Search research

Cross-lingual sentence encoders enable scalable transfer across hundreds of languages, powering applications such as translation mining and zero-shot learning in low-resource settings. Although trained for sentence-level alignment, they are increasingly also applied to token-level tasks such as hallucination detection and sequence tagging, exposing a mismatch between training and usage. We propose SALT, a lightweight post-training method that improves token representations by injecting span-level supervision into existing sentence encoders. Across five multilingual token-level benchmarks, SALT achieves the best overall results on four of them, outperforming alternative fine-tuning strategies and competitive encoders. It also improves sentence-level performance on cross-lingual retrieval and classification tasks. These results demonstrate that span-level supervision is an effective signal for improving both token and sentence representations.

Language model classifiers with explanations are used for moderation, routing, topic triage, and low-resource annotation. We study black-box auditing when the defender has only clean calibration data without trigger information but can ask the classifier for a label plus a short rationale or quoted evidence. We introduce Groundedness Drift, a lightweight score measuring whether the answer summary remains grounded in the input. Across two 7B backbones, five datasets, and four common non-adaptive OpenBackdoor-style attack families, Groundedness Drift achieves higher AUROC and lower residual target ASR than every compared detector in all cases at a nominal 5% clean-FPR budget. We then evaluate Unsupported Groundedness, a multi-probe escalation for explanation-camouflage stress cases. Unsupported Groundedness improves signals but does not close the adaptive gap.

Spoken Question Answering (SQA) remains largely focused on high-resource languages and carefully recorded speech, limiting the reach of speech-LLM methods in low-resource settings. This paper investigates whether text-to-speech (TTS) can provide task-specific training data for Luxembourgish SQA without requiring a large human-recorded QA corpus. Starting from existing text-based QA resources, we translate questions into Luxembourgish, synthesize spoken questions with multiple TTS systems, and pair them with textual answers. We train a parameter-efficient SLAM-style architecture that connects a frozen Whisper encoder to frozen multilingual LLM backends through a learned projector and LoRA adapters. We compare MMS-TTS, Qwen3-TTS, and OmniVoice variants, including single-source corpora of about 48k questions and a 4TTS multi-source mix of approximately 230k questions. Evaluation on LLAMA-LB-Test with two real Luxembourgish speaker conditions shows that multi-source and voice-design-based synthetic training configurations yield the strongest SQA performance. The results also show that no-reference TTS quality scores do not monotonically predict downstream QA performance, indicating that synthetic speech must be evaluated as task-specific training data rather than only as natural-sounding audio.

The Tajik language, written in Cyrillic script, remains severely under-resourced in terms of publicly available natural language processing (NLP) toolkits, hindering both linguistic research and applied development. This paper introduces TajikNLP, an open-source Python library that provides the first comprehensive pipeline for processing authentic Tajik text while preserving the original Cyrillic orthography. The library implements a modular architecture centered around a unified Doc object, enabling sequential application of components for cleaning, normalization, tokenization (including subword BPE), morphemic segmentation, part-of-speech tagging, stemming, lemmatization, and sentence splitting. A novel unified morphology engine is introduced, offering controlled and deep analysis modes that significantly improve handling of Tajik's agglutinative nominal and verbal inflections. The release further incorporates a lexicon-based sentiment analyser and pre-trained Word2Vec/FastText embeddings loaded directly from the Hugging Face Hub. To ensure reproducibility and facilitate future research, four accompanying linguistic datasets -- a POS-tagged corpus (52.5k entries), a sentiment lexicon (3.5k entries), a toponym gazetteer (5.6k entries), and a personal names dataset (3.8k entries) -- have been openly published under permissive licenses. The library's reliability is validated by an extensive test suite of 616 automated tests achieving 93% source code coverage. TajikNLP thus establishes a foundational technological infrastructure for Tajik language processing, lowering the barrier to entry for both academic and industrial applications in low-resource Cyrillic-script environments.

Mixture-of-Experts (MoE) models are widely used to scale language models, yet their expert routing behavior and adaptation in a multilingual setting remain underexplored. In this work, we study multilingual routing dynamics during continual pre-training of an English-centric MoE model on a multilingual corpus, analyzing how expert usage varies across languages. We find that continual multilingual pre-training leads to diffused, language-agnostic routing in early and middle layers, with language specialization primarily emerging in the final layers. We also show that token-level vocabulary overlap between languages plays an important role in how languages are routed. Motivated by these findings, we propose a parameter-efficient adaptation strategy that updates language-specific and shared experts in the final MoE layers. Experiments on MultiBLiMP and Belebele show that our method achieves a strong performance-efficiency trade-off, attaining competitive performance relative to fine-tuning complete final layers, while updating less than 2% of the parameters. Overall, our findings provide insights into where and how language specialization emerges in MoEs during continual pre-training and provide practical insights for low-resource multilingual adaptation. Our code is available at https://github.com/aditi184/moe-routing-adaptation.

Reinforcement Learning with Verifiable Reward (RLVR) has proven effective for training reasoning-oriented large language models, but existing methods largely assume high-resource settings with abundant training data. In low-resource scenarios, RLVR is prone to more severe entropy collapse, which substantially limits exploration and degrades reasoning performance. To address this issue, we propose Hybrid-domain Entropy dynamics ALignment (HEAL), a framework tailored for few-shot RLVR. HEAL first selectively incorporates high-value general-domain data to promote more diverse exploration. Then, we introduce Entropy Dynamics Alignment (EDA), a reward mechanism that aligns trajectory-level entropy dynamics between the target and general domains, capturing both entropy magnitude and fine-grained variation. Through this alignment, EDA not only further mitigates entropy collapse but also encourages the policy to acquire more diverse exploration behaviors from the general domain. Experiments across multiple domains show that HEAL consistently improves few-shot RLVR performance. Notably, using only 32 target-domain samples, HEAL matches or even surpasses full-shot RLVR trained with 1K target-domain samples.

Model collapse, the degradation in performance that arises when generative models are trained on the outputs of prior models, is an increasing concern as artificially generated content proliferates. Related critiques of large language models have highlighted their tendency to reproduce frequent patterns in training data, their reliance on vast datasets, and their substantial environmental cost. Together, these factors contribute to data degradation, the reinforcement of cultural biases, and inefficient resource use. In this position paper we aim to combine these views and argue that model collapse threatens current efforts to democratize AI. By reducing training efficiency and skewing data distributions away from the tails of their support, model collapse disproportionately impacts low-resource and marginalized communities. We examine both the environmental and cultural implications of this phenomenon, situate our position within recent position papers on model collapse, and conclude with a call to action. Finally, we outline initial directions for mitigating these effects.

Large pretrained text-to-speech (TTS) models sound almost human for well-resourced languages, but much worse for languages that are rare in their training data. We study this quality gap for Khmer and Korean using VoxCPM2, a 2.4B-parameter, tokenizer-free TTS model that joins a MiniCPM-4 language-model backbone with a flow-matching diffusion decoder. We build one shared, language-tagged corpus of about 26 hours and adapt VoxCPM2 with a single Low-Rank Adaptation (LoRA) adapter, trained on both languages at once and added to both the language model and the decoder. The adapter is zero-initialized, so training starts exactly at the original (zero-shot) model. In native-speaker listening tests, the Khmer Mean Opinion Score (MOS) rises from 3.85 to 4.23 with the best adapter (rank 64), a highly significant gain (paired Wilcoxon test, p<0.001), while training only 0.19 to 3.03 percent of the parameters. The automatic loss and the human ratings, however, disagree on the best rank: validation loss is lowest at rank 128, yet MOS peaks at rank 64. The same adapter brings no gain for Korean, a language the base model already handles well, and at a high rank it even degrades quality. Adaptation therefore helps mainly where the base model is genuinely weak.

Phone recognition (PR) is a key enabler of multilingual and low-resource speech processing tasks, yet robust performance remains elusive. Highly performant English-focused models do not generalize across languages, while multilingual models underutilize pretrained representations. It also remains unclear how data scale, architecture, and training objective contribute to multilingual PR. We present PhoneticXEUS -- trained on large-scale multilingual data and achieving state-of-the-art performance on both multilingual (17.7% PFER) and accented English speech (10.6% PFER). Through controlled ablations with evaluations across 100+ languages under a unified scheme, we empirically establish our training recipe and quantify the impact of SSL representations, data scale, and loss objectives. In addition, we analyze error patterns across language families, accented speech, and articulatory features. All data and code are released openly at https://github.com/changelinglab/PhoneticXeus

There is relatively little, public, and model-ready data on industrial machinery for African economies. This makes it hard to do quantitative analysis or to train language models on numeric tasks grounded in that setting. We release two things to help with part of this problem. The first is the Nigeria Machinery Usage and Failures Dataset: 89 machine-level records across 28 indicators, covering Nigeria's manufacturing and oil and gas sectors from 2006 to 2025. Every record names a public source and is decoded by a codebook. The second is a method for building chain-of-thought (CoT) reasoning examples from these sparse numeric values. The result is 94 prompt, completion, and reasoning-trace rows. In every row, the prompt names the real indicator, subsector, year, and source of the record it comes from. The data adaptation work was carried out by Adaption Labs. Along the way we describe a problem that is common when language models are used to build datasets. The prompts can match the real numbers while saying nothing about the real domain. We show that fixing this raises the share of domain-grounded prompts from 1 out of 78 in an earlier release to 94 out of 94, and that every retrieval answer now matches its source value (84 out of 84). We release the data, the reasoning layer, and a per-row provenance file under CC-BY-4.0. We are clear about the limits. With 89 records and 17 indicators that have only one observation, this is a reference and seed dataset, not a large training set. Most reasoning rows are retrieval rather than multi-step computation.

Language is humanity's most consequential technology, yet for over a billion speakers across India's twenty-two constitutionally recognised languages, its digital layer remains structurally incomplete. Named Entity Recognition (NER), the foundational step in transforming raw text into machine-interpretable knowledge, has been studied exhaustively for English but remains largely unsolved across most Indic languages. This paper presents a rigorous comparative study of generative and encoder-based neural architectures for NER on all eleven languages of the Naamapadam benchmark. We evaluate five classic model families spanning sequence-to-sequence transformers and multilingual encoders; four decoder-only large language models (LLMs) fine-tuned with LoRA and 4-bit NF4 quantisation; and nine generative models in zero-to-5-shot inference. Under strict CoNLL span-level evaluation, encoder-based models (mBERT and XLM-R, both F1=0.675 on Hindi) substantially outperform every generative architecture in ten of eleven languages, with gaps of 7.5-40 percentage points against the strongest competitor (Gemma-2-2B: avg F1=0.427). The best few-shot result reaches only 28% of the encoder baseline. We identify three language clusters--encoder-dominant, partial-coverage, and failure-zone; and provide actionable deployment guidelines grounded in transfer learning and low-resource NLP principles.

Fine-grained morphosyntactic error annotation is important in clinical and developmental language research, yet it is labour-intensive, expert-dependent, and difficult to scale. We present TalkTag, an LLM-based lightweight tool fine-tuned to automate CHAT-style error annotation in spoken-language transcripts. Developed under conditions of extreme data scarcity using children's narrative data, the system shows the feasibility of linguistic analysis in low-resource settings. Our evaluation demonstrates that TalkTag produces encouragingly precise annotation while effectively identifying instances where linguistic ambiguity makes automated tagging genuinely complex. In summary, with TalkTag, we provide a scalable alternative to manual error annotation and practically viable support for morphosyntactic error annotation.

Large language models (LLMs) are widely used as cross-lingual knowledge interfaces. However, culturally grounded questions often reflect globally dominant narratives rather than local contexts. We study this failure mode as \textit{global narrative dominance} in Bangla, a low-resource cultural context. We introduce \texttt{CulturalNB}, a dataset of 717 manually curated Bengali cultural instances with parallel Bangla--English question--answer pairs and supporting evidence, metadata, and sociocultural annotations. Using question-only and evidence-based prompting, we evaluate nine state-of-the-art LLMs with human and two independent LLM judges across metrics for cross-lingual consistency, language anchoring, global substitution, institutional bias, and epistemic perspective coverage. Results show that questions asked in English systematically increase global substitution and institutional framing while reducing local perspective coverage. Local evidence improves factual consistency and perspective coverage, but does not eliminate language-induced epistemic shifts. These findings suggest that cultural failures in LLMs are not only missing-knowledge errors but also failures of grounding and narrative prioritization.

Interest in dialog systems has grown substantially in the past decade. By extension, so too has interest in developing and improving intent classification and slot-filling models, which are two components that are commonly used in task-oriented dialog systems. Moreover, good evaluation benchmarks are important in helping to compare and analyze systems that incorporate such models. Unfortunately, much of the literature in the field is limited to analysis of relatively few benchmark datasets. In an effort to promote more robust analyses of task-oriented dialog systems, we have conducted a survey of publicly available datasets for the tasks of intent classification and slot-filling. We catalog the important characteristics of each dataset, and offer discussion on the applicability, strengths, and weaknesses of each. The emergence of large language models (LLMs) as capable zero-shot NLU systems gives such benchmarks a new role: the corpora cataloged here provide the principled evaluation infrastructure needed to measure LLM capabilities in structured NLU tasks, compare them against specialized models, and identify the settings---multilingual, multi-intent, low-resource---where significant gaps remain. Our goal is that this survey aids in increasing the accessibility of these datasets, which we hope will enable their use in future evaluations of intent classification and slot-filling models, whether those models are task-specific classifiers, fine-tuned language models, or zero-shot LLMs.

At corpus sizes typical of low-resource dialects, single-run comparisons can yield gains that do not replicate. We show this for Garhwali, an under-resourced Indo-Aryan language of the central Himalaya, building the first reproducible multi-seed ASR benchmark on the official VAANI splits, with per-seed outputs and significance testing. Re-examining plausible gains, we find them fragile: neither Focal CTC nor a matra-weighted objective beats standard CTC under seed-level testing, the matra objective fails to cut even its targeted errors, and Hindi-to-Garhwali transfer gives no gain over direct fine-tuning. What holds up is mundane: w2v-BERT 2.0 with standard CTC reaches 47.0% WER over five seeds, beating the larger MMS-1B and comparable models; pretraining design, not parameter count, drives performance, and speed augmentation gives a small, largely consistent gain. Multi-seed evaluation on official splits separates real gains from seed noise.

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

With the emergence of large language models (LLMs) and AI agent frameworks, the human-AI co-work paradigm known as Vibe Coding is changing how people code, making it more accessible and productive. In scientific research, where workflows are more complex and the burden of specialized labor limits independent researchers and those in low-resource areas, the potential impact is even greater, particularly in biomedicine, which involves heterogeneous data modalities and multi-step analytical pipelines. In this paper, we introduce Vibe Medicine, a co-work paradigm in which clinicians and researchers direct skill-augmented AI agents through natural language to execute complex, multi-step biomedical workflows, while retaining the role of research director who specifies objectives, reviews intermediate results, and makes domain-informed decisions. The enabling infrastructure consists of three layers: capable LLMs, agent frameworks such as OpenClaw and Hermes Agent, and the OpenClaw medical skills collection, which includes more than 1,000 curated skills from multiple open-source repositories. We analyze the architecture and skill categories of this collection across ten biomedical domains, and present case studies covering rare disease diagnosis, drug repurposing, and clinical trial design that demonstrate end-to-end workflows in practice. We also identify the principal risks, such as hallucination, data privacy, and over-reliance, and outline directions toward more reliable, trustworthy, and clinically integrated agent-assisted research that advances research and technological equity and reduces health care resource disparities.

Financial sentiment analysis converts unstructured financial news into quantitative signals that can support market analysis and decision-making. Existing work on resource-efficient financial NLP has largely focused on compressing or adapting pretrained language models, with less attention to combining contextual representations with lightweight rule-derived features. This study develops Rule-Aware FinBERT (RA-FinBERT), a parameter-efficient framework that integrates low-rank adaptation (LoRA) with three continuous VADER-derived sentiment proportions (positive, negative, and neutral) and a source-level metadata feature. The standardized four-dimensional feature vector is directly concatenated with the 768-dimensional final-layer FinBERT [CLS] representation and passed through a lightweight classification head. This design introduces only 1,024 additional trainable weights relative to a structurally matched text-only FinBERT model. RA-FinBERT was evaluated against text-only FinBERT and a lightweight DistilBERT baseline for three-class sentiment classification of financial-news titles and descriptions. On the held-out test set, RA-FinBERT achieved 69.89% accuracy and a macro F1 score of 0.634, compared with 63.44% and 0.526 for text-only FinBERT. Neutral-class recall increased from 18.18% to 45.45%. The framework supports both CPU and GPU execution, offering a lightweight and practical approach to financial sentiment classification under constrained computational resources. These findings indicate that rule-derived sentiment information and source metadata can provide complementary signals to contextual FinBERT representations and improve performance with minimal additional model complexity.

Much clinical value is conveyed not through structured records but through communication: exchanges in which patients describe symptoms, clinicians reason and give instructions, ambulances hand over to emergency departments, and nurses pass on a shift. Such language differs from tabular data because meaning depends on speaker role, intent, causality, uncertainty, omission, and channel noise. Healthcare natural language processing must therefore interpret information as conveyed rather than coded. This requires well-annotated corpora, which are scarce because authentic exchanges are private, fragmented, and costly to annotate. Large language models offer a way forward by transforming clinical sources, such as records, diagnostic labels, symptom lists, or care plans, into written and transcribed communication for downstream models. We present a structured narrative survey organized by source representation, communication form and participants, generation method, and downstream task, complemented by thirteen novel case studies. These build clinical NLP systems for communication channels and languages without labeled real-world data, including EMS pre-arrival reports, field-radio casualty documentation, nurse handoffs, patient-portal triage, and low-resource discharge communication. They show that synthetic communication can bootstrap such systems. Findings include the competitiveness of fine-tuned encoder models over evaluated zero-shot baselines and the value of deliberately degraded communication for robustness. The main limitation is that most studies evaluate on held-out synthetic communication, while train-on-synthetic, test-on-authentic evidence remains limited. We conclude that syn-thetic clinical communication is becoming a practical research resource; establishing it as reusable clinical infrastructure will require authentic-data transfer, safety and external validation.

Early detection of PD remains particularly challenging in resource-constrained settings, where voice-based analysis has emerged as a promising non-invasive and cost-effective alternative. However, existing studies predominantly focus on English or other major languages; notably, no voice dataset for PD exists for Bengali -- a language spoken by over 230 million people worldwide -- posing a significant barrier to culturally inclusive and accessible healthcare solutions. We present BenSparX, the first Bengali conversational speech dataset for PD detection, along with a robust and explainable ML framework tailored for early diagnosis. The proposed framework incorporates diverse acoustic feature categories, systematic feature selection methods, and state-of-the-art ML classifiers with extensive hyperparameter optimization. Furthermore, to enhance interpretability and trust in model predictions, the framework incorporates SHAP (SHapley Additive exPlanations) analysis to quantify the contribution of individual acoustic features toward PD detection. Our framework achieves state-of-the-art performance, yielding an accuracy of 95.67%, F1 score of 95.62%, and AUC of 0.990. We further validated our approach by applying the framework to existing PD datasets in other languages, where it consistently outperforms state-of-the-art approaches. This study lays the foundation for identifying subtle yet clinically meaningful vocal biomarkers, particularly in low-resource settings such as Bengali-speaking populations, and represents a significant step toward equitable, explainable, and robust digital health diagnostics for neurodegenerative disorders. The labelled acoustic-feature dataset derived from the audio recordings in this study is available at https://github.com/riadEDU/BenSParX.

This paper introduces WARDEN, an early language model system capable of transcribing and translating Wardaman, an endangered Australian indigenous language into English. The significant challenge we face is the lack of large-scale training data: in fact, we only have 6 hours of annotated audio. Therefore, while it is common practice to train a single model for transcription and translation using large datasets (like English to French), this practice is no longer viable in the Wardaman to English context. To tackle the low-resource challenge, we design WARDEN to have separate transcription and translation models: WARDEN first turns a Wardaman audio input into phonemic transcription, and then the transcription into English translation. Further, we propose two useful techniques to enhance performance. For transcription, we initialize the Wardaman token from Sundanese, a language that shares similar phonemes with Wardaman, to accelerate fine-tuning of the transcription model. For translation, we compile a Wardaman-English dictionary from expert annotations, and provide this domain-specific knowledge to a large language model (LLM) to reason and decide the final output. We empirically demonstrate that this two-stage design works better than data-hungry unified approaches in extremely low data settings. Using a mere 6 hours of annotated data, WARDEN outperforms larger open-source and proprietary models and establishes a strong baseline. Data and code are available.

This paper presents the joint participation of the BIT.UA and AAUBS groups in the ArchEHR-QA 2026 shared task, which focuses on clinical question answering and evidence grounding in a low-resource setting. Due to the absence of training data and the strict data privacy constraints inherent to the healthcare domain (e.g. GDPR), we investigate the capabilities of Large Language Models (LLMs) without weight updates. We evaluate several state-of-the-art proprietary models and locally deployable open-source alternatives using various prompt engineering strategies, including task decomposition, Chain-of-Thought, and in-context learning. Furthermore, we explore majority voting and LLM-as-a-judge ensembling techniques to maximize predictive robustness. Our results demonstrate that while proprietary models exhibit strong resilience to prompt variations, domain-adapted open-source models (such as MedGemma 3 27B) achieve highly competitive performance when paired with the right prompt. Overall, our prompt-based approach proved highly effective, securing 1st place in Subtask 4 (evidence citation alignment) and 3rd place in Subtask 3 (patient-friendly answer generation). All code, results, and prompts are available on our GitHub repository: https://github.com/bioinformatics-ua/ArchEHR-QA-2026.

Span-level skill extraction from job advertisements underpins candidate-job matching and labor-market analytics, yet generative large language models (LLMs) often yield malformed spans, boundary drift, and hallucinations, especially with long-tail terms and cross-domain shift. We present SRICL, an LLM-centric framework that combines semantic retrieval (SR), in-context learning (ICL), and supervised fine-tuning (SFT) with a deterministic verifier. SR pulls in-domain annotated sentences and definitions from ESCO to form format-constrained prompts that stabilize boundaries and handle coordination. SFT aligns output behavior, while the verifier enforces pairing, non-overlap, and BIO legality with minimal retries. On six public span-labeled corpora of job-ad sentences across sectors and languages, SRICL achieves substantial STRICT-F1 improvements over GPT-3.5 prompting baselines and sharply reduces invalid tags and hallucinated spans, enabling dependable sentence-level deployment in low-resource, multi-domain settings.

Reflective thinking is a key competency in education, but assessing reflective writing remains a time-consuming and subjective task for education experts. While automated reflective analysis has been explored in several languages, Hungarian language was not researched extensively. In this paper, we present the first comprehensive study on automatic reflection level classification in Hungarian student essays. We used a large, expert-annotated Hungarian dataset consisting of 1,954 reflective essays collected over multiple academic years and labeled on a four-level reflection scale. We investigate two approaches: (1) classical machine learning models using TF-IDF and semantic embedding features, and (2) Hungarian-specific transformer models fine-tuned for document-level reflection classification. To address the strong class imbalance in the dataset, we systematically examine class weighting, oversampling, data augmentation, and alternative loss functions. An extensive ablation study is conducted to analyze the contribution of each modeling and balancing strategy. Our results show that shallow machine learning models with appropriate feature engineering achieve strong overall performance, reaching up to 71% overall score averaged over accuracy, F1-score, and ROC AUC metrics, while transformer-based models achieve slightly lower overall score (68%) averaged over the same metrics, but demonstrate better generalization on minority reflection classes. These findings highlight the continued relevance of classical methods for low-resource settings and the robustness of transformer models for imbalanced classification. The proposed dataset and experimental insights provide a solid foundation for future research on automated reflective analysis in Hungarian and other morphologically rich languages.

Codecfakes (CFs) are a type of speech deepfakes generated through Audio Language Models (ALMs), with Neural Audio Codecs (NACs) forming the core mechanism for speech encoding and generation. CFs exhibit distributional characteristics that differ from vocoder-based deepfakes, causing detectors trained on vocoder data to generalize poorly to CFs detection. Although this has led to the development of CF detection benchmarks, existing resources are largely confined to English -- and to a limited extent Chinese -- leaving South-East Asian (SEA) languages unexplored. To bridge this gap, we introduce SEA-CF, the first large-scale benchmark for CF detection spanning multiple SEA languages, diverse speaker profiles, and a wide range of NAC architectures. SEA-CF is constructed by synthesizing publicly available real speech corpora. Our experiments show that state-of-the-art (SOTA) CF detectors trained on English-centric datasets fail to generalize to SEA speech due to language-specific phonetic structures, tonal variations, and rich prosodic diversity. We further conduct a comprehensive zero-shot and fine-tuned evaluation of recent SOTA ALMs on SEA-CF. Fine-tuning the ALMs improves performance, however, these are very large being impractical for real-world application due to their scale, particularly in low-resource and latency-constrained settings. To address this limitation, we propose a novel small-ALM, GARUDA tailored for CF detection, which delivers strong performance while remaining lightweight. Extensive evaluations demonstrate that the proposed Small-ALM outperforms strong end-to-end and ALM-based baselines, establishing a new, practical direction for robust CF detection in SEA languages and beyond.

Clickbait, where video titles and thumbnails exaggerate or misrepresent content, reduces user trust, wastes attention, and promotes misinformation on video-sharing platforms. Detecting Bengali clickbait remains challenging because publicly available multimodal datasets are limited. To address this gap, we introduce BanClickThumb, a curated dataset of 7,147 Bengali YouTube thumbnail-title pairs from five content domains, annotated by ten annotators with high agreement (Cohen's Kappa: 0.83-0.93). Using this dataset, we benchmark text-only, image-only, and multimodal approaches. Among unimodal models, BanClickTextFormer (XLM-RoBERTa) achieves 0.82 accuracy, while BanClickImageFormer (SwiftFormer) reaches 0.68. Our proposed multimodal model, BanClickFusionFormer, combines ViT and XLM-RoBERTa through intermediate fusion and achieves the best accuracy of 0.84. Error analysis shows that dense thumbnail text, figurative language, and culturally specific slang remain challenging. Our findings demonstrate the effectiveness of multimodal fusion for Bengali clickbait detection and provide a publicly available benchmark to support future research on low-resource multimodal content analysis.

Large pre-trained language models are increasingly adapted to downstream tasks using parameter-efficient fine-tuning (PEFT), but existing PEFT methods are typically deterministic and unimodal, making them poorly suited for low-resource multimodal settings where predictive uncertainty and cross-modal reliability both matter. We introduce CALIBER (Context-Aware Low-rank Inference with Bayesian Embedding Regularization), a multimodal uncertainty-aware PEFT framework for audio-text learning. CALIBER extends Bayesian low-rank adaptation by conditioning the variational posterior in the adapter space on per-layer, token-level text-audio cross-attention. Specifically, text-derived low-rank features attend to frame-level audio embeddings to produce localized acoustic context, which then modulates the mean and variance of a compact stochastic latent matrix within the rank-$r$ adapter space. This design treats audio not only as an additional feature source, but as a contextual reliability signal that shapes both adaptation and confidence. By confining stochasticity to a low-dimensional latent component, CALIBER retains the computational efficiency and scalability of PEFT while enabling heteroscedastic multimodal uncertainty estimation. Experimental results across diverse text and audio backbones show that CALIBER consistently matches or improves upon text-only Bayesian PEFT and conventional multimodal transfer-learning baselines, with token-level cross-attention yielding the most consistent gains. Our findings demonstrate that localized cross-modal conditioning is an effective and lightweight mechanism for uncertainty-aware multimodal adaptation.

Resources for Grammatical Error Correction (GEC) in non-English languages are scarce, while available spellcheckers in these languages are mostly limited to simple corrections and rules. In this paper we introduce a first GEC corpus for Romanian consisting of 10k pairs of sentences. In addition, the German version of ERRANT (ERRor ANnotation Toolkit) scorer was adapted for Romanian to analyze this corpus and extract edits needed for evaluation. Multiple neural models were experimented, together with pretraining strategies, which proved effective for GEC in low-resource settings. Our baseline consists of a small Transformer model trained only on the GEC dataset (F0.5 of 44.38), whereas the best performing model is produced by pretraining a larger Transformer model on artificially generated data, followed by finetuning on the actual corpus (F0.5 of 53.76). The proposed method for generating additional training examples is easily extensible and can be applied to any language, as it requires only a POS tagger

Recent advancements in Large Language Models (LLMs) have shown promising results in music understanding and generation tasks. However, existing works remain confined to Western tonal traditions, offering little insight into whether current LLMs can handle structurally distinct low-resource musical traditions. We present the first systematic evaluation of LLM competence in South Asian classical music, a tradition governed by raga, tala-based melodic constraints that impose fundamentally different structural principles from Western harmony-driven music. We ground our evaluation in Hindustani classical theory and Bengali classical forms, including Rabindra and Nazrul Sangeet -- representative low-resource traditions within South Asian classical music. For music understanding evaluation, we introduce a 504-question-answer benchmark spanning raga grammar, cultural knowledge, and symbolic notation reasoning, evaluating 33 LLMs where frontier models such as Gemini 2.5 Pro achieve 85-90% accuracy, while most open-source models remain in the 23-40% range. For music generation, we design a five-level controlled prompting framework and find that even the strongest model produces stylistically faithful outputs only 40% of the time. These results reveal that structural validity and stylistic faithfulness in music generation are distinct objectives and highlight an open challenge for culturally grounded music modeling.

The diachronic evolution from Latin to the Romance languages involved a restructuring of the grammatical gender system from a tripartite configuration (masculine, feminine, neuter) to a bipartite one (masculine, feminine) in most Romance languages. In this work, we introduce an interpretable deep learning framework to investigate this phenomenon at both lexical and contextual levels. First, we show that conventional tokenization strategies are insufficiently robust for this low-resource historical setting, and that our proposed tokenizer improves performance over these baselines. At the lexical level, we evaluate the contribution of morphological features to gender prediction. At the contextual level, we quantify the contributions of different part-of-speech categories to grammatical gender prediction. Together, these analyses characterize the distribution of gender information between the lemma and its sentential context. We make our codebase, datasets, and results publicly available at \href{https://github.com/ahan-2000/Lost-in-Translation-}{https://github.com/ahan-2000/Lost-in-Translation-}.