Linguistics

This paper examines how the labour of translators has been transformed into foundational data capital for the age of artificial intelligence (AI). Translation memories (TM) and parallel corpora preserve a one-to-one correspondence between source and target text and therefore constitute extraordinarily valuable supervised training data for machine translation. The development of statistical machine translation (SMT), neural machine translation (NMT), the Transformer architecture, and multilingual large language models (LLMs) cannot be disentangled from the accumulation of such translation data. And yet, translators' renditions have been bought as deliverables under contract, segmented as technical objects, and processed as "information analysis" data under copyright law -- losing their moral, creative, and economic attribution to the translators who produced them. The paper develops two concepts to capture this process. The first is appropriation without consumption: a mode of use in which works are not read, viewed, or listened to, but only mined for statistical features -- a use that is legitimated under Article 30-4 of the Japanese Copyright Act. The second is the invisible teacherisation of translators: the process by which translators, through the construction of translation memories, post-editing, and quality assessment, have functioned as teachers of AI without recognition as such. Drawing on the data supply chain that runs from translators through language service providers (LSPs) and platforms to model developers, on a comparative reading of Japanese, European, and United States legal frameworks, on the distinction between open and proprietary AI models, and on the premium status that human-generated data has acquired in the era of model collapse, the paper asks what translators are actually afraid of, and points toward concrete directions for redistributive design.

AI agents now participate as first-class team members across the software development lifecycle, yet no specification language exists for expressing the human-agent responsibility boundaries, approval gates, and governance constraints this collaboration requires. Existing approaches encode process in agent prompts (subject to drift), target adjacent domains (workflow management, business processes), or address only fragments (access control, approval gates). We propose a domain-specific language for specifying AI-SDLC processes as protocols, with formal syntax, well-formedness conditions, operational semantics, and enforcement invariants. The language distinguishes policy (declared intent) from mechanism (structural enforcement), enabling implementations to bound process non-determinism through primitives such as validation tokens and capability boundaries. Three results follow. A failure rate analysis shows that structural enforcement bounds system failure rates at a weighted product of agent and validator rates, while behavioral compliance permits cumulative or near-saturating growth. The 2+N team pattern (two human-in-control roles plus N specialized agent members) formalizes classical Separation of Duties for AI-SDLC. Kleene closure of orchestration loops and reflexive protocol-adherence validation emerge as design properties rather than special-case constructs. We position the contribution against multi-agent frameworks (MetaGPT), workflow specification (FlowAgent, BPMN extensions), and capability-based security (SAGA): the novelty lies in the specific integration, not any single primitive. A working implementation demonstrates feasibility; empirical evaluation is future work.

Tokenizer fertility the number of tokens per word imposes a hidden cost on non-English NLP. We measure fertility for ten foundation models across 25 European languages on parallel text, producing the first controlled tokenizer tax map for the continent. The tax spans 2.5x from English (1.2 tokens/word) to Greek/Maltese (~3.1), following a clear hierarchy: Romance (1.5-1.7), Germanic (1.7-1.9), Slavic (2.2-2.5), Uralic/Baltic (2.7-3.0). Ukrainian (2.7) pays 15-18% more than cognate Slavic languages, reflecting underrepresentation in pre-training data. Fertility rankings are domain-invariant across three text registers (rho > 0.97). A subword analysis reveals that high-fertility tokenizers fragment morphological boundaries rather than preserving them. Cross-lingual few-shot evaluation on four Slavic languages shows that few-shot effects are model-intrinsic, not language-dependent. We release all measurements as a public dataset.

Multilingual retrieval increasingly underpins cross-lingual question answering and retrieval-augmented generation. Strong zero-shot scores on multilingual benchmarks are often taken as evidence that current encoders transfer reliably across many languages. We argue that this assumption breaks down for underrepresented, morphologically rich languages, and use Amharic as a diagnostic case. Under a shared passage retrieval protocol covering dense, late-interaction, learned sparse, and cross-encoder paradigms, we compare zero-shot multilingual retrievers, Amharic-fine-tuned multilingual retrievers, and monolingual Amharic retrievers. The strongest zero-shot multilingual retriever underperforms the strongest monolingual Amharic first-stage retriever by 23% relative MRR@10. Fine-tuning two recent multilingual embedding models on the same Amharic supervision yields 32-60% relative MRR@10 gains over zero-shot, but the best Amharic-fine-tuned multilingual model remains below the strongest monolingual Amharic retriever. These findings indicate that zero-shot multilingual retrieval is not a sufficient proxy for equitable information access in the LLM era: for underrepresented languages, retrieval must be evaluated and adapted in-language rather than inferred from aggregate multilingual benchmarks. To foster future research, we publicly release the dataset, codebase, and trained models at https://github.com/rasyosef/amharic-neural-ir.

Legal NLP benchmarks evaluate models on randomly split data, implicitly assuming that legal language is stationary. We test this assumption by fine-tuning four transformer encoders -- XLM-RoBERTa (base and large) and their legal-domain variants -- on Ukrainian court decisions from three temporal epochs defined by geopolitical disruptions: pre-war (2008-2013), hybrid war (2014-2021), and full-scale invasion (2022-2026). Each model is trained on one epoch and evaluated on all three, producing a 3x3 cross-temporal generalization matrix. Four findings emerge. (1) Forward degradation is severe: models trained on pre-war data lose up to 27.2 percentage points of macro-F1 when applied to full-scale invasion era decisions. (2) The degradation is asymmetric: backward transfer (full-scale to pre-war) is substantially more robust than forward transfer, consistent with the hypothesis that legal language is additive. (3) Legal-domain pretraining (Legal-XLM-R) does not improve absolute performance but reduces forward degradation magnitude and asymmetry. (4) Chronological continual learning eliminates catastrophic forgetting for general XLM-R: pre-war knowledge is fully retained (+1.8 to +6.2 pp) while full-scale performance gains +16.5 to +19.0 pp; reverse-chronological training causes severe forgetting. Cross-jurisdictional pretraining on Swiss Judgment Prediction data improves absolute performance but does not reduce temporal degradation magnitude, confirming that temporal drift is an intrinsic property of legal language evolution. The dataset (428K decisions across three epochs) is publicly available as a LEXTREME contribution.

Language models (LMs) can exhibit biases based on variations in their dialects, even in the absence of a dialect label, a behavior known as covert dialect bias. In this work, we quantify covert dialect bias in online discourse by evaluating how LMs associate stereotypical traits (derived from social psychology research on racial bias) with intent-equivalent tweets in Standard American English (SAE) and African-American Vernacular English (AAVE). While prior work shows that LMs associate more negative stereotypes with AAVE when evaluating tweets in isolation, we are surprised to find that this bias is significantly exacerbated when SAE / AAVE tweet pairs are compared side by side, a setting that more closely reflects high-impact decision making contexts in which models are used to rank candidates. The bias only worsens when dialect labels are explicitly specified. This is striking, given the extensive efforts from commercial developers to mitigate bias in their LMs. Encouragingly, we show that counterfactual fairness finetuning can mitigate covert dialect bias for some stereotypical traits, reducing average disparities when evaluating tweets in isolation, however, these improvements do not consistently hold across traits when evaluating SAE / AAVE tweets side by side. Our findings show that existing evaluation settings for covert dialect bias may underestimate its severity, specifically in contrastive settings. Additionally, overt dialect bias remains pronounced even after safety aligned finetuning, indicating that it remains an unresolved problem, and motivates the need for more robust evaluation and mitigation frameworks.

Lexical gaps are words that do not exist in certain languages. They pose challenges for building multilingual lexical resources, for machine translation, and for cross-lingual transfer. Existing lexical gap detection relies on human judgments or fixed conceptual taxonomies. We propose a data-driven framework for identifying cross-lingual lexical gaps. We extracted contextualized embeddings from Korean-English bilingual LLMs for Korean-to-English and English-to-Korean translation pairs. Combinations of LLMs, embedding types, dimensionality, and orthogonal transformations across 100 train-test splits yielded 4000 distinct embedding spaces in each source language. In each space, we computed the semantic similarity between each source word and its nearest neighbor in the target language, and compared their distribution for gap words versus non-gap words. In 94% (Korean-to-English) and 97% (English-to-Korean) of embedding spaces, gap words showed weaker cross-lingual semantic alignment than non-gap words. Logistic classifiers trained on unaligned embedding spaces can reliably separate gap words from non-gap words, achieving AUCs of 0.81 (Korean-to-English) and 0.76 (English-to-Korean) and retrieving 18/19 Korean and 26/27 English gap words. This approach provides a language-agnostic and taxonomy-free method for scalable lexical gap identification.

Cross-lingual knowledge transfer is critical for building high-performing multilingual language models for languages with insufficient training data. When target language data is scarce, the knowledge required for many downstream tasks involving scientific reasoning, commonsense inference, and world knowledge must be acquired primarily from the high-resource language, making effective knowledge transfer essential. Existing methods for improving such cross-lingual knowledge transfer require large amounts of parallel data, translation systems, auxiliary models, or additional training stages that are largely unavailable for many languages. We propose LINK - a data-level intervention method that improves knowledge transfer during model pretraining through lexical substitutions in high-resource part of pretraining data using bilingual vocabularies. For a given replacement ratio, randomly selected words in a portion of the high-resource (English) training corpus are swapped with their word-level translations, requiring no additional model training and only a bilingual vocabulary, which can be obtained at near-zero cost for virtually any language. Evaluation on eight languages across five model sizes shows notable improvements on downstream tasks in the target language, with up to a 2x speedup in training to reach equivalent performance.

Natural Language Generation (NLG) evaluation has changed dramatically since 1990, and will continue to evolve in the future. In 1990, when NLG had close ties to linguistics, there was very little formal experimental evaluation in the modern sense. In 2026, when NLG is closely linked to machine learning, experimental evaluation is expected and indeed fundamental to research. Many evaluation techniques were developed over this period, including most recently LLM-as-Judge. I expect NLG evaluation will continue to evolve in the future. In particular, impact, qualitative, and safety evaluation will become more important as large numbers of people routinely use NLG technology.

While factual correctness and task-performance have been in focus of Large Language Model (LLM) research for a long time, the fundamental question of how human-like generated texts are on a linguistic level has been underexplored. From a corpus-linguistic perspective, language production is inherently context-dependent, with distinct communicative contexts giving rise to differences in frequencies and co-occurrence patterns of linguistic features. A text failing to adhere to these patterns can be content-wise correct, but still be unfavorable to human readers. In this work, we propose a context-aware evaluation framework in which human-likeness is assessed using a two-sample problem between the linguistic feature distribution of a human reference corpus for a given register and a corresponding LLM-generated corpus. We implement this framework using the Maximum Mean Discrepancy (MMD) and the 67 lexico-grammatical features introduced by Biber, which are commonly applied in corpus linguistics. In our experiments, we compare seven instruction-tuned, open-source models across five English-language datasets spanning distinct registers against a human baseline. While across all tested setups, LLMs deviate from the human baseline, which models are closest to human language depends on the register and is not dictated by model size.

The attack surface of a multimodal large language model (MLLM) is language-dependent in ways that reveal the mechanistic structure of alignment failures. We present the first systematic cross-lingual, multimodal red-teaming study comparing jailbreak vulnerability in US English (en-US) and Mexican Spanish (es-MX) across four frontier MLLMs: Claude Sonnet 4.5, GPT-5, Pixtral Large, and Qwen Omni. Using a fixed adversarial benchmark of 363 diverse prompt scenarios administered in text-only and multimodal conditions, we collected 52,272 harm ratings and binary attack success judgements from matched panels of nine native-speaker annotators per language group. Our central finding is that language does not scale vulnerability uniformly. Bayesian mixed-effects analyses reveal that linguistic framing attacks such as role-play become substantially less effective under Spanish prompting, while visually explicit multimodal attacks become more effective, which directly implicates the prompt-language interface rather than global annotator leniency. This dissociation indicates that linguistic and visual alignment failures operate through distinct mechanisms, and that switching language is sufficient to expose that separation. The practical consequence is that safety rankings are not preserved across languages. Qwen Omni overtakes Pixtral Large as the most vulnerable model among es-MX participants, a rank reversal no scalar correction of English-condition scores could recover, and absolute attack success rates have declined across model generations without closing the gaps between them. These findings demonstrate that safety evaluation frameworks treating language and modality as independent dimensions fundamentally misspecify the attack surface of globally deployed MLLMs, and must be redesigned accordingly.

Large language models (LLMs) are increasingly used across diverse linguistic and cultural contexts, yet their cultural knowledge remains uneven across regions and languages. We present the DFKI-MLT system for SemEval-2026 Task 7 on cultural awareness, where we apply activation steering to multilingual LLMs using language vectors extracted from parallel FLORES data. Our method performs inference-time adaptation by adding language-specific steering vectors to the residual stream at a selected transformer layer, without any parameter updates. We participated in both the short-answer (SAQ) and multiple-choice (MCQ) tracks; however, only our MCQ submission received an official score. In the official MCQ track, we achieved 86.96% accuracy, ranking 7th out of 17 teams. To better understand system behavior, we conduct post-hoc analyses on the shared-task MCQ and SAQ settings. These analyses show that activation steering yields modest and heterogeneous improvements on cultural reasoning: gains are strongly layer-sensitive, vary substantially across language-region pairs, with some configurations even degrading performance, and interact with prompt formulation, comparing generic and culturally conditioned prompts. Our findings suggest that prompt design and activation steering should be jointly optimized for culturally aware multilingual inference.

Model collapse, the progressive degradation of LLMs trained on their own outputs, has been characterized statistically but lacks a linguistic explanation for which structures degrade, in what order, and why. We show that iterated learning theory from cultural evolution fills this gap. We derive five falsifiable predictions, distinguish those uniquely discriminative for the theory from confirmatory ones, and test them by self-training LLaMA-2-7B and Mistral-7B over 10 generations in English, German, and Turkish. The critical discriminative finding: compositionality follows a non-monotonic trajectory (initially rising, then falling) under unfiltered self-training. This signature persists with maximally regular seed data (ruling out noise removal) and is sustained only by task-grounded filtering, not random filtering, providing the first LLM-scale evidence for the compression-communication tradeoff. All predictions are confirmed with large effect sizes (Hedges' $g > 1.6$; $\mathrm{BF}_{10} > 100$), and LLM regularization gradients closely match human behavioral data ($R^2 = 0.94$). These results reframe model collapse as a cultural transmission phenomenon and yield concrete principles for self-training pipeline design.

How do learners acquire knowledge of what is unacceptable without negative evidence? Construction Grammar proposes statistical preemption: exposure to a conventional form (e.g., "donated the books to the library") preempts structurally possible but unattested alternatives ("*donated the library the books"). We present a computational study that, for the first time, directly dissociates statistical preemption from the competing entrenchment hypothesis in large language models within a single converging design. Across four experiments spanning 120 English verb-construction pairings (dative, causative, locative), we show that (1) LLM surprisal patterns correlate strongly with human acceptability judgments ($r = 0.79$), validated against three independent behavioral datasets; (2) these patterns are driven by competing-form frequency rather than overall verb frequency, confirmed by non-circular partial correlations; (3) preemption sensitivity scales as a power law with model size; and (4) a controlled fine-tuning intervention causally demonstrates that manipulating competing-form frequencies shifts preemption behavior in the predicted direction, with reverse-direction controls ruling out frequency-sensitivity confounds. These results provide converging evidence that neural language models acquire negative linguistic knowledge through distributional competition, the core mechanism posited by Construction Grammar.

Sparse autoencoders (SAEs) enable feature-level mechanistic interpretability and activation steering in large language models (LLMs), but SAE-based language control remains unreliable in multilingual settings: most SAEs are trained on English-only data, and steering layers are chosen heuristically. We address these limitations by advancing a principled, mechanistic account of multilingual language steering with SAEs. First, we show that training SAEs on multilingual data consistently strengthens cross-lingual representations and yields more reliable, quality-preserving language control across layers and model families. Second, we introduce an \emph{a priori} steering layer-selection rule based on the intersection of multilingual alignment and language separability, which predicts effective intervention depths without exhaustive layerwise search. We evaluate our approach on LLaMA-3.1-8B and Gemma-2-9B across machine translation and cross-lingual summarization (CrossSumm), using SpBLEU, ROUGE-L, COMET, and LaSE. Our results show that multilingual SAEs combined with intersection-selected layers stabilize the trade-off between language identification accuracy and generation quality, providing a principled, predictive, representation-level account of multilingual SAE steering.

Brain-LLM alignment is well established in English, yet the brain's language network is neuroanatomically universal across languages. Does alignment also generalize cross-linguistically, and what governs the variation? We test this using fMRI data from 112 participants across English, Chinese, and French (the Le Petit Prince corpus) and seven LLMs spanning English-dominant, Chinese-dominant, and multilingual architectures. Our central finding is that training-language dominance, not an inherent property of English, drives the alignment pattern: a Chinese-dominant model (Baichuan2-7B), architecture-matched to LLaMA-2-7B, reverses the gradient entirely, aligning best with Chinese brains and worst with English. Beyond training dominance, formal typological distance independently covaries with alignment degradation, syntax-associated brain regions (IFG) show $2.3\times$ steeper typological gradients than lexico-semantic regions (PTL), and tokenization fertility accounts for $\sim$60% of a cross-linguistic shift in optimal encoding layer. These results reveal that the apparent "English advantage" in brain-LLM alignment is an artifact of training data composition, while the remaining variation reflects genuine typological structure concentrated in syntactic processing.

Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models (LLMs), yet its benefits have not fully translated to multilingual contexts. Existing methods struggle with a fundamental trade-off: prioritizing input-language consistency severely hampers reasoning quality, while prioritizing reasoning often leads to unintended language drift toward English. We address this challenge with LANG, a novel framework that leverages language-conditioned hints to guide exploration in non-English reasoning tasks. Our method incorporates two key mechanisms to prevent dependency on these hints: a progressive decay schedule that gradually withdraws scaffolding, and a language-adaptive switch that tailors learning horizons to specific language difficulties. Empirical results on challenging multilingual mathematical benchmarks reveal that LANG substantially enhances reasoning performance without compromising language consistency. Moreover, we show that our framework generalizes beyond mathematics, fostering more consistent language alignment across model layers

In recent years social media has become an increasingly popular tool for communication. People use it to share their ideas, exchange information, and discuss thoughts. Given its prevalence and widespread reach, social media must remain a safe space for people. Content generated on social media can be abusive and it has become increasingly important to detect such content. In this paper, we use a language-based preprocessing and an ensemble of several models and analyze their performance of abusive comment detection. Through extensive experimentation, we propose a pipeline that minimizes the false-positive rate (marking non-abusive as abusive) so that these systems can detect abusive comments without undermining the freedom of expression.

In this study, we compare the performance of four text chunking approaches: Recursive, Khmer-Aware, Sentence-Based, and LLM-Based within a Retrieval-Augmented Generation (RAG) framework applied to Khmer agricultural documents. The document chunks are encoded using the BGE-M3 multilingual embedding model and retrieved using the FAISS library. Performance is evaluated using four metrics: Average Retrieval Score (L2 distance), Answer Relevance, Khmer Coverage, and Khmer Intersection over Union, all measured against ground-truth question-answer pairs. For evaluation, we perform 5-fold cross-validation over 18 question-answer pairs. We observe the best performance for the character-based Recursive chunking method with a chunk size of 300 characters, achieving the lowest L2 distance (0.4295 +- 0.0461), highest Answer Relevance (0.8663 +- 0.0199), and highest Khmer IoU (0.6441 +- 0.0347). A paired t-test shows a statistically significant improvement over the Sentence-Based chunking method in L2 distance (p = 0.0121). These results highlight the importance of segmentation granularity and structural preservation for optimizing dense retrieval in morphologically complex, low-resource languages such as Khmer.

Although Large Language Models (LLMs) demonstrate strong capabilities across various tasks, they exhibit significant performance discrepancies across languages. While prompting LLMs in English typically yields the highest general performance, it often induces a Western-centric bias, hindering the model's ability to accurately reflect diverse cultural knowledge. We hypothesize that LLMs already possess rich cultural knowledge embedded within local-language representations, but fail to retrieve it when prompted in English. To bridge this cross-lingual knowledge gap, we propose a novel self-supervised framework. Our method leverages multilingual self-consistency to identify the most reliable cultural responses across languages, combined with a self-critique mechanism to transfer this knowledge to the weaker language. Evaluations on the BLEnD benchmark demonstrate that our approach significantly improves cultural alignment-boosting performance on English queries by an average of 5.03%-relying entirely on self-generated data. Ultimately, our work demonstrates that latent cultural knowledge can be successfully surfaced and propagated across languages, enabling more culturally equitable and consistent LLMs.

When a multi-module LLM agent fails, the module most responsible for the failure is not necessarily the best place to intervene. We demonstrate this Diagnostic Paradox empirically: causal analysis consistently identifies the routing module -- which selects which tool to call next -- as the primary bottleneck across three independent agent families. Yet injecting prompt-level correction examples into this module consistently degrades performance, sometimes severely. Patching an upstream query-rewriting module instead reliably improves outcomes. The effect holds with statistical significance on two agent families and directional consistency on a third; alternative repair strategies at the routing module (instruction rewriting, model upgrade) are neutral, confirming that the harm is specific to correction-injection patching. We explain this asymmetry through the Linguistic Contract hypothesis: each downstream module implicitly adapts to its upstream's characteristic error distribution, so correcting the bottleneck breaks this implicit alignment in a way that upstream corrections do not. We operationalize this via a per-agent co-adaptation measure, derived from diagnosis alone, and show it is consistently associated with patching harm across agent families: higher co-adaptation co-occurs with harm, lower with safety. This trend holds across all three agent families, providing preliminary support for the hypothesis beyond a single-agent observation.

Low-resource languages face a critical challenge in AI development: creating specialized conversational systems without access to massive training corpora. We present a systematic methodology for transforming structured linguistic resources into specialized AI systems, demonstrating that expert-curated lexical databases can serve as effective foundations for conversational AI development. Our approach converts Hindi WordNet into 1.25 million diverse instruction-response pairs, fine-tunes a 12B-parameter language model using resource-efficient LoRA with 4-bit quantization. Evaluation through a Hindi language learning chatbot demonstrates that structured-knowledge-based systems achieve superior pedagogical effectiveness (91.0 vs. 79.4-83.6 for general-purpose models) while maintaining competitive semantic performance and exceptional consistency. The complete pipeline demonstrates a proof-of-concept methodology using Hindi for developing specialized AI systems for any languages with WordNet resources. This work addresses the critical gap in AI accessibility for low-resource languages, offering a practical alternative to corpus-intensive approaches and potentially enabling specialized AI development for the hundreds of languages with existing WordNet resources.

Agreement attraction errors, in which a verb erroneously agrees with an intervening noun rather than its grammatical head, are amplified by morphological syncretism in some languages (English, German, Russian) but not others (Turkish, Armenian), a cross-linguistic pattern without a principled account. We use surprisal and attention entropy from large language models as processing proxies to investigate this variation across four languages. LLM-derived measures replicate behavioral findings in English and German (syncretism modulates attraction), align with Turkish null results (no modulation), and partially capture Russian patterns. We discuss further directions for better understanding why syncretism affects agreement attraction differently across languages.

Driving Vision-Language-Action Models (Driving VLAs) commonly introduce natural-language reasoning as an intermediate interface for end-to-end planning, but reasoning-centric interfaces face three practical bottlenecks: obtaining high-quality reasoning annotations is difficult, generating and understanding long reasoning chains is challenging for compact models, and inference latency is substantially increased. In this paper, we rethink the design of language interfaces in Driving VLAs and show that concise one-step meta-actions are a simple yet effective alternative to verbose reasoning. Meta-actions provide semantic decision grounding while remaining low-entropy, and being automatically derivable from expert trajectories, enabling scalable supervision and reliable trajectory conditioning. Building on this interface, we propose DriveMA, which combines action-centric supervised training with a turn-level credit-assignment reinforcement learning framework that jointly optimizes meta-action correctness, trajectory quality, and trajectory--meta-action consistency. Experiments show that DriveMA already achieves a new state of the art on the Waymo End-to-End Driving Challenge with a 2B model, reaching a Rater Feedback Score (RFS) of 8.060, while its 4B version further improves the state of the art to 8.079; DriveMA also obtains competitive performance on NAVSIM. Ablations demonstrate that one-step meta-actions offer a better practical trade-off between expressiveness, predictability, and inference efficiency than natural-language reasoning or finer-grained action sequences. Code, data, and models will be released to facilitate future research.

Large language models (LLMs) are increasingly used for writing assistance in small contact languages, yet it is unclear whether they respect community norms around lexical borrowing and neology. We introduce LexNeo-Bench, a 3{,}050-instance token-level benchmark derived from LuxBorrow, a large-scale Luxembourgish news corpus, where target tokens are labelled as native or as French, German, or English borrowings. Using this benchmark, we probe three multilingual LLMs across 34 prompt settings on two tasks: borrowing type classification and a binary lexical-innovation proxy (borrowing versus native). Without external context, models perform only slightly above chance on borrowing classification, so we construct a linguistic knowledge graph that encodes donor language, morphological patterns, and lexical analogues, and inject instance-specific subgraphs into the prompt. Knowledge-graph prompts raise borrowing classification accuracy from 25 -- 35% up to 71 -- 81% and largely close the gap between small and large models, while leaving neology detection difficult and sensitive to few-shot design. Our results show that lexicon-aware prompting is highly beneficial for robust borrowing judgments in low-resource contact languages and that lexical resources can serve as structured context for LLM evaluation. This study was carried out within the ENEOLI COST Action and examines borrowing as a form of lexical innovation in multilingual Luxembourgish data.

The thinking-while-speaking paradigm aims to make AI communication more human. A key challenge is maintaining fluent speech while performing deep reasoning. Our method, InterRS, tackles this by inserting reasoning steps only during natural speech generation. This requires high-quality data where reasoning and speech are precisely aligned, and the length ratio are under controlled. We introduce a novel pipeline to generate such seamlessly interleaved audio data. To train our model, we combine interleaved SFT with refined data and reinforcement learning with two new rewards: a TA-Balance Reward to manage timing and thinking-answer ratio, and a Linguistic Quality Reward to refine expression. Experiments show our approach achieves 13% better performance on mathmatical and logic benchmarks while generating instant response like a spoken-language instruct model which outputs fast CoT response. Furthermore, our method generates more natural and fluent answers than prior methods.

The increasing volume of scientific research necessitates effective communication across language barriers. Machine translation (MT) offers a promising solution for accessing international publications. However, the scientific domain presents unique challenges due to its specialized vocabulary and complex sentence structures. In this paper, we present the development of a collection of parallel and monolingual corpora for the scientific domain. The corpora target the language pairs Spanish-English, French-English, and Portuguese-English. For each language pair, we create a large general scientific corpus as well as four smaller corpora focused on the domains of: Cancer Research, Energy Research, Neuroscience, and Transportation research. To evaluate the quality of these corpora, we utilize them for fine-tuning general-purpose neural machine translation (NMT) systems. We provide details regarding the corpus creation process, the fine-tuning strategies employed, and we conclude with the evaluation results.

This paper reflects on twenty years of building NLP resources and research infrastructure for Arabic, a language spoken by hundreds of millions yet historically underserved relative to languages such as English or Chinese. The first decade focused on foundational linguistic infrastructure; the second shifted toward computational social science, social media analysis, and socially oriented applications. Rather than cataloguing outputs, the paper examines what the experience of building them revealed. Three counterintuitive lessons emerge: building datasets is as much a social process as a technical one; communities formed around shared tasks often matter more than the tasks themselves; and moving from language resources to computational social science exposes challenges that traditional NLP training does not address. We discuss three failures: a depression detection corpus that never reached clinical practice, a period of spreading across too many shared tasks without sufficient depth, and a long-standing assumption that Modern Standard Arabic infrastructure would transfer cleanly to dialectal tasks. These experiences suggest that the hardest problems in developing NLP for underserved communities are not linguistic but social, institutional, and epistemic, and require competencies the field rarely teaches.

Advancements at the intersection of computer vision and natural language processing are crucial for applications like assistive tech, multimedia querying, and robotics. This dissertation proposes novel architectures to improve intelligent agents across three key vision-language tasks: image captioning, visual dialog, and interactive instruction following. First, we address limitations in visual representation for image captioning. Traditional models rely on region-based features from CNN detectors, which lack global context and suffer from high computational overhead. We propose GRIT (Grid and Region-based Image captioning Transformer), a transformer-only architecture. By integrating grid and region features using a DETR-based detector, GRIT enables end-to-end training and out-performs prior methods in both inference accuracy and speed. Second, we tackle visual dialog, which requires multi-turn conversation about an image. The challenge lies in efficiently modeling interactions between multiple inputs (image, question, history). We introduce LTMI (Light-weight Transformer for Many Inputs). Utilizing a specialized attention block, an LTMI layer matches the representational power of a standard Transformer extension while utilizing less than one-tenth of its parameters, as validated on the VisDial dataset. Finally, we study interactive instruction-following for embodied AI using the ALFRED dataset. We propose a framework featuring a two-stage instruction interpretation: it first decodes language directives independently of visual context to predict a tentative action-object sequence, which is then fused with visual features for final execution. Using multiple egocentric views and hierarchical attention, our method accurately localizes objects and achieves a state-of-the-art unseen success rate of 8.37%.

We present the University of Florida Gators submission to the AmericasNLP 2026 shared task on cultural image captioning for Indigenous languages. Our two-stage pipeline generates a Spanish intermediate caption with Qwen2.5-VL, then produces the target-language caption using retrieval-augmented many-shot prompting with Gemini 2.5 Flash. We achieve 164.1%, 131.7%, and 122.6% improvements over the shared task baseline for Bribri, Guaraní, and Orizaba Nahuatl captioning, respectively, in our dev set evaluation and maintain >150% improvements for the Bribri and Orizaba Nahuatl languages in the test set evaluation. We find retrieval is highly language-dependent, beneficial only for large, in-domain corpora, and that synthetic data augmentation accounts for around 28 chrF++ of the dev set Guaraní performance gain. Our submission is the overall winner of the shared task, placing second out of five finalist submissions in human evaluations of target-language captions.

In what ways might statistical signals in linguistic input assist with the acquisition of syntax? Here we hypothesize a mechanism called collocational bootstrapping, in which regularities in word co-occurrence patterns can provide cues to syntactic dependencies. We investigate whether this mechanism can support the acquisition of English subject-verb agreement. First, we simulate language acquisition by training neural networks on synthetic datasets that vary in how predictable their subject-verb pairings are. We find that there is a range of variability levels at which these statistical learners robustly learn subject-verb agreement. We then analyze the variability of subject-verb pairings in child-directed language, and we find that the variability in such data falls within the range that supported robust generalization in our computational simulations. Taken together, these results suggest that collocational bootstrapping is a viable learning strategy for the type of input that children receive.

CHILDES is a paramount resource for language acquisition studies -- yet computational tools for analyzing its syntactic structure remain limited. Leveraging the recent release of the UD-English-CHILDES treebank with gold-standard Universal Dependencies (UD) annotations, we train a state-of-the-art dependency parser specifically tailored to CHILDES. The parser more accurately captures syntactic patterns in child-adult interactions, outperforming widely used off-the-shelf English parsers, including SpaCy and Stanza. Alongside the parser, we also release a Part-of-Speech tagger and an utterance-level construction tagger, which together form the open-source Syntactic Parsing Toolkit for Child-Adult InTeractions (CAIT). Through a detailed error analysis and a case study tracking the distribution of syntactic constructions across developmental time in CHILDES, we demonstrate the practical utility of the toolkit for large-scale, reproducible research on language acquisition.

Automatic speech recognition (ASR) has improved substantially in recent years, yet performance remains limited for low-resource languages. Large language models (LLMs) have shown promise for improving ASR through generative error correction (GER), but their effectiveness in low-resource settings remains underexplored. In addition, it remains unclear to what extent data contamination influences the reported improvements in LLM-based GER. This study investigates LLM-based GER for low-resource Frisian. In addition to a public corpus, we construct and use a Frisian offline dataset with non-public texts for evaluation to control for potential data contamination. Results show that GER improves ASR performance in most settings, with the best GPT-5.1 results surpassing oracle WERs. Comparable gains on the offline dataset indicate that improvements reflect true correction ability. We further provide a detailed error analysis revealing model correction patterns.

The article observes data analysis of 286 multi-word expressions (MWEs) based on 16 lexical, grammatical and other criteria described in theoretical books and papers on the notion of idiomaticity. MWEs were collected from the same theoretical sources, and a set of experts in linguistics annotated them with these categories. The distribution of categories shows that there are no absolutely idiomatic expressions. Lexical criteria seem to be the most influential; grammatical criteria are bound to certain conditions; presence of obsolete words and grammar influence ability of an MWE to be replaced with one word.

Linguistic cues such as "I believe" and "probably" offer an intuitive interface for communicating confidence, yet a generalisable, principled calibration framework for linguistic confidence expressions remains underexplored. In particular, co-occurring linguistic cues, contextual variation, and subjective audience interpretation pose unique challenges. We therefore model linguistic confidence as a distribution over plausible perceived probability values that a statement is correct, capturing interpretation variability that scalar representations discard. Within this distributional framework, we introduce faithfulness as a complementary evaluation dimension and present Faithfulness Divergence (FD), an information-theoretic metric quantifying the surprise induced in audience beliefs upon truth revelation. Building on these foundations, we present Retrieval-Augmented Linguistic Calibration (RALC), a lightweight post-hoc pipeline that propagates calibrated confidence signals back into natural language via retrieval-augmented rewriting. Across three QA benchmarks and five LLM families, RALC improves in-domain faithfulness and calibration up to 66% and 58%, respectively, outperforming black-box and grey-box calibration baselines.

The rapid emergence of AI technologies is reshaping translation practices and theory across the board. This paper deals with the impact of AI in language access. This area is characterized by the need to serve broad and diverse user populations, within a context where efficiency and access are shaped by legal mandates, ethical and commercial tensions, and safety concerns. This paper reports on the attitudes and perceptions of language access managers towards the AI and the human value in the AI age. Methodologically, this paper presents an analysis of a subset of a broader study on language access and technology, specifically a qualitative thematic analysis of ten semi-structured interviews with language access managers in the USA working in healthcare, court, public service and local government contexts. The results indicate that language access managers show conditional optimism towards the inevitable AI implementations, are strongly risk aware, and deeply committed to the human value and human oversight of AI implementations and output.

Large language models (LLMs) are increasingly explored for clinical decision support, yet most evaluations are conducted in English, leaving their reliability in other languages uncertain. Here we evaluate the impact of prompting language on diagnostic reasoning and final diagnosis accuracy by comparing English and French performance across five LLMs (o3, DeepSeek-R1, GPT-4-Turbo, Llama-3.1-405B-Instruct, and BioMistral-7B). A total of 180 clinical vignettes covering 16 medical specialties were assessed by two physicians using an 18-point scale evaluating both diagnosis accuracy and reasoning quality. Four of the five models performed better in English (mean difference 0.37-0.91, adjusted p < 0.05), with the gap spanning multiple aspects of reasoning, including differential diagnosis, logical structure, and internal validity. o3 was the only model showing no overall language effect. These findings demonstrate that prompting language remains a critical determinant of LLM clinical performance, with implications for equitable linguistico-cultural deployment worldwide.

Grounded multi-video question answering over real-world news events requires systems to surface query-relevant evidence across heterogeneous video archives while attributing every claim to its supporting source. We introduce CRAFT (Critic-Refined Adaptive Key-Frame Targeting), a query-conditioned pipeline that combines dynamic keyframe selection, per-video ASR with multilingual fallback, and a hybrid critic loop to iteratively verify and repair claims before consolidation. The pipeline integrates UNLI temporal entailment, DeBERTa-v3 cross-claim screening, and a Llama-3.2-3B adjudicator, with a final citation-merging stage that emits each fact once with all supporting source identifiers. On MAGMaR 2026, CRAFT achieves the best overall average (0.739), reference recall (0.810), and citation F1 (0.635). We further evaluate on a MAGMaR-style conversion of WikiVideo with 52 non-overlapping event queries, where CRAFT also performs strongly (0.823 Avg), showing that its claim-centric evidence aggregation generalizes beyond MAGMaR. Ablations show that atomic claims, ASR, and the critic loop drive the main gains over the vanilla query-conditioned baseline. Code and implementation details are publicly available at https://github.com/bhosalems/CRAFT.

Code-switching -- the natural alternation between two languages within a single utterance -- remains one of the most challenging and under-studied conditions for automatic speech recognition (ASR). We present a benchmark evaluating five commercial ASR providers across four language pairs: Egyptian Arabic--English, Saudi Arabic (Najdi/Hijazi)--English, Persian (Farsi)--English, and German--English, comprising 300 samples per pair selected by a two-stage pipeline combining heuristic filtering with a GPT-4o and Gemini 1.5 Pro ensemble scorer, reducing LLM costs by $\approx$91%. We evaluate on both WER and BERTScore, showing that while both metrics agree on the ordinal ranking of systems for all Arabic and Persian pairs ($τ= 1.0$), WER inflates the magnitude of quality gaps by approximately 3$\times$ by penalising semantically correct transliteration choices. ElevenLabs Scribe v2 achieves the lowest WER (13.2% overall) and leads on BERTScore (0.936 overall). Difficulty-stratified analysis reveals performance gaps masked by aggregate averages, and BERT embedding projections confirm semantic proximity between reference and hypothesis despite surface-level script differences. The dataset is publicly available at https://huggingface.co/datasets/Perle-ai/ASR_Code_Switch.

Over the past decade, low-resource natural language processing (NLP) has experienced explosive growth, propelled by cross-lingual transfer, massively multilingual models, and the rapid proliferation of benchmarks. Yet this apparent progress masks a critical, insufficiently examined tension: the deep sociolinguistic expertise required to evaluate increasingly complex generative systems is severely strained, inequitably distributed, and structurally marginalised. We present a critical narrative survey of low-resource NLP evaluation (2014-present), tracing its evolution across three phases: early heuristic optimism, the illusions of top-down benchmark scaling, and the current era of generative bottlenecks. We conceptualise the Annotation Scarcity Paradox, the structural friction arising when the technical capacity to scale models vastly outpaces the sovereign human infrastructure required to authentically evaluate them. By examining extractive data pipelines, undercompensated ``ghost work'', and language data flaring, we argue that this paradox threatens the epistemic validity of reported progress. We survey emerging responses -- including data augmentation, model-based evaluation, participatory curation, and annotation-efficient approaches via item response theory and active learning -- and assess their equity and validity trade-offs. We close with a practitioner call to action, arguing that overcoming this bottleneck requires a paradigm shift from transactional data extraction to relational, community-embedded evaluation rooted in epistemic governance, data sovereignty, and shared ownership.

A key question in psycholinguistics is how inferences about the meaning of linguistic input unfold incrementally a comprehender's mind. In this work, we study reading dynamics for ``noisy-channel garden-path'' sentences, which temporarily appear well-formed but feature late-appearing violations of expectation that can be resolved not by inferring an alternative syntactic structure, but by inferring the presence of an error. We find evidence for targeted regressions -- eye movements towards regions that are promising loci of possible errors in light of later-arriving information, showing patterns consistent with the posterior inferences of a model of noisy-channel processing with reanalysis. We discuss the implications of these findings for theories of noisy-channel language comprehension and information-theoretic explanations of reading dynamics.

Large Language Models (LLMs) remain vulnerable to jailbreak attempts that circumvent safety guardrails. We investigate whether multi-turn conversations using low-resource African languages (Afrikaans, Kiswahili, isiXhosa, and isiZulu) can bypass safety mechanisms across commercial LLMs. We translated prompts from existing datasets and evaluated ChatGPT, Claude, DeepSeek, Gemini, and Grok through automated testing and human red-teaming with native speakers. Single-turn translation attacks proved ineffective, while multi-turn conversations achieved English harmful response rates from 52.7% (Claude 3.5 Haiku) to 83.6% (GPT-4o-mini), Afrikaans from 60.0% (Claude 3.5 Haiku) to 78.2% (GPT-4o-mini), and Kiswahili from 41.8% (Claude 3.5 Haiku) to 70.9% (DeepSeek). Human red-teaming increased jailbreak rates compared to automated methods. Over all evaluated languages, the average jailbreak rate increased from 59.8% to 75.8%, with improvements of +20.0% (Afrikaans), +12.7% (isiZulu), +12.3% (isiXhosa), and +1% (Kiswahili), demonstrating that poor translation quality limits jailbreak success. These findings suggest that vulnerabilities in LLMs persist in multilingual contexts and that translation quality is the critical factor determining jailbreak success in low-resource languages.

Somali is a Cushitic language of the Horn of Africa with ~25 million speakers, yet no documented dedicated Somali pretraining corpus with a companion tokenizer and language-identification benchmark has been publicly released. Existing Somali text appears either inside multilingual distributions (HPLT v2, CC100, MADLAD-400, OSCAR, mC4) or in small, undocumented Somali-only uploads on Hugging Face. We introduce SomaliWeb v1, a quality-filtered Somali corpus of 819,322 documents (~303M tokens) built from three upstream sources (HPLT v2, CC100, Somali Wikipedia) through a six-stage reproducible pipeline. We release (i) the corpus, (ii) a matched BPE-16K tokenizer, and (iii) the first public side-by-side Somali benchmark of three production language identifiers. Our measurements reveal concrete quality defects in existing distributions: HPLT v2's "cleaned" Somali release retains 17.3% byte-exact duplicates, 56.1% of its documents contain fixable mojibake, and 10.7% of its byte-unique documents are near-duplicates at Jaccard tau=0.80. Our BPE-16K tokenizer emits 40.2% fewer tokens than GPT-4's cl100k_base on FLORES-200 Somali devtest as a tokenizer-level measurement; downstream language-model perplexity comparisons are deferred to a follow-up release.

Recent advancements in Large Language Models (LLMs) and Large Vision Language Models (LVLMs) have enabled general-purpose systems to demonstrate promising capabilities in complex reasoning tasks, including those in the medical domain. Medical Visual Question Answering (MedVQA) has particularly benefited from these developments. However, despite Bangla being one of the most widely spoken languages globally, there exists no established MedVQA benchmark for it. To address this gap, we introduce BanglaMedVQA, a dataset comprising clinically validated image-question-answer pairs, along with a comprehensive evaluation of current foundation models on this resource. Consistent with prior findings that report low performance of current models on English MedVQA benchmarks, our analysis reveals that Bangla performance is substantially lower, reflecting the challenges inherent to low-resource languages. Even top-performing models such as Gemini and GPT-4.1 mini fail to accurately answer specialized diagnostic questions, indicating severe limitations in fine-grained medical reasoning. Although certain open-source models, such as Gemma-3, occasionally outperform these models in general categories, they too struggle with clinically complex questions, underscoring the urgent need for top-notch evaluation method.

Expanding Large Language Models~(LLMs) to new languages is a costly endeavor, demanding extensive Continued Pre-Training~(CPT) and data-intensive alignment. While recent data-free merging techniques attempt to bypass alignment by fusing a multilingual CPT-enhanced model with its instruct counterpart, they are plagued by a critical trade-off: mitigating parameter conflicts to preserve original abilities inevitably dilutes new language acquisition, and vice-versa. To resolve this conflict, we introduce \method, which upcycles a dense model into a Mixture-of-Experts~(MoE) architecture, allocating different experts to different languages. Alignment ability is then transferred by grafting a MoE-expanded parameter delta~($Δ_{\text{post}}$) to the CPT-enhanced base model, bypassing the complex alignment phase. Experiments demonstrate \method's superiority even against baselines with similar FLOPs or number of parameters; it improves performance on expanded languages while effectively preserving original capabilities. We further show our approach is highly applicable across different models and Post-training deltas.

Power differences shape human communication through well documented socio cognitive effects, including language coordination, pronoun usage, authority bias, and harmful compliance. We examine whether large language models (LLMs) exhibit similar behaviors when assigned high or low status personas. Using personas from diverse professions, we simulate multi turn, power asymmetric dialogues (e.g., principal teacher, justice lawyer) and measure (i) language coordination, (ii) pronoun usage, (iii) persuasion success, and (iv) compliance with unsafe requests. Our results show that LLMs show key socio-cognitive effects of power, albeit with nuances and variability, linking simulated interactions to both desirable and unsafe behaviors.

Mixture-of-Experts (MoE) architectures enable efficient model scaling, yet expert routing behavior across underrepresented languages remains poorly understood. We analyze routing dynamics in two architecturally distinct MoE models -- a pure Transformer (Qwen3-30B-A3B) and a hybrid Mamba-Transformer (Nemotron-3-Nano-30B-A3B) -- using Hebrew as a morphologically rich, low-resource testbed. Both pre-trained models exhibit \emph{deep-layer routing collapse}: usage entropy drops sharply in final layers and tokens concentrate on a narrow expert subset, a pattern largely absent for English. Continual pre-training (CPT) on balanced bilingual data substantially corrects this imbalance, increasing entropy and shifting routing toward shared, language-agnostic experts; supervised fine-tuning (SFT) alone achieves less complete correction. Extending the analysis to Japanese reveals quantitatively consistent collapse signatures, providing cross-linguistic evidence that the phenomenon is a systematic consequence of pre-training underrepresentation rather than any language-intrinsic property. Routing improvements correlate with consistent downstream benchmark gains, positioning routing entropy and expert specialization as principled diagnostics for multilingual capacity in MoE systems.

Multilingual NLP often relies on dataset counts from centralized catalogues to characterize which languages are resource-rich or resource-poor. However, these catalogues record only one layer of dataset visibility: what has been registered or institutionally distributed. They do not necessarily reflect which datasets are created, cited, or reused in the research literature. To examine this gap, we combine a catalogue-based baseline with literature-backed evidence of dataset circulation. We introduce the Resource Density Index (RDI), defined as the number of catalogued datasets per one million speakers, and compute it for the 200 most widely spoken languages in Ethnologue. Among them, 118 languages (59%) have an average RDI of zero across the LRE Map and the Linguistic Data Consortium (LDC), and another 23 fall below 0.1, corresponding to at most one catalogued dataset per ten million speakers. We then apply an LLM-assisted citation-mining pipeline over the Semantic Scholar corpus to these 141 low-visibility languages. After manual validation and consolidation, we identify 609 unique datasets across 53 languages, of which 356 remain openly accessible through working public links. These results reveal a substantial visibility gap: many large-speaker languages appear data-poor in catalogue records yet show clear evidence of dataset activity in the research literature. Our findings suggest that multilingual data scarcity should be understood not only as a production problem, but also as a question of documentation, discoverability, and long-term accessibility. Code and data are publicly available at (https://github.com/zhiyintan/dataset-visibility-asymmetry).

As a modern commodity, language has become a vast repository of socially and psychologically significant traits and concepts, reflecting the ways people encode pattern of thoughts, behaviors, and emotions into words. Text-based Automatic Personality Prediction (APP), seeks to infer personality from linguistic behavior, offering a scalable alternative to traditional psychometric assessments. Although text is inherently hierarchical, with the document-level capturing global features, the sentence-level encoding local semantics, and the word-level providing fine-grained lexical information, most existing approaches rely on shallow, sequential, or single-level representations that ignore the multi-level structure of written language. To address this, we propose HyperPersona, a framework that explicitly models the hierarchical organization of text (document, sentence, and word) through hypergraph structure, where a document and its sentences are represented as hyperedges, and the words are represented as nodes, enabling joint modeling of global, local, and lexical dependencies of text. Followed by a transformer-based graph encoder that learns interactions within and across these linguistic layers, yielding context-sensitive and structurally grounded feature representations for personality prediction. Experiments on the Big Five personality dimensions show that, while relying solely on text, HyperPersona effectively integrates multi-level linguistic cues, achieving superior performance compared to state-of-the-art baselines. These findings underscore the critical role of textual hierarchy in advancing human-like personality inference from natural language.

Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as clinical decision support and medical documentation. However, the robustness of these models against subtle linguistic variations, specifically stigmatizing language (SL) commonly found in human-authored clinical notes, remains critically under-explored. In this work, we investigate whether frontier LLMs inherit and propagate this human bias when processing clinical text. We systematically evaluate nine frontier LLMs across four stigmatized medical conditions, utilizing clinical vignettes injected with varying intensities and phenotypes of SL (doubt, blame, and maligning). Our results demonstrate that all evaluated models exhibit substantial bias, with clinical decision-making significantly skewed towards less aggressive patient management. Notably, we observe a high sensitivity to linguistic framing, where a single SL sentence is sufficient to alter model outputs, revealing a clear dose-response relationship. Furthermore, we evaluate standard prompt-based mitigation strategies, including Chain-of-Thought (CoT) reasoning and model self-debiasing. These approaches show limited efficacy; models struggle to explicitly identify SL while remaining implicitly influenced by it. Our findings expose a critical vulnerability in current LLMs regarding fairness and robustness in clinical NLP, underscoring the need for rigorous algorithmic guardrails to prevent the automation of health disparities.

Linguistic annotation of transcribed speech is essential for research in language acquisition, language disorders, and sociolinguistics, yet remains labor-intensive and time-consuming. While Large Language Models (LLMs) have shown promise in automating annotation tasks, their ability to handle complex discourse-level annotation in non-English languages remains understudied. This study evaluates whether LLMs can reliably annotate narrative macrostructure-the hierarchical organization of story grammar elements-in spoken Mandarin, using the Multilingual Assessment Instrument for Narratives (MAIN) as a testbed. We compared four LLMs against trained human annotators on narratives produced by children, young adults, and older adults. The best-performing model achieved agreement with human raters (k=.794) approaching human-human reliability levels (k=.872) while reducing annotation time by 65%, whereas the locally deployable lightweight model performed substantially worse. Annotation difficulty varied systematically by macrostructure element type, with categories requiring subtle semantic differentiation posing persistent challenges. Furthermore, model reliability decreased on young adult narratives, which exhibited greater lexical variation, semantic ambiguity, and multi-element integration within single utterances. These findings suggest that LLMs can effectively support discourse-level annotation in non-English spoken corpora, while highlighting the continued need for human oversight in semantically complex tasks. Our prompt templates are open sourced for future use.

Multimodal LLMs are evolving from vision-language to tri-modality that see, hear, and read, yet pipelines and benchmarks remain English-centric and compute-heavy. The tutorial offers an overview of this emerging research area for multilingual multimodality across text, speech, and vision under limited data/compute budgets, synthesizing foundations, recent multilingual models (PALO, Maya), speech-text LLMs. We cover low-cost data creation/curation; adapter stacks for tri-modal alignment; culture-aware evaluation beyond English and hands on resources for fine-tuning a compact multilingual VLM and wiring a speech->text->LLM pipeline. The content will be delivered as an interactive half-day tutorial, designed for researchers and practitioners working on multilingual, multimodal AI in low-resource language settings.

Standard PII filters often miss contextual data leakage in RAG systems, such as non-regulated attribute clusters that collectively identify individuals. We introduce a Privacy Policy Enforcement (PPE) framework using dual one-class density estimators with fused text embeddings and a calibrated abstain region for out-of-distribution inputs. Using an axis-stratified, multi-LLM synthetic data pipeline across medicine, finance, and law, we found that traditional Gaussian Mixture baselines fail on borderline-safe stress tests by focusing on linguistic register rather than content. Our proposed T3+OCSVM detector, trained on safe and borderline-safe data, achieves a borderline AUROC of 0.93+ while reducing false positives by 44-55 percentage points and maintaining millisecond latency. Compared to supervised MLP classifiers or 14B-parameter LLM judges, our framework offers superior operational suitability, as the former suffers from high abstention rates and the latter from latency and calibration issues. This methodology provides a robust stress-testing standard for any synthetic-data-trained classifier.

Algorithmic feeds have become primary environments for encountering information online, yet while they shape what people see, less is known about how sustained feed exposure shapes how people write. Drawing on Cultivation Theory, we examine whether algorithmic feeds function as online environments that leave measurable traces in users' language. We leverage a large-scale longitudinal dataset of 235M posts by 4M users on Bluesky, and conduct a quasi-experimental study matching an initial pool of 368,513 users exposed to one of three feeds -- News, Science, and Blacksky -- with a pool of 2,001,915 active control users who did not engage with any of these feeds. We examine linguistic evolution across three dimensions: lexico-semantics, psycholinguistics, and topics. We find that users exposed to these feeds show significantly greater stylistic accommodation, semantic alignment, and register formalization than matched controls. These effects vary markedly by feed identity -- Blacksky produces the deepest psycholinguistic restructuring, with significant shifts in cognitive processing, affective expression, and pronoun use, while News and Science effects are largely confined to register and topical focus. Regression models reveal that reposting is the most consistent predictor of linguistic convergence across all feeds, whereas posting and bookmarking show feed-dependent effects, with effects differing more than fourfold across feeds. Our work extends Cultivation Theory beyond belief formation to linguistic behavior, demonstrating that feeds function as persistent linguistic environments that gradually shape what and how users write online. Our work has implications for studying algorithmic influence, online identity formation, and the design and governance of feed-based platforms that mediate online interactions.

Digital humanities projects increasingly rely on machine translation and large language models to widen access to classical, religious, and otherwise under-translated textual traditions. Yet standard translation benchmarks are poorly suited to such materials: they typically compare a system output against a single reference translation, even though classical texts often support multiple faithful renderings that differ in terminology, register, and interpretation. This article introduces PaliBench, both a benchmark for Pali-to-English translation and a reusable method for constructing multi-reference translation benchmarks for classical languages. The Pali case study draws on passages from the Sutta Pitaka aligned with independent English translations by Bhikkhu Sujato, Bhikkhu Thanissaro, and Bhikkhu Bodhi. The workflow combines LLM-assisted alignment of independently segmented translations, automated verification against source files, passage-level quality filtering, deduplication of formulaic repetitions, and multi-metric evaluation against multiple human references. The resulting benchmark contains 1,700 passages spanning 8,389 segments and approximately 345,000 tokens. We use it to evaluate ten contemporary large language models with complementary metrics, finding strong cross-metric concordance in system rankings alongside substantial variation in reliability and semantic outlier rates. The broader contribution is methodological: PaliBench shows how existing scholarly translations can be transformed into evaluation infrastructure for interpretive textual traditions without treating any single translation as definitive. Although developed for Pali Buddhist texts, the approach could be portable to other classical corpora where sufficient independent reference translations exist.

Manner and result verbs encode different aspects of event structure and have been discussed in developmental work as a potentially informative distinction for studying early verb learning. However, this distinction remains difficult to measure at scale because large annotated resources for manner and result classification are not currently available. We present a computational approach for identifying manner and result verbs in sentence context. Using linguistically informed prompts, we generate sentence-level annotations with large language models over data drawn from MASC and InterCorp, extending coverage from previously annotated portions of VerbNet to 436 classes. We then train a RoBERTa-based classifier on these annotations and evaluate it on three held-out gold-standard datasets, including previously annotated items and a new expert-annotated set. Across these evaluations, the model shows promising performance, with average accuracy up to 89.6%. We present this work as a scalable measurement tool that can support future research on verb semantics in developmental and other language datasets, while noting that further validation is needed for borderline cases, mixed manner/result verbs, and downstream developmental applications.

Aphasias, selective language impairments which can arise from brain damage, reveal the functional organization of human language by providing causal links between affected brain regions and specific symptom profiles. Drawing on this literature, we introduce an aphasia-inspired technique to characterize the emergent functional organization of language models (LMs). We ``lesion'' (zero-out) model parameters and measure the effects of this intervention against clinical aphasia symptoms, as diagnosed by the Text Aphasia Battery (TAB). When applied to 112,426 outputs from five 1B-scale LMs, the full range of evaluated symptoms surface, but in distributions largely distinct from those of humans. Our method uncovers broad symptom-profile differences between attention components (query, key, value, output) and feed-forward components (up, gate, down), with weaker evidence for differences among components within the same mechanism. We also find an effect of depth, where lesions in early layers disproportionately cause syntactic and semantic symptoms while late-middle layers yield higher rates of phonological and fluency deficits. Although some LM lesions induce quantitatively more similar profiles to some human aphasia types than others, qualitative differences in symptom patterns between LMs and humans suggest that aphasia syndromes are heavily influenced by the details of learning and processing rather than being a domain-invariant consequence of disrupted language processing.

Production machine translation relies overwhelmingly on encoder-decoder Seq2Seq models, yet reinforcement learning approaches to MT fine-tuning have largely targeted decoder-only LLMs at $\geq$7B parameters, with limited systematic study of encoder-decoder architectures. We apply Group Relative Policy Optimization to NLLB-200 (600M and 1.3B) using a hybrid reference-free reward (LaBSE and COMET-Kiwi) that requires no parallel data at fine-tuning time, evaluating across 13 typologically diverse languages. GRPO yields consistent improvements on all 13 languages, up to $+$5.03 chrF++ for Traditional Chinese, and, without any target-language data, competes with 3-epoch supervised fine-tuning on morphologically complex languages . We identify a consistent empirical pattern in which gains are largest where baseline performance is weakest and reward discriminability is highest, making this approach most effective precisely where parallel data is scarcest, and replicate this pattern across English and Spanish source languages.

This paper introduces a dataset of interlinked multimodal political communications from the Russian government, addressing persistent deficiencies in the availability of social text- and image-based data for authoritarian politics contexts. The dataset comprises two large corpora of official speeches delivered by senior actors within the Kremlin and the Russian Ministry of Foreign Affairs over multiple decades. For each speech, we provide Russian- and English-language texts, associated images and captions where available, and harmonized metadata including (e.g.) dates, speakers, (geo)locations, and official government content tags. Unique identifiers link images to speeches and align Russian and English versions of the same communication texts. We further augment these linked datasets with validated topical annotations for both speech texts and speech images, which are generated via transformer-based multimodal topic modeling and refined by a Russian politics expert. The resulting data resources support multimodal, multilingual, temporal, and/or spatial analyses of (authoritarian) political communication and offer a valuable testbed for social science research and large language model (LLM) applications in political domains.

Through an analysis of sequences generated by open-weight large language models (LLMs), we demonstrate that LLMs are heavily biased toward English. While continual pre-training is commonly used to adapt LLMs to a target language, we show that it does not offer a cost advantage over training from scratch, even for improving cultural understanding in the target language. These findings suggest that dedicated per-language investment may become increasingly important for future LLM development, rather than relying primarily on the expansion of English-centric resources.