Linguistics

Organizations and regulators increasingly consult large language models (LLMs) for regulatory-compliance questions, yet a wrong statutory citation can silently propagate into legal advice, compliance documentation, and policy decisions. We introduce a bilingual benchmark of 120 questions probing whether freely accessible LLMs fabricate article citations for two data-protection instruments: the EU General Data Protection Regulation (GDPR) and the Saudi Personal Data Protection Law (PDPL). The benchmark pairs direct citation retrieval questions with false premise verification probes and deliberately unanswerable "trap" questions -- including questions about a repealed article and about deadlines that exist only in implementing regulations, not in the law itself. Every question is posed in both Arabic and English, and all scoring is fully automatic against a manually verified gold reference. Evaluating three freely accessible models (Gemini 2.5 Flash, GPT-OSS-120B, Nemotron-3-Super-120B), we find a dramatic jurisdiction gap: near-ceiling citation accuracy on the GDPR (94-100% on direct retrieval) against majority fabrication on the Saudi PDPL (60-77%), invariant to query language; the highest fabrication rates (67%) arise from statute-vs-regulations confusion, and 91% of fabricated citations are asserted with confidence >= 0.8. Fabrication tracks the jurisdiction of the law, not the language of the query, and model confidence provides no protection -- indicating that verbatim-verification safeguards, rather than model self confidence, must gate any institutional reliance on LLMs for compliance screening.

We address ambivalence and hesitancy (A/H) recognition in the ABAW 2026 BAH Challenge: given a short interview video, predict whether the person shows signs of A/H. Our system combines affect-specialised text, audio, and visual representations with a small set of readable linguistic hesitation cues, fused by a reliability gate we call Affective Marker Fusion (AMF), and finished with a simple AP-weighted ensemble at a fixed decision threshold. We also introduce \emph{ASR-erased time}: speech recognisers delete fillers and hesitation pauses from the transcript, but the chunk timestamps keep the time those events took, and sixteen features built from these gaps form the strongest and most independent non-verbal channel we measured (AP $0.718$, correlation $0.11$--$0.36$ with all other members). Across controlled experiments we find three things: cross-modal conflict design does not reliably help on BAH; language is by far the strongest channel while affect-specialised audio is a useful second; and calibration matters more than architecture. Fitting ensemble weights and a threshold on the small validation split overfits: it scores $0.741$ macro-F1 on validation but only $0.690$ on the untouched test set. AP-weighting at a fixed threshold instead reaches $\mathbf{0.731}$ on test.

Does a reinforcement-learning agent that earns reward learn its task's hidden state? We study this question with hidden finite automata that the agent partially controls. Because each automaton is known, we can normalize reward by the best achievable return and probe the network for the true state at every step. Together the two measurements separate failures that reward alone conflates. An agent can encode too little of a state its network could hold, or encode the state and still control poorly. Weak on-policy RL matches random play while the state probe stays at chance. State learning depends on the optimizer, the training budget, and the task's structure. Permutation automata provide a warning before training: no input symbol maps two distinct states to the same successor. On a stratified held-out set, 86 of 103 permutation automata fail the state probe, and the classification is stable across probe read-outs and recovery thresholds. Most of these failures come with weak reward. High reward without the state occurs but is rare. Non-permutation automata can also fail. Oracle-normalized reward alone therefore does not establish that the task's state was learned.

Despite recent scaling successes, multilingual ASR performance remains highly uneven, with long-tail languages suffering from severe data scarcity. This work addresses the challenge of building robust foundation models for underrepresented Central Asian languages (Kazakh, Kyrgyz, Uzbek). We present GigaAM Multilingual, a Conformer encoder pre-trained on 2M hours of audio using a HuBERT-style objective. Crucially, we introduce a cluster-level data balancing strategy during pre-training and a domain-aware sampling method during fine-tuning to mitigate head-language dominance. In controlled comparisons, our approach outperforms strong open pretrained encoders (Whisper Large v3, Omnilingual-1B) on target languages, achieving significant gains on spontaneous speech while maintaining efficiency. We release the foundation encoder and ASR model, offering a proven recipe for effective multilingual adaptation under realistic data imbalance.

The rapid proliferation of online polarization threatens social cohesion, necessitating robust automated detection systems that operate effectively across diverse linguistic contexts. This paper presents our system description for the POLAR Shared Task 2026, focusing on the detection and characterization of polarized discourse in English and Hausa. We propose a hybrid modeling strategy: for English binary detection, we leverage the monolingual strength of \textbf{DeBERTa}, while for Hausa and all fine-grained subtasks (Types and Manifestations), we utilize \textbf{AfroXLMR-Social}. This domain-adapted multilingual model proved critical for capturing the nuances of polarization in social media text. To further address computational constraints and data scarcity, we implement Low-Rank Adaptation (LoRA) and textual data augmentation via \texttt{nlpaug}. We report competitive results across all three subtasks, demonstrating that model selection tailored to specific subtask requirements yields the best balance of performance.

Language identification is an important step toward integrating endangered Australian Aboriginal languages (AALs) into speech technologies supporting language revitalisation and digital inclusion. However, extreme data scarcity limits model performance. Transfer learning from high-resource languages shows promise but often suffers from catastrophic forgetting when adapting to new languages. Continual learning (CL) can mitigate this issue, though it remains challenging with very limited data. To address this, we propose two hybrid continual learning methods: Replay Augmented Elastic Weight Consolidation and Constraint Guided Knowledge Distillation to adapt pretrained speech models for AAL identification while preserving previously learned knowledge. Experiments on Warlpiri, Dalabon and Dharawal show that the proposed methods outperform fine-tuning and existing CL baselines, improving adaptation to multiple AALs while maintaining performance on previously learnt high-resource languages.

This paper investigates how language similarity can improve cross-lingual transfer for automatic speech recognition (ASR) in extremely low-resource settings. Warlpiri, an Australian Aboriginal language, has very limited transcribed speech data, making transfer learning essential. We propose a framework combining acoustic similarity from pre-trained speech models with linguistic similarity based on typology, phoneme inventories, grammatical, and syntactic features to rank high-resource source languages and evaluate their effectiveness for ASR transfer to Warlpiri. Experiments with Whisper show that acoustically and typologically similar languages outperform monolingual and multilingual baselines. Assamese and Hindi achieve substantial reductions in word and character error rates. Correlation analysis further indicates that acoustic similarity is the strongest predictor of fine-tuning performance, while phoneme inventory and typological similarity better explain zero-shot transfer.

Language builds discourse contexts other than the actual: a painting, a belief, a memory, a hypothetical. Each is a mental space in which the same entity can take a different value, as when a flower is red in reality but purple in a portrait. Formal semantics keeps these contexts apart because their logics differ (modal, temporal, doxastic, depictive); Fauconnier's mental-space theory treats them as one space-building operation. We ask which of these a transformer language model implements, and find a mechanistic version of Fauconnier's unification. The model uses one router/slot format across the inventory: a reusable value slot stores attributed content, and a causally manipulable router (the space index) selects which space is read. A subspace trained with Distributed Alignment Search to control one space type, counterfactual, belief, fictional, or temporal, also controls the others, well above a random floor, on three model families; belief, which formal semantics marks as a distinct case, is not specially separated. The router is low-rank, composes additively with entity identity, and acts through a few late-layer heads. Two further results show the mechanism drives inference and composes: a subspace trained on a rule-derived conclusion flips what the model infers while dissociating from what it reports, and composing space-builders mints a fresh router over the shared slot. This paper establishes the cross-type generality. A companion paper develops belief in depth, because of its special status in philosophy, psychology, and linguistics (epistemology, theory of mind, and propositional attitude reports).

Reasoning Language Models (RLMs) achieve their strongest performance when they reason in English, the language for which reasoning-oriented training data is most abundant. However, reasoning trace is a clue for model interpretability and safety, and useful in practice for both the model users and for model developers. Thus, it is desirable to be able to develop a model that reasons in a language of the user's choice, while still maintaining strong reasoning performance. To this end, we study the feasibility of training a model that reasons in Japanese. We develop a Japanese-reasoning variant of Qwen-3-Swallow-8B, which is a Japanese LLM continually pretrained from Qwen-3-8B, with GRPO and evaluate it across coding, math, and science benchmarks. The study shows that reasoning-language control is feasible by training a Japanese continually pretrained model with GRPO. However, its performance is at best on par with strong English-reasoning baselines on several benchmarks. We also evaluate the trained model on Japanese cultural benchmarks and observe that the model's performance is worse than the baseline models, suggesting that the reasoning in Japanese does not immediately improve performance on culturally relevant tasks for free.

Safety alignment in large language models remains brittle across languages: prompts reliably refused in English can elicit harmful compliance in non-English and low-resource settings. We introduce \textsc{Minionese}, a multilingual jailbreak benchmark spanning 18 languages, 4 resource tiers, and 4 perturbation types (standard translation, code-switching, transliteration, and translationese), paired with a geometric mechanistic analysis of refusal failure across language tiers. We show that each attack type produces a distinct vulnerability profile: transliteration vulnerability is mediated by script identity, code-switching maintains effectiveness through the lowest-resource tier, and a sharp safety regime transition between Tiers 2 and 3 is consistent across all models. Mechanistically, low-resource jailbreaks succeed by routing harmful content through a geometrically misaligned subspace that projects insufficiently onto the refusal directions, leaving the refusal mechanism intact but untriggered. These findings show that English-only safety evaluations are insufficient; they require accounting for script family, perturbation type, and per-language alignment coverage. The benchmark and analysis code is at https://github.com/Brentkong/Minionese-Comprehensive-Benchmark-and-Mechanistic-Study-of-Multilingual-LLM-Safety.git.

Spoken language models (SLMs) unify speech perception and reasoning, but adapting them to sensitive domains is underexplored, especially when the original training data is inaccessible and the use case demands multilingual, spoken-query interaction. We adapt an open-source SLM to the Singaporean Home Team context across five speech tasks in Singapore's four official languages, combining LoRA fine-tuning, a surrogate text-QA dataset that guards against catastrophic forgetting, and a multi-task objective that adapts the CoBa reweighting scheme to speech. We also build HTD-multilingual-QA, a 504,853 sample multilingual QA dataset in text and spoken form. The resulting HT-Moonstone (5B) matches or outperforms SLMs up to 7x its size on most tasks, attains the best accent and gender recognition among all models evaluated, and loses under 2% of its original speech QA ability.

We present an interpretable network-based framework for representing idiomatic and figurative meaning across eight typologically diverse languages, totaling 160 conventional expressions, the large majority of which are idiomatic. Each expression is annotated with binary conceptual features (containment, concealment, emotional, social, etc.) derived from cognitive-linguistic theory, and pairwise Jaccard similarities define a weighted graph. Community detection reveals that idioms cluster by conceptual schema rather than by language, producing a structure consistent with cognitive-linguistic predictions. The conceptual network captures unique semantic information not present in distributional embeddings, can be scaled via automatic annotation with LLMs, improves downstream idiom detection, and remains robust when enriched with corpus frequencies. Cross-lingual transfer experiments show that conceptual proximity alone can identify acceptable translation equivalents across five language families, with substantial gains over embedding-based baselines. Ablation studies demonstrate that all three feature dimensions -- schemas, roles, and valence -- contribute non-redundantly to both the network's organizational properties and its performance on idiom detection, and that specific graph-derived signals (community membership, neighbor similarity) are particularly informative. The framework offers an interpretable, cross-linguistically stable representation of idiomatic meaning, combining theoretical grounding with practical utility.

Text-guided medical image segmentation leverages clinical semantics to improve lesion delineation, yet many existing models bind cross-modal fusion, supervision, and decoder design into a task-specific architecture. Such tight coupling makes it difficult to reuse language guidance modules across heterogeneous vision and text backbones, and often requires redesigning the network when the encoder pair changes. This paper presents BTHA, a backbone-transferable hierarchical adapter framework for text-guided medical image segmentation. BTHA is built around a stable feature-level interface: given multi-scale visual features and a text representation, it injects semantic guidance through shape-preserving adapters while maintaining the decoder-side tensor contract. To make this interface effective, we introduce a Hierarchical Coarse-to-Fine Supervision Strategy that decomposes learning into global image-text alignment, multi-scale auxiliary localization, and boundary-aware final mask refinement. We further design a Scale-Adaptive Gated Semantic Guidance (SAGSG) adapter, where resolution-specific gates adaptively control textual injection and channel recalibration suppresses redundant cross-modal responses. Evaluations across diverse vision and text backbones show that the same adapter and supervision design remains effective across convolutional and transformer-based visual encoders as well as different language encoders. Experiments on four public datasets further demonstrate that BTHA improves strong text-guided baselines with modest computational overhead.

Test-time scaling (TTS) reliably improves reasoning in large language models, but whether it transfers to small open vision-language models remains unclear. We examine this on EXAMS-V, a multilingual visual multiple-choice benchmark, comparing self-consistency, describe-then-reason with PRM-guided beam search, and two post-hoc selectors across Qwen2.5-VL-7B-Instruct and Qwen3.5-4B. What matters is the conditions under which TTS runs, not the search or verification machinery. The largest factor is parseability: an early prompt format left many chains reasoning correctly yet never committing to an answer letter, which a standard answer cue and a guided repair step largely remove. A larger decoding budget removes the rest: raising the per-chain token limit from 1k to 2k recovers 3.7 pp, whereas sampling more chains (8 to 16) adds only 0.15 pp. Once chains have room to finish, elaborate methods contribute little: PRM-guided beam search trails plain self-consistency by 0.39 pp at over eight times the cost, and neither a training-free generative critic nor a trained multimodal PRM beats majority vote across both policies. The largest gain comes instead from the policy model itself (+11.4 pp). Our best configuration reaches 84.1% on the held-out ImageCLEF 2026 test split, ranking first on the Visual MCQ leaderboard.

We present Soofi S 30B-A3B, a sovereign, open-source Mixture-of-Experts (MoE) hybrid Mamba Transformer foundation model for German and English. Its hybrid design activates only 3B of 30B parameters per token and keeps the inference cache near-constant as context grows, giving it a decisive throughput advantage over dense models for long-context, high-concurrency deployment. Pretrained on roughly 27 trillion tokens with deliberately up-weighted German, Soofi S matches dense 14 to 27B models on aggregate English and German benchmarks while achieving the best code aggregates in both languages among 17 open base models, and outperforms every European sovereign baseline in our comparison, including ones far larger in active parameters. Among fully open models, Soofi S obtains the highest English and German evaluation scores, ahead of Olmo 3 32B and Apertus 70B. Soofi S was built end-to-end on the German Industrial AI Cloud, a sovereign HPC scale AI infrastructure operated by Deutsche Telekom in Munich. Soofi S will be released under highly permissive, open-access terms: weights, selected intermediate checkpoints, full per-source data accounting, hyperparameters, and training and evaluation code. Where source licenses permit, data-construction artifacts are released under permissive licenses; commercially licensed sources are documented with aggregate statistics and exact mixture accounting.

The rapid development of large language models and multimodal large language models has accelerated the emergence of proactive agents capable of operating everyday tools and assisting users in real-world environments. However, existing benchmarks struggle to evaluate such agents effectively, as they often rely on sandboxed environments and single-turn evaluation paradigms. Moreover, their scenario-based task taxonomies mix multiple model capabilities within the same task category, making it difficult to identify the root causes of agent failures. To address these limitations, we introduce UniClawBench, the first capability-driven benchmark designed to evaluate proactive agents in dynamic, real-world settings. UniClawBench is built around five foundational model capabilities: Skill Usage, Exploration, Long-Context Reasoning, Multimodal Understanding, and Cross-Platform Coordination. Based on these capabilities, we design 400 bilingual real-world tasks. Unlike previous benchmarks that rely on static, pre-recorded answers, our benchmark evaluates agents in live Docker containers using fine-grained, step-by-step completion checkpoints. Furthermore, we design a closed-loop evaluation strategy comprising an executor agent, a hidden supervisor agent, and a user agent to simulate realistic multi-turn human feedback without leaking grading criteria. To disentangle base model capabilities from framework-level design choices, we evaluate state-of-the-art models under multiple agent frameworks. Through comprehensive comparisons across both models and frameworks, we show how base model capabilities and agent framework designs jointly shape performance in real-world environments. To facilitate future research, we make our benchmark and code publicly available at https://github.com/HKU-MMLab/UniClawBench.

We present a Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoder (SAE) for extracting cross-seed universal features from independently trained BERT models. Cross-seed feature universality is a fundamental challenge in mechanistic interpretability: because dictionary learning is non-convex, independently trained networks learn misaligned feature spaces, so apparently identical features may differ by random initialization. We address this by computing an orthogonal Procrustes rotation between seeds' activation spaces before joint SAE training, combining Top-K sparsity, end-to-end downstream optimization, and an auxiliary dead-feature revival loss based on previous SAE literature. Evaluating on five independent seed pairs (ten BERT models) across three benchmark datasets (SST-2, Stanford Politeness, TweetEval Emotion), our full pipeline produces more universal features (Pearson r $\geq$ 0.70 across seeds) than post-hoc alignment baselines on all three datasets. A minimal qualitative analysis confirms that high-universality features encode interpretable sociolinguistic patterns.

Vietnam's ethnic minority languages are almost absent from the field of Natural Language Processing (NLP), and the challenge goes beyond data scarcity: Cham, Khmer, and Tay-Nung differ sharply in script, Vietnamese contact, and standardization, conditions under which standard multilingual adaptation can learn the wrong signals. We introduce CKTN, the first corpus and benchmark for these languages (44,367 documents, 24M subword tokens), spanning continued pretraining, category classification, and summary-document retrieval. We show that existing multilingual encoders severely fragment these languages, and that common adaptation metrics can mislead: models may lower language-modeling loss or excel at lexical-overlap retrieval while still failing at semantic generalization across documents. We address this with a script-aware adaptation recipe - vocabulary augmentation combined with calibrated replaced-token pretraining - that prevents the discriminator from exploiting trivial script mismatches. The result is an encoder with substantially less fragmentation and the strongest classification performance among evaluated models, exposing the limits of lexical-overlap retrieval as an evaluation signal.

How should language interface with a world model's discrete symbol system? The dominant paradigm -- end-to-end injection of LLM/VLM features into robot world models (RT-2, Octo, PaLM-E) -- implicitly assumes that language gradients can directly shape physical symbol representations. We ask whether this assumption is safe, find that it is not, and characterize the minimal architectural constraint that prevents the failure. Any language gradient entering a Gumbel-softmax-based discrete symbol bottleneck forces a structural trade-off: the vanilla estimator collapses to 2.2/64 symbols (4/5 seeds), while five anti-collapse strategies maintain diversity but fail to learn semantic labels (all <= 9.2% accuracy). No tested GumbelBottleneck variant achieves both objectives simultaneously. Within this family of discrete bottlenecks, the failure is structural rather than a matter of optimization. We characterize a sufficient set of three constraints that prevent the failure: (1) cut the gradient chain (z.detach()), preventing language signals from reaching the symbol bottleneck; (2) provide a gradient-free semantic channel -- a non-parametric Memory Table (Dict[symbol -> Counter[label]], zero parameters, zero gradients) where co-occurrence counting replaces gradient-based binding; (3) handle symbol collisions via DP-Means streaming clustering for automatic sub-cluster splitting. All three layers together achieve 97.2% grounding accuracy vs. 22.2% without Layer 3. Across two experiments spanning 74 independent runs, we demonstrate zero symbol collapse in all 32 seeds, with the blackboard achieving 79-100% semantic binding across three encoder architectures (CNN, V-JEPA 300M, CLIP ViT-L), two environments, and three texture conditions. The fix trains fewer than 2M parameters and requires no LLM fine-tuning.

Roy Harris's Integrationist linguistics offers a compelling critique of the referentialist tradition embedded deep at the heart of computational approaches to language, arguing that language is not a code that maps onto a pre-given world but a situated, bipartite activity oriented toward prospective joint action. Yet Integrationism leaves certain explanatory gaps: it does not fully account for the structural mechanism by which signs sustain prospective openness, it undertheorises the continuity between linguistic and non-linguistic semiotic activity, and it offers no detailed account of the structural properties of the accumulated archive of past integrations. This paper argues that Elan Barenholtz's autogenerative theory of language, developed in response to the behaviour of Large Language Models (LLMs), can fill precisely these gaps, enriching Integrationism without undermining any of its core commitments. Specifically, the autogenerative account provides: a structural mechanism for the prospective openness that Harris identifies as central to bipartite communication; a computational correlate for Harris's thesis of semiotic continuity between language and other sign-making activity; and a theory of the archive: what the accumulated residue of past integrations looks like and how new participants draw upon it. The synthesis preserves Harris's ontological primacy of the situated integrative act while adding explanatory content that Integrationism itself does not supply. For practitioners and researchers in natural language processing and large language model design, the argument offers a principled account of what the statistical structure that LLMs so effectively exploit actually is, and of what it cannot, by its nature, provide.

Large language models increasingly understand dialectal English, yet still produce only standard, US-leaning English, leaving dialectal generation, the harder half of the problem, largely unaddressed. We introduce DiaLLM, which continually pretrains three open-weight language model families on the International Corpus of English and applies implicit and explicit post-training paradigms, each combined with three model alignment strategies, giving the first controlled comparison of these components across Australian, Indian, and Northern British English. Our results reveal a robustness-generation gap: benchmarks are shaped by continual pretraining and SFT, while alignment visibly reshapes generation in ways benchmarks do not capture. Explicit variety-targeted adaptation produces output reliably recognised as dialectal and judged more dialectal than broad alignment, yet where human judgement was directly assessed, the method that most aggressively optimises the dialectal reward is not the one judged most dialectal. Independent linguistic analysis corroborates this reward-quality gap, most clearly on two of the three families. No single alignment method dominates, and closing the gap will require richer reward designs and continued investment in dialectal resources. We release all code, checkpoints, and preference datasets.

One of the expected abilities of vision-language models (VLMs) is spatial reasoning ability based on a given text and image. To evaluate the spatial reasoning abilities of VLMs, we focus on the use of spatial deictic expressions, which are defined as spatial expressions whose referent is determined by their situational context, such as this'' and that''. To handle spatial deictic expressions, VLMs must jointly reason over language and visual space, grounding context-dependent references in the image's spatial structure. In addition, selecting appropriate spatial deictic expressions across languages requires VLMs to understand the language-specific spatial distinctions encoded by these expressions. In this paper, we develop a benchmark to evaluate the multilingual ability of VLMs to use spatial deictic expressions in four languages. Our experiments using this benchmark reveal that the tested models use demonstratives in a manner different from that of humans, particularly in selecting the appropriate demonstratives based on the distance to the object.

Large Language Models achieve strong code generation for high resource languages like Python and Java but suffer sharp performance drops on Low-Resource Programming Languages~(LRPLs) such as Julia. Improving Small Language Models~(SLMs) for these languages faces a trilemma: Supervised Fine-Tuning~(SFT) is bottlenecked by data scarcity, inference-time scaling is too expensive for deployment, and Reinforcement Learning from scratch yields near zero advantages. We propose a three-phase pipeline that resolves this trilemma by decoupling syntax acquisition from algorithmic reasoning. First, we \emph{left-shift} inference-time compute to an offline data synthesis engine that uses iterative compiler and test feedback to generate verified training examples. Second, we fine-tune an SLM on this synthetic, verified data to embed strong syntactic priors. Third, we apply Reinforcement Learning with Verifiable Reward~(RLVR) grounded by language-agnostic Input/Output tests, where the SFT prior constrains exploration away from syntax errors. Applied to Qwen3-8B, our pipeline improves pass@1 by up to +7.6 points on MultiPL-E and +14.2 points on the Agnostics LiveCodeBench for Julia compared to SOTA results. Furthermore, the pipeline only used $\frac{1}{3}$ data and $\frac{1}{6}$ cost over the previous state-of-the-art. We further demonstrate that the pipeline generalizes to Ballerina achieving 49.7% MultiPL-E Pass@1, a language with near-zero pretraining representation. Ablations confirm that both the SFT phase and execution-grounded rewards are necessary for stable training.

African American English (AAE), a rule-governed dialect spoken by over 30 million people, is routinely misinterpreted and "corrected" by large language models (LLMs). Across six instruction-tuned LLMs (14B to 70B), we show that state-of-the-art models systematically prefer Standard American English (SAE) continuations even when the preceding context is in AAE, effectively rewriting AAE into SAE. We present an end-to-end framework to audit and mitigate this bias. For auditing, we introduce conditional Dialect Group Invariance (cDGI), which isolates true model bias from translator-induced artifacts, and a feature-level localization analysis that identifies which AAE markers most strongly trigger bias; we find that syntactic constructions, especially negative concord (e.g., "ain't nobody"), are universal triggers across all models. For mitigation, we introduce, to our knowledge, the first application of activation steering to dialect bias: a training-free, test-time method that extracts dialect directions via causal tracing and injects them into bias-relevant layers. Activation steering reduces bias 5 to 20 times more than prompting while preserving SAE fluency. To enable this work, we release REAL-AAE , the largest real-AAE parallel corpus to date: 17,479 AAE/SAE/ AAE_back triplets from natural tweets (2 to 6 times larger than prior real-AAE resources), validated automatically (BERTScore F1 = 0.95) and by three native AAE speakers (83.0% semantic agreement).

Dhivehi, the national language of the Maldives, is currently under-resourced for automatic speech recognition (ASR) and other NLP tasks. This study investigates whether cross-lingual transfer learning from Sinhala, a linguistically related, relatively well-resourced Insular Indo-Aryan language, can improve Dhivehi ASR. We conduct seventeen experiments across five transfer learning paradigms: Dhivehi-only baselines, sequential fine-tuning, multilingual fine-tuning, continual pre-training, and a control using Turkish as an unrelated language. The strongest system, continual pre-training on Sinhala followed by fine-tuning on Dhivehi with KenLM, achieves 12.89% WER and 2.70% CER, outperforming the Dhivehi-only baseline by 13.50% WER and 3.02% CER. However, the adaptation strategy and decoding configuration are equally critical for a successful transfer learning experiment. We conduct seventeen controlled experiments spanning five transfer learning paradigms: Dhivehi-only baselines, sequential fine-tuning, multilingual fine-tuning, continual pre-training, and a control experiment using Turkish as an unrelated language. The strongest system, continual pre-training on Sinhala followed by fine-tuning on Dhivehi with KenLM, achieves 12.89% WER and 2.70% CER, outperforming the Dhivehi-only baseline by 13.50% WER and 3.02% CER. The Turkish control experiment confirms that observed improvements stem from linguistic relatedness; adaptation strategy and decoding configuration are also critical.

Is word acquisition in children uneven with respect to semantic and lexical categories? To answer this question, we model early language learning as a search on a graph-based mental lexicon, driven by two interacting processes: spreading activation and an enforced exploration (rather than exploitation) of lexical categories. We evaluate model performance on four languages (German, English, Dutch, and Rioplatense Spanish), using CDIs as ground-truth data for lexical categories, normative ages derived from the Wordbank repository, and state-of-the-art resources for reconstructing graphs of word similarities. We find that spreading activation outperforms a shortest path baseline in simulating normative word acquisition. At the category level, we highlight complex transitions between CDIs. By studying their sequences in terms of burstiness and average persistence time within the same CDI, we find that spreading activation better captures the exploration dynamics observed empirically. Overall, our findings suggest that vocabulary development can be understood through the non-trivial interplay between activation dynamics and some degree of constraints regulating the visiting of lexical categories in complex networks.

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

Mathematical reasoning has become a central task for evaluating and tuning reasoning Large Language Models (LLMs), yet existing benchmarks remain heavily biased toward high-resource languages, with English and Chinese dominating both pre-training corpora and evaluation suites. The recently released PolyMath (Wang et al., 2025) dataset represents a significant step forward, yet its coverage is still limited to 18 only high-resource languages. To address this gap, we introduce PluraMath, an extension of PolyMath to 18 additional {underrepresented languages spanning 6 language families -- ranging from mid-resource to extreme low-resource settings. We constructed the dataset through a human-curated pipeline, where native speakers thoroughly validated pre-computed translations. Using PluraMath, we then benchmark 27 reasoning LLMs across four model scales -- small, mid-size, large, and closed-source ensembles -- probing the multilingual mathematical reasoning capabilities of state-of-the-art models under diverse linguistic conditions. Our fine-grained analysis confirms a persistent gap in mathematical reasoning performance between high-resource and underrepresented languages, with stronger results largely associated with better instruction-following ability. We fully open-source our dataset, data acquisition pipeline, and evaluation framework, with the goal of lowering the barrier to multilingual benchmark development for underrepresented communities.

Information Operations on social media networks have been identified as a significant threat to democracy and modern society, but they are challenging and expensive to detect by humans. Existing supervised IO detection methods fail to capture the dynamic nature of evolving IO user behavior, while existing unsupervised approaches rely on oversimplified assumptions of coordination among IO users that may not exist in practice. To overcome the limitations of existing methods, we formulate IO user detection as an anomaly detection problem and propose a novel unsupervised IO user detection approach called Temporal-bEhavior-laNguage Signals for information Operation Recognition (TENSOR), which leverages multimodal data, including temporal online user behavior, such as message posting activities, and the textual content of the messages. The motivation is that IO users are typically a very small fraction of all online users and have unique temporal behavioral and language patterns. Specifically, we train a Temporal Point Process (TPP) to capture abnormal temporal behavioral patterns of IO users because they are known to behave in a coordinated manner for IO campaigns. We further introduce a novel evidence function that converts LLM responses, which are generated from user post timelines, into quantitative scores to adjust the TPP outputs for better IO user detection. Experimental results show that TENSOR outperforms the baselines on five real-world IO datasets. Code is available at https://github.com/xiuzhenzhang/TENSOR.

Low-resource languages remain challenging for machine translation, and Mongolian is a representative case. As a digraphic language, Mongolian is written in both Cyrillic and Traditional scripts, which exhibit a severe imbalance in data availability. While the Cyrillic script is relatively well-resourced, the Traditional script remains extremely data-scarce and orthographically ambiguous, leading to substantial performance degradation in direct translation. We propose CoPiT, a cognitively motivated pivot-based translation pipeline that exploits this internal resource hierarchy by routing translation through the Cyrillic script. The pipeline explicitly resolves script-induced ambiguity in the Traditional script before translation, enabling more stable and accurate meaning transfer. Across multiple backbone models and target languages, CoPiT consistently outperforms direct translation, achieving substantial absolute BLEU improvements together with consistent 1.5-1.6x COMET gains. These gains allow strong open-source models to match or outperform GPT-4.1 under comparable evaluation settings. Beyond inference-time improvements, CoPiT enables the construction of synthetic parallel data directly from Traditional-script text, mitigating data scarcity in realistic low-resource scenarios. We release a new multi-script parallel dataset covering Mongolian in both scripts alongside English, Korean, and Russian. All datasets and code are publicly available at https://anonymous.4open.science/r/anonymous_project-76C7.

Leading multilingual speech recognition models like Whisper transcribe diverse, low-resource languages without language-specific training but are computationally expensive to deploy. Token merging mitigates this inefficiency by dynamically combining redundant features, shortening the sequence length during inference without requiring retraining. In this paper, we systematically evaluate token merging on the Whisper model family across sixteen diverse languages and three different model sizes. We also test how token merging interacts with fine-tuning (DoRA) on low-resource languages. Our findings show that merging tokens increases computational efficiency with almost no loss in transcription accuracy across most low-resource languages and model sizes, and it works even after the model has been fine-tuned. Our results demonstrate that token merging is a highly practical method for making multilingual speech recognition faster and cheaper to deploy.

Logit-based watermarking is a widely used mechanism for identifying LLM generated content, yet its effectiveness is governed by a fundamental trade-off between detectability and semantic distortion. Existing analyses provide limited guidance for principled hyperparameter selection, leaving practical deployments reliant on heuristic tuning. In this work, we develop a power-calibrated statistical framework that establishes explicit quantitative relationships between watermark hyperparameters, detection power, and distortion. This characterization transforms watermark design into a guided optimization problem. Building on these results, we derive practical parameter selection procedures that achieve optimal tradeoffs under constraints. Extensive experiments across multiple language models and datasets validate the theory and demonstrate that the proposed framework consistently identifies Pareto-optimal points.

Sentiment analysis has been a primary domain under Natural Language Processing (NLP) from its inception as it plays a vital role in both real-world and research applications. In high-resource languages, this has been extended a step further, and instead of predicting sentiment at the sentence level, models have been developed to detect more fine-grained sentiments at aspect level. However, in order to conduct this fine-grained Aspect-based Sentiment Analysis (ABSA), datasets annotated with aspects and sentiments toward the said aspects is required. Such datasets are lacking for low-resources languages among which, we can count Sinhala, an Indo-Aryan languages used primarily in Sri Lanka. In this work, we introduce, SalAngaBhava, a new Sinhala Aspect-based Sentiment Analysis dataset which contains Sinhala product reviews that are manually labeled with aspect terms and the associated sentiments (positive, negative, neutral). The data was collected from domain-relevant sources such as user-generated reviews and comments, and was annotated following carefully defined guidelines to ensure consistency and quality. The dataset consists of sentences and aspect-sentiment pairs, encompassing a considerable range of aspects from several domains. The analysis confirms that the dataset is well-structured and sufficiently balanced for ABSA research. This dataset can be used as a benchmark and facilitates further studies related to Sinhala natural language processing, and low-resource sentiment analysis tasks.

Code-switching (CS), alternating languages within the same utterance, poses significant challenges for automatic speech recognition (ASR) due to limited CS training data. This paper applies an iterative pseudo-labeling training approach to CS-ASR for the first time, demonstrating its effectiveness in leveraging unlabeled data to improve CS-ASR performance. The approach comprises three phases: pseudo-label generation, two-stage bilingual model training, and iterative improvements. It begins by generating pseudo-labels from a large unlabeled corpus, creating a semi-supervised dataset. This dataset supports a two-stage training framework where the model is pre-trained and then fine-tuned on supervised CS data. Iterative refinements further enhance the model's accuracy in handling complex CS scenarios. Our approach significantly advances CS-ASR systems, achieving notable Mix Error Rate (MER) reductions on SEAME's devman (6.35%) and devsge (8.29%) subsets.

We systematically investigate neural speech enhancement systems, ranging from very small ($\sim$10,k parameters) to medium-large ($\sim$2-5,M parameters), which specialize to acoustic conditions using contextual information such as speaker identity, noise type, speaker gender, spoken language, and SNR. By fine-tuning generalist models on specific data subsets, we find that specializing to a speaker's identity consistently yields the largest gains in estimated speech intelligibility and quality. In contrast, specializing to SNR, noise type, or gender offers only marginal benefits. Crucially, we show that a small model specialized to both a specific speaker and a specific noise type can match or exceed the performance of a generalist model ten times its size. Further, cross-lingual tests reveal that models specialized to a target language outperform multilingual generalists, suggesting that language is a salient feature for specialization. These findings highlight the potential of small, adaptive models for resource-constrained applications like hearing aids, which specialize on-the-fly to contextual information.

Extending automatic speech recognition (ASR) to low-resource African languages is constrained by the prohibitive demands of data collection at scale. A promising direction is to leverage linguistic relatedness to enhance cross-lingual transfer from a related auxiliary language to the low-resource target by sequentially adapting on both. Although this strategy has shown meaningful improvements in small ASR models, its effectiveness in large ASR remains unclear. We extend this framework to large multilingual ASR through a systematic controlled experimental design spanning six factors, two Africa-centric corpora, and four large ASR models, isolating whether linguistic relatedness reliably predicts cross-lingual transfer gains in this setting. Across all conditions, pre-adaptation on related auxiliary languages yields no practically meaningful transfer improvements given minimal target-language data, suggesting that linguistic relatedness alone may not reliably predict cross-lingual transfer gains in large multilingual ASR, or constitute an effective strategy for extending such models to low-resource languages.

Efik, a tonal language spoken by about 3 million second language speakers and 1.5 million native speakers in Southeastern Nigeria, remains underrepresented in speech synthesis research. We present the first documented end-to-end text-to-speech study for Efik, introducing a curated single speaker corpus of 2,632 utterances totaling three hours and a comparative evaluation of four neural models (VITS, MMS-TTS, SpeechT5, and Orpheus-TTS) under low resource conditions. Native speakers evaluated the systems using MOS, Nat-MOS, and A-MOS. MMS-TTS achieved the highest MOS of 3.80 +/- 0.63 and produced more stable long form speech, though tonal errors persisted. Other models showed greater tonal and prosodic inconsistencies. These results provide a reproducible baseline and highlight the need for larger corpora and tone aware modeling for tonal African languages.

Portuguese remains underrepresented in text embedding evaluation, despite being one of the most widely spoken languages in the world. As a result, embedding models are often selected based on English or multilingual metrics, while their effectiveness in Portuguese remains unclear. We present MTEB-PT, a Portuguese benchmark constructed from a subset of MMTEB, comprising 14 existing datasets across Semantic Textual Similarity (STS), classification, retrieval, and reranking. We use this benchmark to evaluate 17 open- and closed-source embedding models under a unified protocol. Our results show that Portuguese performance is strongly task-dependent: multilingual rankings do not reliably predict Portuguese-specific performance across task families, no single model dominates all settings, and models with stronger long-context capacity are particularly advantageous on longer-input tasks such as retrieval and reranking. The benchmark also shows that language-specific fine-tuning still improves model performance in Portuguese, especially on task types that match the adaptation data most closely. To examine this effect, we fine-tune three representative backbone models with Portuguese contrastive supervision and Matryoshka Representation Learning (MRL). These benchmark-informed baselines yield their strongest gains on STS, consistent with the predominantly symmetric supervision used during training, while also improving retrieval and remaining competitive under dimensional truncation. We release the MTEB-PT benchmark, the fine-tuned models, and the training and evaluation code.

Robots deployed over long periods must reason about environments that change over time. Existing long-term perception systems often address object change reactively, updating their maps only after revisiting a scene and observing that an object has moved. Instead, robots should reason proactively about how long objects are likely to persist using the context in which they appear. For example, a car at a traffic light and a car in a parking spot share the same semantic class, but their contexts imply different persistence durations. We propose PreSIST (Predictive Scene-conditioned Instance Survival over Time), a method for predicting whether an observed object will remain in its last seen pose at arbitrary future times. PreSIST estimates instance-level persistence priors from object properties and scene context, then integrates these priors with a probabilistic persistence filter as observations become available. Its key insight is that the reasoning capabilities of vision-language models (VLMs) can relate scene context to likely object use and human activity, enabling persistence prediction before long-term observations are available. We develop two interchangeable variants: PreSIST-Lang, which estimates persistence priors using a VLM, and PreSIST-Vis, a novel vision-only model trained using PreSIST-Lang pseudo-labels for efficient deployment. Experiments on a new dataset of in-the-wild object persistence annotations show that PreSIST-Lang and PreSIST-Vis outperform baselines on open-world persistence prediction.

Recent hallucination detection techniques in large language models (LLMs) focus on directly extracting features from a model's internal representations and training a classifier on these features to detect hallucinations, demonstrating promising results. Notwithstanding this advancement, most internal-state hallucination detection techniques have been explored predominantly in English, raising the question of whether such internal signals generalize across different languages and domains. To address this gap, we present CrossHallu, the first study to evaluate the cross-lingual and cross-domain generalization of hallucination detection using internal representations from six LLMs on the generative question-answering task. We conduct a systematic Arabic <-> English evaluation using TruthfulQA, an Arabic translated version of TruthfulQA, and HalluScore. This evaluation encompasses monolingual training and testing, cross-lingual transfer, cross-domain transfer, and combined cross-lingual and cross-domain transfer. The results reveal that internal-state hallucination signals in LLMs transfer across languages and domains for most models, with cross-lingual performance highly dependent on both class separability and language alignment in the feature space, whereas cross-domain transfer within Arabic varies depending on the training and testing datasets used for the hallucination detector. The code is publicly available at https://github.com/aishaalansari57/CrossHal.

Dialectal data are scarce relative to Modern Standard Arabic (MSA), causing Arabic LLMs to overproduce MSA and struggle with dialectally accurate generation. This raises a fundamental interpretability question about where and how dialectal features are encoded within model internals and whether these representations can improve dialect generation without fine-tuning. We study two inference-time approaches as interpretability probes and control mechanisms. First, neuron-level analysis identifies sparse populations that encode dialect-specific features and tests whether amplifying or suppressing them steers model outputs toward target dialects. Second, vector steering extracts dialect-specific activation directions and injects them during inference, motivated by feature entanglement at the neuron level. We find that these neurons are real but only partially explanatory. They occupy under 1% of MLP dimensions but span only 5% to 21% of the residual dialect direction. This limited coverage is causally consequential. Neuron steering reinforces dialect in some varieties when the prompt is already dialectal but cannot induce it from MSA prompts, whereas vector steering succeeds in both settings. Arabic dialects are therefore steerable mainly through distributed rather than localized representations

Human reasoning often operates through qualitative concepts expressed by linguistic labels such as high, low, expensive, or cheap, whose interpretation depends on context and is usually vague, despite being rooted in numerical data. This paper explores a novel fuzzy-logic-based qualitative extension of Answer Set Programming (ASP) to bridge numerical information and qualitative reasoning. The underlying language, formally introduced in a separate work, provides a principled framework that avoids rigid thresholds and supports robust reasoning under vagueness. Focusing on a representative use case, we illustrate how the framework integrates numerically grounded inputs (such as outputs of machine learning models) with symbolic reasoning over qualitative labels. Key features, including learning-based membership functions and semantically enriched predicates, enable the combination of expert knowledge, contextual factors, and subjective interpretations within a unified declarative setting.

Long-form recordings (LFRs) of child-centered audio are ecologically valid sources for studying early language development, but three problems limit their use. First, LFR corpora are collected across sites with heterogeneous formats and consent structures, making cross-corpus use non-trivial. Second, without standardized benchmarks, assessing whether tools generalize across languages and conditions is hard. Third, ML workflows rarely respect privacy constraints governing sensitive child speech. This paper presents a framework addressing all three: a standardized collection of 27 child-centered datasets built with open-source tools (S1); a replicable pipeline for four speech-processing benchmarks (S2); and ELSI, a role-based ecosystem embedding ethical governance into the ML workflow (S3). We demonstrate the framework via a voice type classification case study and show the three solutions are mutually dependent.

The use of Large Language Models (LLMs) across diverse areas of human activity-ranging from everyday tasks to safety-critical applications-aims to enhance decision-making effectiveness with minimal human feedback. Concurrently, it seeks to align decisions with human expectations, preferences, and needs while mitigating risks associated with AI non-determinism. However, humans frequently over- or under-rely on AI recommendations, and current AI systems remain poorly calibrated to human expectations. To address these challenges, we introduce a human-AI collaborative decision-making framework designed to augment human capabilities and align AI agents with human preferences and expectations. Specifically, this paper (a) formulates the collaborative decision-making task as a stochastic game between an AI agent and a human player, and (b) proposes the Human-Centric Reflective Architecture (HCRA), which integrates human-calibrated models with reinforcement learning agents that leverage linguistic feedback in an iterative, reflective process. Evaluation results demonstrate that HCRA enhances decision-making effectiveness and delivers high-quality recommendations.

Cross-lingual retrieval-augmented generation (RAG) is often deployed in an English-evidence regime, where users query in diverse languages but retrieved passages remain English. In this setting, generation can fail despite strong base models: English evidence induces language drift (English or code-switching outputs) and models use evidence unreliably when producing non-English answers. We attribute these failures to two post-training challenges: (i) errors are prefix-dependent, so fixed-trajectory supervision suffers from prefix mismatch; and (ii) sequence-level (partly discrete / judge-based) rewards yield noisy credit assignment and high-variance updates. We propose TR-RAG, a teacher-regularized RL recipe that couples reward optimization with on-policy distillation on student-visited prefixes. A compact student samples on-policy answers, while a stronger frozen teacher is queried only on those prefixes and provides a prefix-wise student-to-teacher reverse-KL anchor. We further introduce a reward decomposition for English-evidence multilingual generation, combining language consistency, character 3-gram recall, and an LLM-judge score for evidence-grounded correctness. Across three benchmarks (BioASQ-ENKB5, Hotpot-ENKB5, and naturally multilingual MKQA) and two backbones, TR-RAG improves the composite of language adherence and evidence-grounded correctness over strong baselines. Crucially, the teacher anchor acts as a safety net: on in-domain languages it prevents the large language-consistency collapses (up to ~27 percentage points) that reward-only RL can suffer by drifting below even the base model, while on distant out-of-distribution languages, where reward-only RL stalls at the base model's ceiling, it still improves evidence grounding; and on character 3-gram recall the compact student sometimes surpasses its 70B teacher.

Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records. Parsing this content into structured, machine-readable formats is critical for unlocking global knowledge. However, existing benchmarks predominantly focus on high-resource languages like English and Chinese, creating an evaluation blind spot concerning model performance on other languages. While recent Vision-Language Models (VLMs) claim support for hundreds of languages, the lack of ground truth makes it impossible to empirically verify these capabilities. To bridge this gap, we introduce MORE, a large-scale benchmark designed for multilingual document parsing evaluation. MORE distinguishes itself through three key dimensions: (1) Unprecedented Scale: It covers 149 languages, making it the most linguistically diverse benchmark to date; (2) Structural Complexity: Unlike previous works, it extends evaluation beyond plain text to include structural elements such as code blocks, tables, and catalogs; and (3) Data Authenticity: All samples are curated from real-world documents via a model-assisted, human-refined annotation pipeline. We evaluate state-of-the-art models using MORE, establishing new performance baselines for long-tail languages and validating the benchmark's effectiveness in diagnosing model capabilities in realistic, diverse scenarios. The MORE dataset will be available at https://github.com/zimoqingfeng/MORE.

Language models are increasingly used to quantify cultural phenomena, but what makes such measurement distinctively cultural? This paper argues that NLP work on culture is a material-discursive practice: the apparatus -- model, data, annotation, evaluation -- participates in constituting the cultural reality it measures, rather than passively recording it. Drawing on Karen Barad's concept of the agential cut -- the contingent boundary between phenomenon and instrument -- I show that the apparatus's substantive design choices draw such boundaries, and that the boundary is entangled from the start because language models have already internalized much of the cultural material they measure. I illustrate this through three case studies on television and film dialogue (measuring structure, interaction, and deviation) and three examinations of the apparatus itself (erasure of cultural markers, attunement to historical material, and agency in an agentic workflow). This big picture analysis proposes a research program that is theory-driven, empirically rigorous, and culturally contingent, treating each agential cut as a conscious commitment, at once methodological and ethical.

LLM-as-a-Judge has become the dominant evaluation paradigm for many natural language generation tasks (albeit mostly in English) due to shortcomings of conventional metrics and high correlations with human judgment. There are now attempts to extend LLM-as-a-Judge to multilingual settings including low-resource languages. However, LLMs have limited proficiency in low-resource languages, and there is often no adequate human validation in these settings. To highlight the scope of the problem and current practices, we explore the use of LLM-as-a-Judge evaluators in ACL Anthology papers focusing on multilingual settings and low-resource languages across a diverse set of tasks. Out of 650 papers mentioning LLM-as-a-judge, only 33 of them focus on low-resource or multilingual settings. Our in-depth analysis of these papers indicates inconsistent evaluation outcomes, a tendency to overtrust LLM judgments in multilingual settings, and the widespread reliance on a single judge model per study. To help the NLP community further, we conclude with a checklist of recommendations about how to use LLM-as-a-Judge in multilingual and low-resource settings

Large Language Models are increasingly deployed in emotional-support contexts and crisis-related situations. Nevertheless, their cross-lingual abilities in these circumstances remain underexplored. Existing benchmarks emphasize multilingual performance but rarely examine crisis-related empathy and cultural grounding in low-to-mid-resource languages. We introduce SPLIT, a 500-prompt benchmark designed to evaluate LLM consistency in generating emotionally grounded responses across five categories: Stress, Panic, Loneliness, Internal Displacement, and Tension. We evaluate three technically diverse LLMs across three dimensions: Empathetic Accuracy, Linguistic Naturalness, and Contextual & Cultural Grounding. The framework aims to assess and compare the quality of LLM responses in both English and Ukrainian languages, as well as to explore the reliability of the LLM-as-a-jury paradigm. Our findings reveal that Gemini-2.5-Flash and LLaMA-3.3-70B-Instruct degrade when transitioning to Ukrainian, while DeepSeek-V3 remains comparatively stable within our benchmark. We additionally find that human and AI evaluators agree weakly on empathy and naturalness but diverge on cultural grounding. We further argue that producing Ukrainian text is not equivalent to producing Ukrainian emotional support. Our findings may assist in the future development of more culturally tailored benchmark designs, as well as encourage a stronger emphasis on human-centered evaluation.

Recent advances in automatic speech recognition (ASR) have explored different sequence models, including Conformer-based models and newer state space models such as Mamba. Although prior work has evaluated these architectures in multiple languages, their effectiveness in African languages remains underexplored. In this work, we evaluate Mamba for ASR on seven South African languages. In monolingual experiments, each model is trained on 50 hours of speech per language, and we compare Mamba to a Conformer baseline of similar parameter scale. Mamba achieves similar recognition accuracy to Conformer while using fewer computational resources and training faster. We further evaluate generalization in this setting and find that both models struggle to generalize to speech that is much longer than what they were trained on. We then study multilingual ASR using Mamba models, where the baseline is pooling all languages together. On top of this, we tested three extensions: training with language-family information by adding both language and language-family embeddings as biases to the downsampled acoustic representations, and multitask learning with a CTC ASR objective and a language identification (LID) head. We find that multilingual training consistently improves performance over monolingual training. However, adding explicit language information does not improve in-domain performance but does improve cross-corpus robustness. We conducted ablation studies in low-resource multilingual settings using 5-hour and 10-hour per-language training data, where we observed gains from using language embeddings and further demonstrated that removing or altering them hurt model performance. Lastly, we analysed these embeddings and find that they do not capture linguistic similarity in a typological sense, but instead act as task-specific control vectors.

Cross-lingual speaker verification (SV) systems typically exhibit performance degradation when enrollment and test utterances are spoken in different languages. However, standard evaluation protocols confound language mismatch with inter-speaker variability, as evaluation is generally performed with different speakers across languages. In this work, we introduce a bilingual same-speaker evaluation set for five Iberian languages, enabling analysis of cross-lingual SV under constant speaker identity. We apply this setup to a HuBERT-based SV system previously shown to exhibit strong language dependence, and analyze results using the Cross-Lingual Transfer Matrix (CLTM) to study pairwise cross-lingual transfer. Our results show that speaker-related variability accounts for part of the observed degradation, but language mismatch remains the main driver of cross-lingual performance loss. These findings provide a more precise characterization of language dependence in cross-lingual SV.

Open web-scale pre-training corpora remain concentrated in English, limiting multilingual LLM development. We introduce MultiSynt/MT, an open synthetic parallel corpus with approximately 4.8 trillion target-language tokens across 36 languages, produced by translating 100 billion high-quality Nemotron-CC tokens with Tower+ and OPUS-MT/HPLT-MT systems. For many medium- and lower-resource European languages, this is the largest openly available pre-training resource. Across five high- and medium-resource languages, reference LLMs trained on MultiSynt/MT reach the final score of HPLT 2.0, a native-data baseline, using roughly 72% fewer pre-training tokens, and outperform it by approximately 15% relative at a matched 100B-token training budget. Our analyses also identify evaluation blind spots: standard multiple-choice benchmarks miss translation-quality differences that a fluency-sensitive LLM-as-judge protocol recovers on the trained LLMs without detecting a deficit relative to its native-data baseline, while Norwegian idiomatic and culturally grounded tasks remain better served by native data. We release the corpus, including row-aligned translations from multiple systems, to support controlled research on multilingual pre-training data and evaluation.

Multilingual fluency often invites a stronger assumption: a model that can speak a user's language must also understand the culture encoded by that language. We call this the Illusion of Cultural Alignment. To test this assumption directly, we introduce MSQA, a benchmark of 1,064 natively sourced questions across 11 language groups, five cultural dimensions, and three difficulty tiers. Unlike translated benchmarks, MSQA targets locally grounded knowledge and reduces shortcuts from English-centric cross-lingual transfer. Evaluating 18 LLMs, we find substantial cultural degradation and a pronounced Locality Effect: cultural competence tracks pre-training exposure more closely than general reasoning ability. We further show that common inference-time remedies do not dissolve the illusion. Models remain overconfident on unfamiliar cultural questions, repeated sampling yields unstable rather than reliable correctness, and retrieval augmentation helps unevenly on long-tail facts. These findings indicate that cultural alignment cannot be inferred from multilingual ability alone and requires deeper intervention than calibration, sampling, or retrieval at inference time

Large reasoning models (LRMs) have achieved strong reasoning capabilities in English, yet their performance degrades significantly when required to reason in other languages. A natural solution is to transfer the model's English reasoning ability to target languages. However, existing transfer approaches typically rely on distilled target-language reasoning traces from stronger LRMs or online supervision from external judge models, which are costly and difficult to scale. In this paper, we propose PCS (Progressive Code-Switching), a more efficient transfer framework that requires only lightweight translation without any stronger model for distillation or judging. PCS first constructs code-switched reasoning traces by translating a subset of English reasoning steps into the target language, and uses them to initialize the model's code-switching ability via supervised fine-tuning. It then applies reinforcement learning with a step-level language consistency curriculum, progressively raising the target-language ratio until the model reasons entirely in the target language. This progressive design provides a smooth transfer path that avoids the instability and performance degradation commonly observed when directly enforcing target-language reasoning. Experiments on multiple benchmarks and five typologically diverse languages show that PCS substantially narrows the performance gap between target-language and English reasoning, yielding more language-consistent reasoning while maintaining competitive accuracy.

Maltese, although a low-resource language, has its own text corpora and pretrained language models, but we are aware of only one real labelled PDF corpus for OCR training, 57 pages, far below what paragraph-level training needs. With no real corpus to train on at scale, we built a synthetic training pipeline and a 5-stream Tesseract ensemble voted under a lexicon-anchored, ROVER-style scheme adapted for a low-resource setting. We call the Maltese submission LV-ROVER-MLT: an engineered adaptation of LV-ROVER's voting algorithm, not a new one, submitted to the DocEng 2026 competition. All results below are dev-set figures from the competition's own benchmark; the held-out real test CER is unknown at the time of writing and this paper does not claim one. We report results on a 422-paragraph benchmark against a fine-tuned Tesseract baseline with a character error rate of 0.0234. Ensemble recognition alone, scored under the same label convention as the baseline, improves character error rate by 44 percent to 0.01317. A post-processing chain that aligns Tesseract's straight-quote and dash output to the benchmark's curly-quote convention, plus one stage that recovers misread diacritics, brings the full pipeline to a character error rate of 0.00700, a 70 percent reduction. We also tested the same method, unchanged, on Hungarian and Luxembourgish: a bootstrap and permutation audit confirms a 33.7 percent character error rate improvement on Luxembourgish, while the Hungarian margin, 0.8 percent, is not statistically significant.

Metacognition is a critical component of intelligence that describes the ability to monitor and regulate one's own cognitive processes. Yet LLMs exhibit systemic deficiencies in key metacognitive faculties: they hallucinate with high confidence, fail to recognize knowledge boundaries, and misrepresent their internal uncertainty--undermining trustworthiness and reliability. Since monitoring task performance and adapting behavior accordingly are central to metacognition, we posit that models capable of accurately judging their own performance are better positioned to improve it. We operationalize this idea via two novel mechanisms: reinforcement learning with metacognitive feedback (RLMF), a paradigm to refine completion rankings during preference optimization based on the quality of a model's self-judgments of performance, and metacognitive data selection, which uses similar self-judgments to identify high-value training examples, outperforming naive active learning. We apply these innovations to the problem of faithful calibration (FC), a task that is itself fundamentally metacognitive: the goal is to align expressed with intrinsic uncertainty, difficult even for frontier LLMs. We adopt a two-stage, decoupled approach, first using these methods to calibrate the faithfulness of models' self-reported confidence scores, then mapping to natural, context-adaptable linguistic uncertainty via targeted output editing. Extensive experiments show RLMF achieves generalizable, state-of-the-art FC on diverse tasks while preserving accuracy. Further, RLMF surpasses standard RL by up to 63% while enhancing models' ability to assess and express their own capability limits. This positions RLMF as a promising paradigm to enhance LLM metacognition toward improved abilities and alignment, and suggests metacognitive performance as an effective RL signal to overcome limits of prior intrinsic feedback methods.

State-of-the-art speech datasets predominantly focus on widely spoken languages, often overlooking low-resource languages such as Luxembourgish, which remain underrepresented in speech technology research. In this work, we introduce LuxEmo, a 21-hour conversational expressive speech corpus for Luxembourgish with 4 emotion categories. LuxEmo is derived from Radio Télévision Luxembourg (RTL) youth broadcasts, using automated detection followed by human validation. We propose a semi-automatic curation workflow combining voice activity detection, denoising, language identification, LuxASR-based segmentation, automatic emotion prediction, lexical cues, and targeted human review. Additionally, we benchmark five expressive TTS systems covering German-based cross-lingual transfer, multilingual Luxembourgish support, Luxembourgish adaptation, and non-parametric prosody transfer. Performance is evaluated using both objective metrics and human evaluation.

Relation extraction (RE) for low-resource languages is typically constrained by the lack of annotated corpora. We investigate the feasibility of cross-lingual RE for Romanian by combining automatic dataset translation with large language model (LLM) inference. We translate the SemEval-2010 Task 8 benchmark from English to Romanian using an LLM-based translation pipeline and evaluate Gemma 4 31B under zero-shot, few-shot, and QLoRA fine-tuned configurations, against four encoder baselines spanning 125M to 560M parameters: XLM- RoBERTa (base and large), Romanian BERT, and RoBERT- large. We assess two task formulations: relation classification with marked entities and end-to-end extraction. Our results show that Romanian incurs a 3 to 5 percentage point (pp) drop relative to English in prompt-only settings, that few-shot prompting provides marginal gains over zero-shot, and that QLoRA fine-tuning improves macro F1-Score by more than 22 percentage points in both languages while reducing the cross-lingual gap from 3.3 to 1.4pp. The encoder baselines come within 1-4pp of QLoRA Gemma on Romanian despite being 50-250 times smaller, with monolingual Romanian BERT at 125M parameters matching multilingual XLM-R at 278M. The case for using a 31B model for single-task RE on Romanian is therefore weak in deployment scenarios where compute matters. We release the translated dataset, evaluation code, and trained models.

We present LuckyStar 111B, a 111B-parameter hybrid reasoning model developed through a collaboration between Cohere and LG CNS for Korean-English enterprise agents under practical memory and serving constraints. The model trains from Cohere's fully post-trained Command A model rather than a new pretraining run, and uses preamble conditioning to switch between concise non-reasoning behavior and longer tool-oriented reasoning. We study four choices for scaling tool-using agents efficiently: multilingual supervised fine-tuning, reinforcement learning with verifiable rewards for multi-step tool-use tasks, language-consistency rewards for Korean user-facing responses, and 4-bit quantization for single-GPU serving. The adapted model improves mathematical reasoning, function calling, and agentic natural-language-to-SQL (NL2SQL) performance while preserving general Korean and English instruction-following quality. These results provide a practical recipe and failure-mode analysis for adapting post-trained multilingual models to verifiable agentic workflows under memory-constrained deployment.

SSL speech models capture rich phonetic, prosodic, and acoustic patterns from raw audio, yet how they encode articulatory information across diverse languages remains unclear. Using EMA data from bilingual Finnish-Russian speakers, we evaluate cross-lingual correlations between SSL latent representations and articulatory movements. Models achieve strong prediction performance (Pearson r up to 0.68) even with approximately 5 minutes of training data, with multilingual models outperforming monolingual ones. Intermediate layers encode articulatory features most effectively, and tongue movements are more predictable than lip movements. We also assess the impact of task type (read versus spontaneous speech) and language proficiency, finding higher accuracy for structured tasks and strong generalization across proficiency levels. These results enhance the interpretability of SSL models and show their potential for speech-technology applications.