, 2{,}000-item evaluation pool, we find its halves separated almost perfectly by the lexicon itself: every item labeled ``random'' is in fact lexicon-negative, so the lexicon's apparent macro-AUROC of 0.686 collapses to a 0.500 floor fixed by construction. We keep the dictionary's 22-construct ontology but replace term matching with context-reading models, evaluated on a non-circular benchmark that separates unconditional-random, lexicon-positive, and lexicon-negative strata across five languages. Reading the full post rather than the target sentence alone helps most where the lexicon is silent, raising average precision on lexicon-negative text from 0.14 to 0.20, with the largest gains on quoted, implicit, and cross-sentence grievance. Together, these results show that grievance is measured more faithfully by reading the surrounding context, and more honestly when tested on text the lexicon did not select. We release our code and benchmark at https://github.com/behavioral-ds/multilingual_grievance.

Value alignment of Large Language Models (LLMs) has been shown to be culturally biased toward Western norms. This results in the mishandling of local values in multilingual societies such as Sri Lanka that have their unique cultural dynamics. Existing benchmarks overlook Sri Lankan-contextualized values in its official language Sinhala, hindering culturally sensitive evaluation and fine-tuning. To bridge this gap, we propose LKValues, the first survey-grounded resource suite for Sri Lankan value alignment. From a trilingual survey of 205 respondents, blending adapted global frameworks and LLM-elicited local constructs, we derive 40 majority-endorsed societal values. Using these values, we construct LKvaluesIT, a Sinhala-English news-derived instruction corpus containing 150k scenario-based instances, and LKvaluesBench, a value-sensitive evaluation benchmark of 1,000 instances. We evaluate a set of proprietary and open-weight LLMs with LKvaluesBench. We fine-tune three open-weight base models (Qwen3.5-4B-Base, Qwen3.5-9B-Base, and Aya-Expanse-8B-Base). Our experiments show that newer and larger LLMs still exhibit low-resource and cultural value-alignment gaps. LKValues fine-tuning improves Qwen-family models in English and Sinhala, reducing invalid outputs and cross-lingual disparities, though gains remain model-family dependent. These highlight LKValues efficacy in embedding Sri Lankan values, offering a replicable pipeline for low-resource, country-specific pluralist value alignment. The dataset is publicly available at https://github.com/NextME14/LKValues.

Coordination, a fundamental linguistic structure, remains a subject of intense debate, and its exact nature continues to elude theoretical linguistics. A common view holds that only same-category constituents can be conjoined, which has been challenged by the many grammatical unlike coordinations found in natural language. Treating language models as a computational testbed, we investigate whether the acquisition of unlike coordination requires direct exposure in the training data, or whether it can emerge organically from general compositional abilities. Using Filtered-Corpus Training (FiCT), we train GPT-2 models on corpora from which all instances of unlike coordination have been removed. We find that direct exposure is not necessary: models trained on filtered data successfully generalize to unlike coordination, achieving perplexity and grammaticality judgments comparable to models trained on unfiltered text. Furthermore, our analyses of internal representations indicate that language models process unlike coordination by treating the conjoined elements as belonging to similar structural categories or through a mechanism akin to deletion, both of which appear learnable from exposure to alike coordination alone. This work contributes to the growing understanding of how language models internally represent linguistic structures, while also adding to the broader debate on coordination by showing how models generalize and process unlike coordination without direct exposure.

Surprisal Theory is often characterized as a computational-level explanation per (Marr, 1982). We argue in this work that, even though a computational level narrative has been used to support "representation-agnostic research" within computational psycholinguistics, the movement toward black box systems embodied by large language models (LLMs) does not exempt modelers using the surprisal metric from the representational decisions required by computational-level characterizations. In fact, we argue that the uncritical use of LLM-surprisal obfuscates the representational and algorithmic-level commitments of different models. In three analyses, we show that the choice of algorithm and model architecture play significant roles in the computation of language model probabilities. We advise that researchers who wish to test Surprisal Theory re-evaluate the practice of treating large language model probabilities as interchangeable

Large language models (LLMs) are known to be sensitive to prompt and input formulations. However, existing studies have focused on lexical realization and largely ignored constructional choice. This paper studies whether linguistic construction can systematically shift LLM decisions and where these shifts can be causally localized inside the model. We use political stance judgment as a meaning-sensitive case study and extend an English political statements dataset, resulting in six controlled linguistic rewrite types that preserve or invert the meaning of a statement. Experiments on four open-weight models show that stance instability affect both meaning-preserving and meaning-inversing rewrites. Because output shifts reveal that rewrites affect stance, but not where in the model, we apply activation patching, where activations from the original statement are substituted into the forward pass for the rewritten statement and measure which components recover the original stance distribution. The results show that mid-to-late decoder layers, especially block outputs at the final prompt position, provide the strongest restoration signal.

Although large language models (LLMs) have recently gained traction in recommender systems due to their strong reasoning capabilities and extensive world knowledge, previous LLM-based agents suffer from hallucination and context-length limitations, and thus are not suitable for full-ranking recommendation tasks. To circumvent these limitations through architectural design rather than modifying the LLM itself, we propose an agent-based recommendation framework, memory-based $\textbf{P}$ersonalized $\textbf{R}$ecommendation $\textbf{T}$ool learning via autonomous language $\textbf{A}$gents (PRTA), in which an LLM acts as a central planner interacting with multiple recommendation models as tools. The LLM-based agent is responsible for high-level reasoning and personalized tool selection, while traditional recommendation models perform full-ranking scoring, leveraging their scalability in modeling behavioral patterns. To support personalized tool selection, we design reflection mechanisms that enable the agent to evaluate and compare tools for each user based on user profiles and candidate ranked lists. Extensive experiments across three public datasets demonstrate the superiority of \modelname over traditional recommendation and LLM-based baselines in improving full-ranking recommendation performance.

Although Large Language Models (LLMs) demonstrate remarkable multilingual fluency, their internal knowledge representations remain disproportionately biased toward high-resource languages. This leads to cross-lingual factual inconsistency, where they shift their empirical answer distributions based solely on the prompt language. We investigate whether these biases can be mitigated at inference time, forcing an English-prompted model to answer as if it were queried in target languages (German, Spanish, Bulgarian), and evaluate four intervention strategies: zero-shot contextual steering (persona prompting), internal representation manipulation via Contrastive Activation Addition (CAA), and lightweight weight modification via Direct Preference Optimization (DPO) trained on benchmark-derived factual data as well as conceptual generalization data. To assess alignment, we curate a multilingual factual dataset alongside a novel generalization benchmark comprising culturally rooted queries to determine whether factual interventions transfer to broader target-centric preferences. Experiments on Gemma 3 12B Instruct reveal persona prompting to be the strongest overall intervention, balancing efficacy, safety, and out-of-domain generalization. While CAA yields sharp inconsistency benchmark shifts, it is configuration-sensitive and risks knowledge degradation. DPO-based adapters offer permanent, yet narrower and less transferable gains. These findings suggest that cross-lingual inconsistency is at least partly a selection problem, and that simple contextual interventions may outperform more invasive methods for robust, transferable alignment.

Reliable Text Difficulty Assessment is a prerequisite for valid text simplification workflows and personalized learning applications. However, the development of robust assessment models is severely hindered by a critical bottleneck: the scarcity of expert-annotated corpora containing fine-grained difficulty levels (e.g., CEFR), particularly for lower-resource languages. This paper addresses this data scarcity problem in the context of a low-resource European language. We propose a cross-lingual data augmentation strategy that leverages machine translation to transfer labeled resources from high-resource languages to the target low-resource language. We train BERT-based regression models to predict difficulty scores and investigate whether synthetic, translated data can effectively supplement native training sets. Our experiments demonstrate that augmenting scarce native data with machine-translated corpora significantly improves the accuracy of difficulty estimation, offering a viable solution for languages lacking extensive expert annotations.

Automatic speech recognition (ASR) for African languages is constrained by orthographic inconsistency, annotation artifacts, missing audio, speaker and domain imbalance, and evaluation procedures that differ from deployment. We present an end-to-end engineering study adapting NVIDIA Nemotron 3.5 ASR Streaming 0.6B to Kikuyu, Dholuo, and Kalenjin. Starting from a Kenyan Swahili-adapted checkpoint, we retain its cache-aware FastConformer RNN-T, prompt conditioning, and streaming decoder during full-parameter fine-tuning. The study covers corpus auditing, Unicode normalization, split checks, duration filtering, low-rate continuation, validation-based checkpoint selection, true-streaming evaluation, artifact preservation, and isolated serving. On internal, adaptively consulted evaluation sets excluded from gradient updates at context [56,13], selected Kikuyu and Dholuo models achieve 42.97% and 33.98% WER, respectively. Dholuo records 9.59% CER and 8.13% no-space CER under its frozen historical label policy; Kikuyu records 7.79% no-space CER. Kalenjin remains a work in progress: v1-v reaches 68.74% WER on a 2,411-row clean-v3 diagnostic subset excluding long-pause annotations, digit-bearing references, and targets shorter than three tokens. Its checkpoint selection used a mixed-source validation manifest containing test-origin rows, so the score is not an independent generalization estimate. We also report negative findings involving non-speech labels, short-utterance over-generation, boundary-sensitive WER, and cloud job-lifecycle failures. We make no state-of-the-art claim because the internal sets, repeated consultation, and normalization differ from public benchmarks. This work provides an auditable account of adapting a multilingual streaming model into language-specific systems without discarding streaming constraints.

Goal-directed visual processing is a hallmark of human visual intelligence, resulting in representations that support downstream tasks such as categorization or search. Though vision-language models (VLMs) are often faced with these same tasks, their ability to recode visual representations when presented with goal-directed language remains poorly characterized. Indeed, prior work largely treats visual representations in VLMs as static repositories of visual information that are manipulated by language representations. In the present work, we provide evidence for two concrete instances of language-induced recoding of visual representations. First, we identify an abstract reference representation that denotes which objects are goal-relevant under a natural language prompt. We extract contrastive steering vectors corresponding to this reference representation and demonstrate that they are causally implicated in model predictions. These reference representations are abstract in that they generalize to different objects, different task contexts, and even from synthetic to naturalistic images. Second, we demonstrate language-induced attribute modulation: later layers selectively amplify goal-relevant attributes in visual representations of objects. We demonstrate this phenomenon across a range of different prompts. Finally, we provide a causal intervention that demonstrates that attribute modulation mediates a VLM's response distribution. Together, our results support a more dynamic account of cross-modality processing in VLMs -- rather than vision tokens serving as static repositories of information, they are modulated to support queries articulated in language.

Vision-language-action (VLA) models have shown impressive generalization, but often lack interpretability and can struggle to follow precise natural language instructions that encode spatial, temporal, and logical requirements. We propose a hierarchical framework that uses Signal Temporal Logic (STL) as a shared representation connecting high-level language understanding with low-level robot execution. A high-level policy leverages a VLM to decompose language instructions into high-level subtasks, generate STL specifications for each subtask, and choose a low-level policy for executing each subtask. The STL specifications translate language-derived intent into precise constraints, and the low-level policy selection determines whether those constraints are enforced directly through STL-guided model-predictive control or monitored during execution of a learned policy for perceptually complex, or contact-rich behaviors. By integrating STL into plan validation, low-level policy, subtask monitoring, and replanning, our framework enables language-derived plans to be checked, optimized, and revised at runtime using a common formal structure. We evaluate the approach on a real-world tabletop domain, demonstrating how formal specifications can improve the precision, reliability, and interpretability of language-conditioned robot planning.

This paper reports on a collaboration between the Directorate-General for Translation (DGT) and the European Master's in Translation (EMT) to localise the MMLU dataset into 11 European languages. Beyond creating a more inclusive benchmark for LLM evaluation, the project offers master's students authentic, project-based professional training in translation, revision, project management, and multilingual coordination, while highlighting key methodological, administrative, and workflow challenges.

Users frequently express their beliefs to large language models (LLMs). In some situations, the LLM should accept these contextual beliefs as true. In others, they should stick to their prior knowledge. Notably, users' expressions of belief (EoBs) can take linguistically diverse forms - using presuppositions, evidential and certainty markers, or varied tones - each of which may have a different persuasiveness over the LLMs. We introduce a typology to systematically evaluate how different EoBs affect whether models follow context versus prior knowledge. The typology is grounded in four linguistically motivated dimensions: form, evidentiality, epistemic stance, and tone, spanning 17 fine-grained types. By pairing these EoBs with world knowledge facts, we generate controlled EoB-query pairs that isolate the effect of linguistic variation. Using this benchmark, we evaluate 16 LLMs that differ in architecture (Llama3, Qwen3, Gemma3), scale (1B-30B parameters), and training stages (base vs instruct). We identify meaningful variations in response behavior across these axes, e.g., that bigger models and instruction models tend to be less context-following than smaller models and base models. We further identify specific EoBs that statistically significantly persuade LMs more consistently than others. Our work reveals systematic patterns in how linguistic framing affects LLM context integration, with implications for prompt engineering and model robustness.

Many Bangla words are at once personal names and culturally loaded common nouns, "Maya" is both a girl's name and a word for affectionate compassion. Choosing the right reading demands cultural knowledge that is scarce in the pretraining data of modern language models. We introduce Culturally Entangled Homograph (CEH) disambiguation and build a Bangla benchmark of 1,516 expert-verified sentences (3,032 labelled occurrences) in which one word appears twice with two distinct readings, each labelled with a culturally grounded category and an explanation of the reasoning behind it. Across open- and closed-source models, we find a systematic dominant-meaning bias: models default to the common-noun sense and overlook the name. A Bangla-specific model fails under every prompting regime we test, showing that language-specific pretraining alone does not confer cultural grounding. We further show that contrastive chain-of-thought prompting can sharply reduce this bias without training, and that distilling cultural explanations teaches small (1-3B) models to reason toward the correct reading rather than memorise labels, cutting dominant-meaning bias from as high as 100% to under 5% and turning the failed Bangla-specific model into our strongest system. Dataset and code are available at https://github.com/ashuvo25/BanglaCEH.

As large audio language models (LALMs) advance, robust evaluation frameworks have become essential. In this context, Spanish speech understanding under realistic acoustic conditions has received particularly little attention. We introduce ESCUCHA, the first Spanish speech understanding benchmark designed to evaluate LALMs across heterogeneous acoustic conditions and reasoning abilities. ESCUCHA comprises 1,000 human-curated questions paired with audio, totaling 162.9 hours sourced directly ``from the wild'' rather than drawn from existing datasets, with durations ranging from a few seconds to over 80 minutes. The benchmark emphasizes reasoning, spanning 9 perceptual and 10 reasoning categories, and it captures linguistic diversity through multiple Spanish accents and non-normative speech. ESCUCHA further includes multi-audio questions, spoken questions, and audio instructions, and it flags which questions support open-ended evaluation. Benchmarking several state-of-the-art multimodal and speech models reveals substantial performance gaps relative to trained humans.

Measuring conversational states such as cognitive load and conversational power from multimodal behavior requires characteristic features that are not only predictive but also reliable across task contexts. We present a three-dimensional evaluation framework assessing predictive accuracy, cross-task generalizability, and test-retest reliability, applied to interactional, acoustic, and linguistic features extracted from dyadic conversations during collaborative tasks performed over a video-conferencing platform (AVCAffe dataset; 53 dyads, 9 tasks). Our results show that no single feature family dominates all three dimensions. Linguistic features show the highest predictive accuracy for cognitive load but collapse under cross-task evaluation, revealing sensitivity to task-specific vocabulary. Additionally, acoustic reliability, often reported as evidence of feature stability, degrades once speaker identity is controlled, confirming that standard prosodic features measure vocal characteristics rather than conversational state. Interaction features provide the only genuinely reliable signal, unchanged after speaker normalization. Interestingly, classifying power role remained near chance baseline across all conditions, indicating limitations of task-level aggregated behavior for predicting power role in conversation. Our findings reveal three insights: (1) linguistic features predict best but generalize poorly across task contexts; (2) acoustic reliability collapses to near-zero once speaker identity is controlled, challenging standard evaluation practice; and (3) interaction features provide the only genuinely reliable signal, with floor dominance predicting within-dyad cognitive load asymmetry. These results argue for speaker normalization and multi-dimensional evaluation as prerequisites for context-aware, robust multimodal feature selection in conversational systems.

Safety evaluation of large language models is conducted predominantly in English and predominantly on frontier systems. Neither condition describes how such models are encountered in low-resource health settings, where small quantised systems are run locally and queried in local languages. We ask whether clinical safety established in English transfers to Hausa, and whether any failure is attributable to the language, the clinical task, or the class of model that low-resource deployment admits. Matched English-Hausa question pairs were built for three conditions of high burden in northern Nigeria: malaria, sickle cell disease, and tuberculosis, probing knowledge recall, emergency triage, a leading question inviting a contraindicated action, and a traditional-remedy claim. Six models were evaluated: five locally deployable systems of 4-9 billion parameters, two medically fine-tuned, and one frontier system. All 128 responses were scored against Nigerian national treatment guidelines by two fluent Hausa speakers working independently and blind to one another. Among locally deployable models, mean clinical correctness fell from 1.57 in English to -0.03 in Hausa, on a scale where 2 denotes a correct answer and -1 an actively harmful one. The frontier model moved from 2.00 to 1.75 and produced no response judged harmful in either language. Drift was consistent across all three conditions. Inter-rater agreement was substantial for clinical correctness (kappa = 0.70); agreement on harm was initially poor (kappa = 0.22) and is examined in detail. Because a frontier model answers the same questions competently in Hausa, the deficit is a property neither of the language nor of the clinical material, but of the deployable tier.

Prior work on LLM-generated text has demonstrated quantitative and qualitative departures from text produced by humans. LLM-generated texts differ from human writing in style, resulting in a characteristic textual "feel," while the semantic range of LLMs is much restricted compared to that of humans. In this contribution, I note simple but consistent patterns in the statistical distribution of n-grams within LLM-generated text. Via qualitative analysis of these n-grams, I reveal deficiencies in LLM style. Because higher-order n-grams correlate to semantic content, I conclude that questions of style and semantics are not cleanly separable.

Evaluating large language models (LLMs) across languages remains challenging, as most multilingual benchmarks rely on translated English datasets, often obscuring linguistic and cultural specificity in the target language. This issue is particularly pronounced for less-resourced languages such as Kyrgyz, where reliable natively authored evaluation data are scarce. Building on previously introduced Kyrgyz-language evaluation datasets, this work reports the first systematic and large-scale evaluation of LLMs in Kyrgyz using the KyrgyzLLM-Bench benchmark suite. KyrgyzLLM-Bench comprises two natively authored datasets$-$KyrgyzMMLU and KyrgyzRC$-$together with carefully translated and manually post-edited versions of WinoGrande, HellaSwag, BoolQ, and TruthfulQA. We evaluate 26 open- and closed-source LLMs under zero-shot and few-shot settings, analyzing model performance, cross-lingual transfer, and the impact of translation artifacts on evaluation reliability. Across families and tasks, model rankings transfer broadly from English to Kyrgyz on WinoGrande and BoolQ, and to a lesser extent on MMLU, while HellaSwag exhibits a substantial English-Kyrgyz performance gap consistent with translation-induced plausibility shifts. Few-shot prompting improves several open-source models on reading comprehension but behaves inconsistently for proprietary models on translated tasks. We publicly release all datasets, evaluation code, and per-model results, and integrate the Kyrgyz tasks into a widely used multilingual evaluation framework to support future research on Kyrgyz NLP.

Developing Automatic Speech Recognition (ASR) for morphologically rich, low-resource languages such as Assamese is challenging due to insufficient annotated speech data. The pretrained Whisper model performs poorly on Assamese speech recognition tasks. This paper presents a controlled, fine-tuned Whisper-based Assamese ASR system trained on the Mozilla Common Voice 24.0-Assamese corpus. A hardware-aware optimized training pipeline is implemented for resource-constrained environments, employing mixed-precision training and gradient accumulation on Tesla 4 Graphics Processing Units (T4 GPUs). The proposed fine-tuned model significantly outperformed the Zero-shot baseline, yielding Word Error Rate (WER), Character Error Rate (CER), Match Error Rate (MER), and Word Infomation Loss (WIL) of 43.17%, 13.18%, 43%, and 64.81%, respectively, achieving significant relative improvements of 78.26%, 93.10%, 57.0%, and 35.19% over the baseline. Semantic evaluation of the fine-tuned model also demonstrates notable improvement over a zero baseline, attaining Bilingual Evaluation Understudy (BLEU) and Metric for Evaluation of Translation with Explicit ORdering (METEOR) scores of 30.81 and 0.5262, respectively. Additionally, the predicted hallucination rate and Real-Time Factor (RTF) are substantially improved by 96.70% and 32.38%, compared to the zero-shot baseline.

Fine-grained offensive language detection organizes labels into a hierarchical structure, for which two modeling paradigms exist: cascaded decomposition and joint multi-task modeling. Prior work rarely provides a direct, controlled comparison of the two paradigms in terms of accuracy, parameter count, and inference latency, and rarely verifies whether a chosen class-imbalance handling strategy is actually optimal. This paper proposes a three-level cascaded detection system whose training strategy is customized per subtask, together with two verification mechanisms. First, a controlled ablation study determines the best class-imbalance handling strategy for each subtask. Second, a joint multi-task model with a shared encoder is trained as an architectural control, yielding real measurements along the dimensions of accuracy, parameter count, and inference latency. Experiments show that the cascaded system attains macro-F1 scores of 0.795, 0.716, and 0.557 on the three subtasks of the official test set. The ablation study reveals that configuring the loss function purely by imbalance-severity intuition is suboptimal; reconfiguring based on the ablation results improves both performance and stability. End-to-end cascade evaluation shows that roughly one-fifth of the errors in the cascade pipeline originate from the first-stage filter and cannot be corrected by subsequent stages. Relative to the joint multi-task model, the cascaded architecture achieves higher accuracy on all three subtasks, with a 7.1-point macro-F1 gain on the most severely imbalanced subtask, at the cost of three times the parameters and 1.67 times the inference latency. Together, these results establish an explicit, quantifiable trade-off between the accuracy advantage of cascaded architectures and their deployment cost.

As Large Language Models (LLMs) grow more capable across diverse tasks, their (in)ability to generalize remains difficult to quantify and poorly understood beyond limited domains. In particular, LLMs are known to struggle generalizing multilingually, to languages outside of English, and that are poorly attested in their training data. To understand why this may be, and what enables some models to perform better than others, we turn to a long history of work across the cognitive sciences, arguing that successful generalization derives from appropriate representations in similarity space. We look at how well LLMs' representations capture the hierarchical similarity structure between distinct languages. Strikingly, we show LLMs' latent representations largely recover the hierarchical structure of the Indo-European language family tree -- grouping languages that are members of the same subfamily closely together in representation space. Furthermore, we show that the degree to which models reflect the similarity structure of languages correlates with their performance on XNLI, a multilingual natural language inference benchmark. This extends classic work on similarity-driven generalization at scale, showing how models that represent similar languages similarly generalize better from one language to another.

We present JOR-Bench, a collection of five Japanese-language benchmarks for evaluating the ability of large language models (LLMs) to formulate and solve operations research (OR) problems. Each benchmark is a Japanese translation of an existing English benchmark: IndustryOR, MAMO Complex LP, NL4OPT, OptiBench, and OptMATH, covering 1,319 problems spanning linear programming, mixed-integer programming, non-linear programming, and combinatorial optimization. JOR-Bench is a solver-independent benchmark that can be used with any solver or programming language, and consists of pairs of Japanese problem statements and expected numerical answers. We evaluate seven LLMs, including multilingual general-purpose models and Japanese-specialized models, on both the original English and the new Japanese versions, and compare performance across languages. For the main evaluation, we standardize execution with the Python interface to OR-Tools to make model outputs comparable and reproducible with open-source software. Our results show that OR formulation ability is largely language-neutral for strong multilingual models; the overall average accuracy difference between English and Japanese is only $-0.3$ pp. Yet error analysis reveals subtle cross-lingual differences, including a pragmatic disambiguation failure in some domains that causes models to output decision-variable values instead of the objective value when the prompt is in Japanese.

Language models encode text as subword tokens, raw bytes, or rendered pixels, but these encodings are usually compared under modeling constraints that expose different amounts of linguistic content to models across different languages. We instead ask what each encoding preserves when both the content and the downstream capacity are controlled. Using verified parallel sentences across thirteen languages and five scripts, we compare tokens, bytes, and pixels through a shared bottleneck whose width is swept to trace rate-utility frontiers. This separates three quantities that are often conflated: the number of input positions an encoding creates, the latent capacity available after encoding, and the task-relevant information that survives compression. We evaluate three utilities: surface form preservation, cross-lingual sentence alignment, and topic classification. No encoding dominates across tasks or capacity regimes. Pixels preserve surface form best, bytes preserve cross-lingual alignment best, especially in same-script multilingual settings, and tokens support topic prediction best. These performances are not explained by sequence length alone. Short inputs can discard useful meaning, while long inputs can preserve information that compresses well. Choosing an encoding is therefore not a fixed preference for tokens, bytes, or pixels, but a rate-utility tradeoff that depends on the task, language mix, capacity regime, and compute budget.

Increasingly, speech and language processing tasks take either audio or text directly rather than extracting features from these as the input to the classifier or regressor. Often these systems make use of complex, for example transformer-based, processes that have the ability to derive highly non-linear mappings between the input and the output. Unfortunately these systems can also learn ''shortcuts'' where the classifier is overly reliant on particular aspects of the input to yield the output. For the task of language proficiency assessment, this over-reliance can enable learners to increase their score by exploiting the shortcut rather than improving their ability. This paper introduces a novel training criterion that is able to reduce the classifier's reliance on shortcuts, thus for example limiting this option for malpractice in language assessment. This process is illustrated on two forms of assessment system, one based on the audio the other on the speech recognition text. The results show that, for both systems, there is higher correlations with features that could be exploited for malpractice than expected from the human reference, indicating an over-reliance on these features. By introducing the modified training criterion, this correlation can be reduced to be closer to the reference correlation.

Moderation systems increasingly rely on external toxicity tools, but those tools are unreliable under code-mixing, transliteration, slang, and language mismatch. We study the \emph{conditional reliability} of toxicity priors in Indian multilingual and code-mixed short text: English toxicity, Indic abuse, and rule-based severity cues can be useful evidence, but only in some linguistic and abuse-severity contexts. We propose ToxGate, a trust-fusion head that conditions each auxiliary signal on the encoder representation before adding it to the prediction state. Across three short-text abuse datasets, four transformer encoders, and five seeds per setting, ToxGate improves over matched plain encoders in 10 of 12 in-domain settings and 7 of 8 transfer settings. The largest and most interpretable gains occur in high-risk moderation slices, including explicit slurs, violent threats, and cross-dataset transfer. The broader lesson is that moderation systems should treat external toxicity tools and priors as conditional evidence rather than fixed features or ground truth, in focused ablations, source-specific gating gives the strongest results in transfer, severe-abuse slices, and high-risk triage.

Multilingual pre-trained language models (PLMs) exhibit degraded performance on low-resource, non-Latin-script languages, driven by high out-of-vocabulary (OOV) rates and excessive subword fragmentation that result from Latin-script-centric tokenizer training. We introduce VEXMLM, a vocabulary-extended variant of XLM-R targeting the two highest-resource Ge'ez-script languages, Amharic and Tigrinya, and further evaluated on 17 additional low-resource African languages (19 total). We train a language-specific SentencePiece tokenizer on curated Amharic and Tigrinya monolingual corpora, extend XLM-R's vocabulary with 30,000 Ge'ez-script subwords derived from this tokenizer, and initialize their embeddings by averaging the embeddings of their constituent subwords under XLM-R's original tokenizer. VEXMLM is trained in two stages: (1) continued masked language modeling over the extended vocabulary on the curated corpora, and (2) supervised fine-tuning on question answering (QA), named entity recognition (NER), and sentiment analysis (SA). On Amharic/Tigrinya QA, VEXMLM achieves 87.0 EM /90.0 F1, versus 66.0 EM/78.0 F1 for XLM-R and 74.0 EM/ 78.0 F1 for Glot500. On SA, VEXMLM reaches 80.0% accuracy versus 77.0% (XLM-R) and 46.0% (Glot500). On NER, VEXMLM raises OOV-token entity accuracy from 81.4% to 94.3%, averaged over 11 of the 19 evaluated languages for which OOV analysis was possible. Our contributions are: (i) a vocabulary-extension and embedding-initialization procedure tailored to Ge'ez script; (ii) a two-stage training strategy under which vocabulary and continued-pretraining gains on Amharic/Tigrinya transfer to 17 typologically related, unaugmented African languages; and (iii) an evaluation spanning both intrinsic tokenization metrics (vocabulary coverage, fertility, OOV rate) and extrinsic task performance across all 19 languages.

Large Language Models (LLMs) perform differently on identical programming tasks when prompted in different natural languages, a phenomenon known as language bias. While this behavior has been widely studied for general text generation, its impact on code generation quality and programming conventions remains largely unexplored. We investigate how the language used to describe programming tasks affects the source code generated by GPT-4o mini, DeepSeek, and Claude. Our study comprises 460 coding tasks spanning Python (230) and Java (230). We translate and manually curate the original English prompts into Chinese, Hindi, Spanish, and Italian while preserving their technical meaning. We evaluate the generated code using multiple dimensions, including functional correctness through test pass rates, structural quality using established code metrics, issues detected by static analysis tools, and lexical characteristics such as the language used in identifiers and comments. Our results show that (i) English prompts do not consistently produce the best functional correctness or code quality, (ii) the impact of prompt language depends on both the programming language and the LLM, and (iii) generated code frequently mixes English with the prompt language in comments and string literals. These findings provide the first curated multilingual benchmark for studying language bias in code generation and offer insights for developing more robust multilingual code generation systems.

This study examines the cross-prompt generalization and first-language (L1) scoring effects of a LoRA-adapted open-weight large language model (Gemma-3-27B-it) applied to automated essay scoring. Using the identical model and inference configuration reported in "AiAWE: An Open-Source LLM Automated Writing Evaluation System Using LoRA-Adapted Instruction-Tuned Models" (Gayed, 2026), which was fine-tuned on 480 argumentative essays from two prompts, we evaluate scoring accuracy on the full TOEFL11 corpus: 12,100 essays written by test-takers from 11 first-language backgrounds across eight prompts, none of which were seen during training. The model's raw scores (0.5-5.0) are mapped to the same three proficiency bands (low, medium, high) used by ETS, enabling direct comparison. The model achieved an overall band agreement of 77.79% and a quadratic weighted kappa of 0.702, with adjacent-band agreement of 99.98%. Accuracy was stable across all eight unseen prompts, with no advantage for prompts thematically related to the training data, indicating robust cross-prompt generalization. However, the model exhibited a systematic, L1-linked scoring offset. Within every proficiency band, essays from European-language backgrounds received consistently higher scores than essays from East-Asian-language backgrounds, a pattern not attributable to the composition of the fine-tuning data. This is the first large-scale L1 fairness analysis of a fine-tuned open-weight LLM for automated essay scoring.

This study examines feedback in English as a Foreign Language (EFL) writing contexts, focusing on written corrective feedback (WCF). Large language models (LLMs) can provide WCF at scale, but aligning them with pedagogical best practices remains an ongoing challenge. WCF meeting criteria like factuality or relevance may still be unsuitable for learning contexts, highlighting the need for extrinsic evaluation based on the learner's perspective. We deployed WCF systems in a university-level EFL class with nearly 2,000 students, collecting over 20,000 drafts. We evaluated the generated WCF from two perspectives: intrinsic evaluation by experienced English teachers using a rubric, and extrinsic evaluation via student feedback and engagement metrics. Results revealed low alignment between teacher expert ratings and student feedback. These findings suggest that traditional expert evaluation alone may not fully capture WCF's usability or helpfulness from the learner's perspective, highlighting the importance of learner-centered evaluation frameworks for AI-based applications in language education.

Adapting a multilingual encoder to a new language \emph{and} a new task with only a few hundred gold examples is a common low-resource NLP setting, yet the two axes are usually fused via an expensive language--task fine-tuning run. We ask whether they can instead be trained separately and recombined in weight space. \DeltaMergeLowRes{} learns a language delta $Δ_L$ from unlabeled monolingual text and a task delta $Δ_T$ from labeled English data, then composes them at inference under one of four rules: additive, activation-guided, sparsity-aware, and a novel \emph{cross-axis TIES}. The new rule adapts the TIES-Merging steps of trimming, sign election, and merging to the language and task axes rather than to two task axes. Holding $(Δ_L,Δ_T)$ fixed across rules on four task families and four African languages ($158$ evaluated cells, $10{,}000$-sample paired bootstrap per cell), we find: (i) cross-axis TIES wins summarisation on $3/4$ languages by $+4$ to $+7$ chrF (chrF $18.59$ vs.\ $13.80$ task-only); (ii) it improves QA F1 by $+2.32$ and EM by $+2.91$; and (iii) sparsity-aware merging cuts classification ECE by $36\%$ at parity macro-F1. The composition rule materially changes what the merged model preserves, suppresses, and calibrates. We release all JSON traces and a claim ledger.

Critical thinking is a fundamental skill that helps learners move beyond simple memorization. One way to develop this skill is through high-order questioning. However, crafting such questions remains a challenge for educators, and classroom practices tend to rely on low-order questions. Large Language Models have demonstrated strong capabilities in generating high-order questions, especially when guided by prompts based on Bloom's Taxonomy. Yet, existing research has largely centered on this framework and focused only on English. This study addresses these gaps by introducing prompts grounded in two alternative frameworks: Claim-Evidence-Reasoning and Divergent Questioning within a multilingual context using Basque, Spanish, and English. Results indicate that while both an open-source and a proprietary model rather effectively generate questions in all three languages, only about half of the answerable questions are recognized by teachers as high-order. A positive finding is that the alternative frameworks produce structurally and conceptually varied questions, suggesting they could complement each other and provide viable alternatives to Bloom's Taxonomy.

Discourse data are the primary empirical basis of grammar writing in field linguistics, but producing interlinearized text is notoriously expensive - on the order of one hour of work per minute of recording. For endangered languages, where the time remaining to verify analyses with native speakers is itself limited, automating parts of the interlinearization workflow has direct documentary value. We implement a full neural annotation pipeline (morpheme segmentation, POS tagging, glossing) for Irabu Ryukyuan using deliberately small, transparent BiLSTM-CRF models, and evaluate it under a realistic hard constraint: approximately one hour of fully annotated discourse as the entire supervised resource. Two factors of the annotation itself are manipulated: its richness (with or without a POS tier) and its quantity (training budgets from 6 to 47 minutes). Gold POS improves grammatical glossing by +4.4 (SD 0.7) points (significant in all 5 seeds), and the gain grows as data shrink (+11.6 points at a quarter of the data); a POS tier more than halves the amount of glossed data needed to reach a given accuracy. In a fully automatic pipeline this gain is not yet realized: the tagger still errs on 12% of morphemes, and an incorrect POS misleads the glossing model more than no POS at all. The value is latent rather than lost: degrading gold POS with controlled noise shows the gain returning as tagger accuracy rises, with break-even near our tagger's current 88% and +1.6 to +3.2 points recovered at 92-96%. We conclude with a concrete recommendation for documentation practice: annotate quadrilinearly - text, POS, gloss, translation.

We present a frame-independent audio-text system for the 3rd Ambivalence/Hesitancy Video Recognition Challenge at the 11th Affective & Behavior Analysis in-the-Wild (ABAW) Workshop. Videos are divided into overlapping 5-s windows aligned with transcript timestamps. Each window combines prosodic audio descriptors, emotion-oriented RoBERTa embeddings, and 74 psycholinguistic features representing uncertainty, hedging, and attitudinal conflict. Temporal cross-attention fuses audio and text, while the support features condition gated Multiple Instance Learning (MIL) pooling. A five-seed ensemble achieves an average precision of 0.875 and a macro-F1 of 0.722 on the 525-video labeled public-test split. Notably, our submission ranked third overall on the official challenge leaderboard, with a macro-F1 of 0.7455. Source code is available at https://github.com/Liga-de-IA-PUCPR/abaw-11-ah-challenge/.

Unequal availability of human preference data across languages poses a significant challenge for aligning large language models in multilingual settings. To address the lack of sufficient data in low-resource language alignment, we propose a meta-learning framework for Reinforcement Learning from Human Feedback and Direct Preference Optimization. By leveraging preference data from other languages, our framework learns a transferable initialization that enables effective adaptation to a target language with minimal data. We provide theoretical guarantees for both the meta-reward modeling and meta-policy optimization settings, and empirically demonstrate the effectiveness of our approach on multilingual benchmarks. In an extremely low-resource setting with only 100 target-language preference samples, our approach achieves up to $28\%$ win-rate improvements over baseline methods, and consistently outperforms baselines across multiple target languages and model scales. Our approaches retain these advantages across different combinations of meta-training languages and varying linguistic distances from the target languages.

BERT models have revolutionised Natural Language Processing (NLP) through their ability to process unstructured text across diverse domains. However, developing high-quality BERT models for non-English languages remains challenging due to limited annotated data and high computational demands. Translating non-English data into English and fine-tuning existing English BERT models offers a resource-efficient alternative, yet few studies have structurally compared translation-based fine-tuning with native-language BERT performance across tasks and languages. This study provides such a comparison, evaluating the feasibility of translation-based fine-tuning across six NLP tasks: Sentiment Analysis, Hate Speech Detection, Question Answering, Named Entity Recognition, Part-of-Speech Tagging, and Natural Language Inference, using datasets translated from Bulgarian, Chinese, Dutch, Italian, and Russian. Across all settings, the translation-based approach was comparable or superior in 53.3 percent of cases. Gains were most frequent in Question Answering, Part-of-Speech Tagging, and Natural Language Inference, while performance declines were common in Named Entity Recognition and Hate Speech Detection. The results show that translation-based fine-tuning is most effective for tasks relying on syntactic or structural patterns and for languages typologically close to English, such as Dutch, but less effective for token-level or culturally nuanced tasks, particularly in Chinese. Overall, this study demonstrates that translation-based fine-tuning offers a scalable, resource-efficient, and empirically validated path for extending NLP to low-resource languages while advancing linguistic inclusivity and sustainability in artificial intelligence.

Artificial Intelligence (AI) technologies, while serving as a foundational enabler for modern social media and digital health services, exert a bivalent effect by simultaneously acting as a combatant against and a spread vector for misinformation. A prevalent challenge in mitigating this issue arises in non-English contexts and low socioeconomic classes, where limited data hinders the training of AI models for effective detection. Consequently, culturally and linguistically diverse (CALD) communities struggle to access trustworthy health information through AI-driven tools. Current AI tools underperform due to a lack of training data and are largely unable to consider language nuances and traditions in non-English contexts. This research addresses these gaps by proposing a CALD-friendly AI-based health misinformation detector and providing a dashboard for medical professionals to analyse this misinformation, a critical step toward mitigating a growing concern among CALD populations. To this end, we conduct a series of experiments using a Bangla-translated health misinformation dataset to evaluate the performance of various Small Language Models (SLMs). SLMs are particularly relevant in this context given the frequent underperformance of Large Language Models (LLMs), which often stems from insufficient domain-specific knowledge and the prohibitive costs of resource-intensive fine-tuning. The results demonstrate that Phi-4 is the superior model, achieving an ideal balance between precision and recall in claim extraction. Then, to mitigate the limitations of SLMs, we design and test a novel health misinformation detection framework grounded in Responsible Natural Language Processing (NLP), which incorporates cultural sensitivity, potential for harm, and communication quality, thereby providing a holistic lens for evaluating misinformation in low-resource languages.

Language models are increasingly used for moral decision-making across diverse linguistic and cultural contexts, yet existing work overlooks multilinguality on three aspects: 1) multilingual evaluation benchmarks use direct translation, failing to adapt culture-specific items; 2) inference-time methods for moral reasoning rely on static, English-centric scaffolds and lack grounding in moral theory; 3) training methods for moral decision-making typically require expensive supervision from stronger models or human annotators. We address these gaps with three contributions. First, we introduce MCLASH, a multilingual moral decision-making benchmark to capture culturally situated moral intuitions and social norms across languages. Second, we propose MET (Multilingual Ethics with Theory-grounded reasoning), a two-step prompting method built on expert-curated, theory-based grounds drawn from psychology and philosophy: the model first selects situation- and culture-specific grounds, then reasons over them in the native language of the user. Third, we introduce MET-D (MET-Distillation), which enhances the second step through a self-distillation training stage that requires no external supervision. MET-D improves macro-F1 over the base model on all three models of different sizes and families (Qwen3-4B, Qwen3-8B, Gemma3-4B), by an average of 3.71 points on MCLASH and 4.23 on MMoralExceptQA, with a peak MCLASH gain of 12.94 points for Malay on Qwen3-8B. We further reveal that MET-D increases native-language reasoning by 62.13 points on average, and that beneficial grounds differ systematically across cultures. Together, these contributions open the path for culture-aligned, theory-grounded multilingual moral reasoning.

Large-scale, richly annotated career trajectory data underpins workforce planning, job recommendation, and labour market analysis, yet publicly available datasets are either small, closed to independent use, or built from pre-standardized occupational codes with LLM-synthesized rather than authentic free text. We present JobHopv2, an improved version of the publicly available JobHop dataset, constructed through end-to-end large language model (LLM) extraction from a corpus of ${\sim}440{,}000$ pseudonymized, multilingual resumes provided by VDAB, the Flemish Public Employment Service. The released dataset comprises $355{,}315$ career trajectories annotated with ESCO occupational codes, quarter-level temporal information, and normalized five-level education attainment, broadening both the coverage and the annotation richness of the original release. Relative to v1, JobHopv2 introduces a redesigned extraction pipeline based on reasoning-controlled LLM inference with a retry mechanism (achieving a 100% JSON parse rate), a richer extraction schema, and a revised evaluation protocol scored against three complementary annotation baselines. Evaluated against these baselines, our best extractor comes closest to the inter-annotator agreement ceiling among all compared models, trailing it by only 1.1-2.7 percentage points. The dataset and code are publicly released to support reproducible career-trajectory research.

The asymmetry between language production and perception has been well-documented in psycholinguistics. Whether large language models (LLMs) exhibit a functionally analogous distinction remains an open question, particularly given that LLMs rely on the same underlying mechanism (next-token prediction) for both input and output processing. In this exploratory study, we operationalize the production-perception distinction through direct token probability measurements rather than metalinguistic prompting. Using the base Llama-3.1-8B model, we generated poems under a production prompt and re-scored the same tokens under both rephrased production prompts and perception-oriented prompts. Across an extended experiment with four production and three perception prompts, production-perception distances consistently and substantially exceeded production-production distances, with non-overlapping ranges across conditions and an overall average ratio of approximately 1.8. Near-ceiling correlations in the production-production control confirm that the effect is specific to communicative framing rather than prompt surface variation, and we show the effect replicates across five open-weight models (Llama-3.1-8B, EuroLLM-9B, gemma-2-9b-it, Mistral-7B-Instruct-v0.3, and Qwen2.5-7B-Instruct), spanning both base and instruction-tuned variants. Temporal analysis revealed that the perception prompt exerts its strongest influence at the beginning of the sequence, with divergence decaying as generated context accumulates, though the specific shape of this decay varies across prompt pairs. These findings suggest that prompt framing alone induces a production-perception distinction in LLM probability distributions, even within a decoder-only architecture.

Aphasia following stroke commonly produces systematic naming errors with characteristic profiles, but whether general-purpose language models not designed for clinical simulation can reproduce these patterns remains untested. We investigated (1) whether lesions or controlled perturbations to a multimodal language model can reproduce different types of errors in picture naming, and (2) whether the framework can reproduce the complete error profile of individual persons with aphasia (PWAs). Using LLaVA 1.6, we evaluated perturbation configurations that varied the layer, proportion, and amount of noise applied to model units. We examined 278 PWAs on the Philadelphia Naming Test, classifying responses into seven categories using a validated neural classifier. Six of seven response categories (correct, semantic, mixed, unrelated, neologism, no response errors) emerged at clinically-comparable proportions across distinct parameter space regions, with formal paraphasia being the exception. Searching the perturbation space revealed configurations that reproduced the individual error profile in at least six of seven categories for 97.8% of PWAs and in all seven categories for 79.5% of PWAs. Monte Carlo baselines confirmed that this matching reflects joint inter-category structure rather than marginal overlap. These results establish a quantitative framework for reproducing individual aphasic error patterns in picture naming. They suggest the potential for language models to serve as digital twins of individuals with post-stroke aphasia.

We study how little extra information is needed to make adversarial language learning possible. In Gold's model of language identification in the limit, a learner is given an enumeration of the strings from an unknown language chosen from a countable language collection. The learner guesses the identity of the language over the course of the enumeration, and it succeeds if, eventually, all of its guesses are the correct language. Classical results of Gold and Angluin show that many natural collections cannot be learned in this way. Recent work on trace colorings, motivated by the success of thinking-trace strategies in language learning, overcomes this obstruction by annotating every symbol of every string with a color. We ask whether the learner really needs this whole sequence of colors, or whether one color at the end of each string (a terminal coloring) is enough for language identification. We show that just one terminal bit per string is enough for every countable collection of infinite languages. In fact, the colorings can be chosen collection-independently: there is a single assignment of a two-color terminal coloring to every infinite language such that the same preassigned colorings identify every countable subcollection. Thus, in this model, an entire color trace can be compressed to one bit attached to the end of each example. Our global construction uses transfinite recursion, and we prove that this kind of nonconstructivity is unavoidable for any bounded number of colors. As a notion of constructivity, we use the formalism of Borel maps (a regularity condition satisfied by natural explicit constructions); we show that no global terminal coloring with a finite number of colors defined by a Borel map can identify all countable subcollections. By contrast, known trace-coloring constructions are Borel when encoded as terminal colorings, but require infinitely many colors.

The spread of hate speech (HS) across different social media platforms (SMPs) poses a major concern for online safety and ethical moderation. Automatic detection of HS remains a challenging task, especially in under-resourced languages like Bangla, due to cultural context, implicit expressions, and informal linguistic patterns. This study aimed to expose the crisis of Bangla HS detection systems by diagnosing how and why benchmark-trained models fail to identify implicit, context-dependent HS. Six architectures (FastText + CNN, FastText + LSTM, FastText + BiLSTM, BanglaBERT, BanglaBERT + CNN, and BanglaBERT + BiLSTM) were trained on benchmark datasets (about 75,000 posts) and a merged multi-source dataset (about 120,000 posts), then externally validated on an annotated dataset (about 200 posts) collected from Facebook, Twitter, and YouTube, labeled as HS and non-HS, where HS was further categorized as explicit and implicit. BanglaBERT achieved an F1-score of 91.4% on benchmark datasets but declined to 75.3% on the external set and 63.4% for implicit HS involving sarcasm and emojis. The accuracy of FastText + CNN dropped from 78.0% to 51.2% under similar conditions. Emoji-aware preprocessing improved implicit HS detection by up to 12%, whereas emoji removal caused a notable decline in performance (F1: 0.75 to 0.63). Frequent misclassifications in politically charged or satirical comments revealed over-policing risks. This study not only exposes the generalization crisis due to implicit, culturally embedded, and emoji-laden expressions but also underscores the need for developing adaptive, emoji-aware, and culturally grounded frameworks that ensure ethical moderation while preserving freedom of expression. Findings of this study provide insights for researchers, SMPs, and policymakers to design more context-sensitive HS detection systems for low-resource languages.

Ensuring the quality of educational materials requires more than standard proofreading: textbooks must be audited for factual accuracy, domain-specific technical correctness, and linguistic quality simultaneously -- a task that general-purpose grammar checkers cannot address. We present \textbf{AI Textbook Auditor}, a modular multi-agent pipeline for automated quality assurance of educational materials across subject domains. The system accepts a textbook PDF and produces a structured, human-reviewable report via two analysis tracks: a \textbf{Factual and Technical Track} in which an ensemble of specialized LLM agents detects factual inaccuracies, code errors, incorrect definitions, and conceptual inconsistencies, augmented with web search for humanities domains; and a \textbf{Grammar Track} operating PDF-natively to preserve diacritical encoding. A \textbf{Judge Agent} filters false positives using domain-specific rules before presenting findings to a human reviewer. The pipeline supports two ingestion modes -- vision-native page rendering and PyMuPDF text extraction -- and is domain-adaptable via custom prompts encoding subject-specific error taxonomies. We demonstrate the system on two Romanian upper-secondary textbooks: a CS textbook (56 technical findings across seven categories, with an expert-validated precision of 62.5%) and a history and social sciences textbook (72 findings spanning factual errors, ideological bias, and grammar). The system is designed as a triage tool that reduces the manual effort of locating candidate issues, with human expert validation required before any editorial action.

Large-scale pretrained ASR models such as Whisper exhibit strong multilingual capabilities. However, fine-tuning on low-resource languages often causes catastrophic forgetting. Although continual learning mitigates this issue, existing methods struggle to regulate cross-task interference in multilingual settings, where dominant languages bias optimization. We propose Unified Gradient Projection (UGP), which constrains parameter updates using reference gradients from language-balanced replay in a unified projection space. By equalizing per-language contributions in the projection, UGP reduces dominant-language bias and improves cross-lingual stability. We further show that combining gradient-level projection with data-level replay yields complementary gains in stability and plasticity. Across diverse low-resource language groups and model scales, UGP enables effective adaptation while substantially mitigating forgetting. On Whisper-large-v3, it achieves near-zero average forgetting.