arXiv subjects

Antonios Anastasopoulos

Publications and source records attributed to Antonios Anastasopoulos.

At least 19 recordsLinked to original sources

arXiv2026

Mobilizing the Archive: Bitext Extraction at Scale from Archival Documents for Extremely Low-resource Languages

While mining parallel sentences from web pages has proven effective for low-resource machine translation, the majority of the world's languages have little to no web presence. What they do have, though, are resources that are the result of centuries of efforts by linguists, such as grammars, dictionaries, and other documentation materials. We propose extracting translation examples from such linguistic resources, which offer parallel data for languages under-represented online and could potentially scale to thousands more languages. We develop a pipeline to achieve this, leveraging an Optical Character Recognition (OCR) model as well as a vision language model (VLM), to ensure identified content to be aligned with visual layout information. We demonstrate the utility of the extracted bitexts for bootstrapping translation systems across 20 languages, both by training machine translation models and by applying in-context learning for large language models. For in-context learning, we observe improvements of +15.78 and +6.94 chrF2++ over zero-shot translation for into low- and high-resource languages, respectively.

cs.CL↗

arXiv2026

Debias It Yourself: Teaching LLMs Cognitive Bias Mitigation Interventions

Bias has long been studied in social psychology and cognitive science, where decades of research have produced a body of validated interventions that reduce stereotypical thinking and prejudiced responses in humans. We propose Debias It Yourself (DIY), a cognitively grounded framework that translates five such interventions into debiasing procedures for large language models and delivers them through three established paradigms: Show (in-context examples), Train (instruction tuning), and Revise (guided self-revision). Across three models, five bias benchmarks, eleven debiasing baselines, and three reasoning benchmarks, Train+Revise and Revise alone attain the top two average ranks, lead the bias-reasoning tradeoff (mean bias as low as 2% at 90% reasoning accuracy), and reduce bias on unseen dimensions by up to 14.8%. Our code and data are publicly available.

cs.CL↗

arXiv2026

MAPLE: Metadata Conditioned LLM Pretraining for Locale-Aware Question Answering

Large language models can memorize competing locale-specific facts yet fail to select among them when the locale changes, defaulting instead to a single globally dominant answer. We formalize this as localized knowledge disambiguation and introduce LocalNewsQA, an 18,700-item English-news benchmark that pairs the same question across two locales and scores whether a model actually switches its answer when the locale changes. We also introduce MAPLE, a controlled family of decoder-only models pretrained with document-level geographic metadata (source URL, country, and continent) already present in the training corpus, and compare it to metadata-free controls trained on identical data with the same token budget, architecture, and optimization. In controlled experiments at 1B and 3B, with inference-time metadata fixed, pretraining with metadata in MAPLE produces measurable switching and improves accuracy on questions whose correct answer depends on locale. Ablations and external-benchmark evaluations further suggest that locale-conditioned prediction benefits from geographic provenance learned during pretraining and that these benefits strengthen at larger model sizes.

cs.CL↗

arXiv2026

Double Trouble: Bilingual Pretraining Leaves Language-Conditioned Effects in Shared-Language Representations

A concept can carry different associations across languages, while modern language models learn English alongside many other languages during pretraining. Yet comparisons among existing models cannot easily isolate how any one language changes the way these models represent English concepts because their training corpora, compute, architectures, and random seeds all differ. We study this question through a controlled experiment with 40 matched 310M-parameter decoder-only models that share an architecture, tokenizer, training recipe, and English data source. Each bilingual condition adds one of eight languages, while four experimental comparisons separately account for English exposure, total training, and English-document overlap. We align each model pair using 3,000 common English words, then measure where 1,000 held-out English concepts fall along 50 fixed semantic contrasts, such as red versus white. Across 32 experimental comparisons, English concept positions differ more between bilingual and English-only conditions than between English-only runs with different random seeds. These differences are larger in contextual states than in token embeddings and peak in middle layers. The language learned alongside English can therefore change how a model represents English concepts even when its English input representations are explicitly aligned.

cs.CL↗

arXiv2026

Lost in the Tower of Babel: The Adverse Effects of Incidental Multilingualism in LLMs

This paper argues that contemporary multilingual NLP has converged on a fragile and misleading paradigm of incidental multilingualism. Today's LLMs appear multilingual largely because they are trained on massive, uneven web corpora, not because multilingual or multicultural competence has been treated as a core design objective. We contend that this paradigm systematically produces unequal, brittle, and opaque behavior across languages, with severe consequences in real-world and agentic deployments where models must reason, plan, and act across multiple linguistic contexts. We report a focused empirical study of two practical questions: which languages models self-report as supported and which languages they actually respond in across multilingual prompts. We additionally demonstrate how even a simple language-change attack can surface these failures and expose hidden assumptions about language in LLM-based systems. To address this, we call for a shift toward multilingualism by design: a research agenda that treats equitable multilingual performance, cultural grounding, and cross-lingual behavioral understanding as first-class goals in all aspects of the model pipeline.

cs.CL↗

arXiv2026

Safe Language Generation in the Limit

Recent results in learning a language in the limit have shown that, although language identification is impossible, language generation is tractable. As this foundational area expands, we need to consider the implications of language generation in real-world settings. This work offers the first theoretical treatment of safe language generation. Building on the computational paradigm of learning in the limit, we formalize the tasks of safe language identification and generation. We prove that under this model, safe language identification is impossible, and that safe language generation is at least as hard as (vanilla) language identification, which is also impossible. Last, we discuss several intractable and tractable cases.

cs.CL↗

arXiv2026

Speaking of Language: Reflections on Metalanguage Research in NLP

This work aims to shine a spotlight on the topic of metalanguage. We first define metalanguage, link it to NLP and LLMs, and then discuss our two labs' metalanguage-centered efforts. Finally, we discuss four dimensions of metalanguage and metalinguistic tasks, offering a list of understudied future research directions.

cs.CL↗

arXiv2026

VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models

While bias in large language models (LLMs) is well-studied, similar concerns in vision-language models (VLMs) have received comparatively less attention. Existing VLM bias studies often focus on portrait-style images and gender-occupation associations, overlooking broader and more complex social stereotypes and their implied harm. This work introduces VIGNETTE, a large-scale VQA benchmark with 30M+ images for evaluating bias in VLMs through a question-answering framework spanning four directions: factuality, perception, stereotyping, and decision making. Beyond narrowly-centered studies, we assess how VLMs interpret identities in contextualized settings, revealing how models make trait and capability assumptions and exhibit patterns of discrimination. Drawing from social psychology, we examine how VLMs connect visual identity cues to trait and role-based inferences, encoding social hierarchies, through biased selections. Our findings uncover subtle, multifaceted, and surprising stereotypical patterns, offering insights into how VLMs construct social meaning from inputs.

cs.CL↗

arXiv2026

Talent or Luck? Evaluating Attribution Bias in Large Language Models

When a student fails an exam, do we tend to blame their effort or the test's difficulty? Attribution, defined as how reasons are assigned to event outcomes, shapes perceptions, reinforces stereotypes, and influences decisions. Attribution Theory in social psychology explains how humans assign responsibility for events using implicit cognition, attributing causes to internal (e.g., effort, ability) or external (e.g., task difficulty, luck) factors. LLMs' attribution of event outcomes based on demographics carries important fairness implications. Most works exploring social biases in LLMs focus on surface-level associations or isolated stereotypes. This work proposes a cognitively grounded bias evaluation framework to identify how models' reasoning disparities channelize biases toward demographic groups.

cs.CL↗

arXiv2026

IDIOLEX: Unified and Continuous Representations for Idiolectal and Stylistic Variation

Existing sentence representations primarily encode what a sentence says, rather than how it is expressed, even though the latter is important for many applications. In contrast, we develop sentence representations that capture style and dialect, decoupled from semantic content. We call this the task of idiolectal representation learning. We introduce IDIOLEX, a framework for training models that combines supervision from a sentence's provenance with linguistic features of a sentence's content, to learn a continuous representation of each sentence's style and dialect. We evaluate the approach on dialects of both Arabic and Spanish. The learned representations capture meaningful variation and transfer across domains for analysis and classification. We further explore the use of these representations as training objectives for stylistically aligning language models. Our results suggest that jointly modeling individual and community-level variation provides a useful perspective for studying idiolect and supports downstream applications requiring sensitivity to stylistic differences, such as developing diverse and accessible LLMs.

cs.CL↗

arXiv2026

What Do We Mean by 'Pilot Study': Early Findings from a Meta-Review of Pilot Study Reporting at CHI

Pilot studies (PS) are ubiquitous in HCI research. CHI papers routinely reference 'pilot studies', 'pilot tests', or 'preliminary studies' to justify design decisions, verify procedures, or motivate methodological choices. Yet despite their frequency, the role of pilot studies in HCI remains conceptually vague and empirically underexamined. Unlike fields such as medicine, nursing, and education, where pilot and feasibility studies have well-established definitions, guidelines, reporting standards and even a dedicated research journal, the CHI community lacks a shared understanding of what constitutes a pilot study, why they are conducted, and how they should be reported. Many papers reference pilots 'in passing', without details about design, outcomes, or how the pilot informed the main study. This variability suggests a methodological blind spot in our community.

cs.HC↗

arXiv2025

Graph Enhanced Trajectory Anomaly Detection

Trajectory anomaly detection is essential for identifying unusual and unexpected movement patterns in applications ranging from intelligent transportation systems to urban safety and fraud prevention. Existing methods only consider limited aspects of the trajectory nature and its movement space by treating trajectories as sequences of sampled locations, with sampling determined by positioning technology, e.g., GPS, or by high-level abstractions such as staypoints. Trajectories are analyzed in Euclidean space, neglecting the constraints and connectivity information of the underlying movement network, e.g., road or transit networks. The proposed Graph Enhanced Trajectory Anomaly Detection (GETAD) framework tightly integrates road network topology, segment semantics, and historical travel patterns to model trajectory data. GETAD uses a Graph Attention Network to learn road-aware embeddings that capture both physical attributes and transition behavior, and augments these with graph-based positional encodings that reflect the spatial layout of the road network. A Transformer-based decoder models sequential movement, while a multiobjective loss function combining autoregressive prediction and supervised link prediction ensures realistic and structurally coherent representations. To improve the robustness of anomaly detection, we introduce Confidence Weighted Negative Log Likelihood (CW NLL), an anomaly scoring function that emphasizes high-confidence deviations. Experiments on real-world and synthetic datasets demonstrate that GETAD achieves consistent improvements over existing methods, particularly in detecting subtle anomalies in road-constrained environments. These results highlight the benefits of incorporating graph structure and contextual semantics into trajectory modeling, enabling more precise and context-aware anomaly detection.

cs.LG↗

arXiv2025

TigerCoder: A Novel Suite of LLMs for Code Generation in Bangla

Despite being the 5th most spoken language, Bangla remains underrepresented in Large Language Models (LLMs), particularly for code generation. This primarily stems from the scarcity of high-quality data to pre-train and/or finetune such models. Hence, we introduce the first dedicated family of Code LLMs for Bangla (1B & 9B). We offer three major contributions: (1) a comprehensive Bangla code instruction datasets for programming domain adaptation; (2) MBPP-Bangla, an evaluation benchmark for Bangla code generation; and (3) the TigerCoder-family of Code LLMs, achieving significant ~11-18% performance gains at Pass@1 over existing multilingual and general-purpose Bangla LLMs. Our findings show that curated, high-quality datasets can overcome limitations of smaller models for low-resource languages. We open-source all resources to advance further Bangla LLM research.

cs.CL↗

arXiv2025

Dialect Normalization using Large Language Models and Morphological Rules

Natural language understanding systems struggle with low-resource languages, including many dialects of high-resource ones. Dialect-to-standard normalization attempts to tackle this issue by transforming dialectal text so that it can be used by standard-language tools downstream. In this study, we tackle this task by introducing a new normalization method that combines rule-based linguistically informed transformations and large language models (LLMs) with targeted few-shot prompting, without requiring any parallel data. We implement our method for Greek dialects and apply it on a dataset of regional proverbs, evaluating the outputs using human annotators. We then use this dataset to conduct downstream experiments, finding that previous results regarding these proverbs relied solely on superficial linguistic information, including orthographic artifacts, while new observations can still be made through the remaining semantics.

cs.CL↗

arXiv2025

Developing a Mixed-Methods Pipeline for Community-Oriented Digitization of Kwak'wala Legacy Texts

Kwak'wala is an Indigenous language spoken in British Columbia, with a rich legacy of published documentation spanning more than a century, and an active community of speakers, teachers, and learners engaged in language revitalization. Over 11 volumes of the earliest texts created during the collaboration between Franz Boas and George Hunt have been scanned but remain unreadable by machines. Complete digitization through optical character recognition has the potential to facilitate transliteration into modern orthographies and the creation of other language technologies. In this paper, we apply the latest OCR techniques to a series of Kwak'wala texts only accessible as images, and discuss the challenges and unique adaptations necessary to make such technologies work for these real-world texts. Building on previous methods, we propose using a mix of off-the-shelf OCR methods, language identification, and masking to effectively isolate Kwak'wala text, along with post-correction models, to produce a final high-quality transcription.

cs.CL↗

arXiv2025

GMU Systems for the IWSLT 2025 Low-Resource Speech Translation Shared Task

This paper describes the GMU systems for the IWSLT 2025 low-resource speech translation shared task. We trained systems for all language pairs, except for Levantine Arabic. We fine-tuned SeamlessM4T-v2 for automatic speech recognition (ASR), machine translation (MT), and end-to-end speech translation (E2E ST). The ASR and MT models are also used to form cascaded ST systems. Additionally, we explored various training paradigms for E2E ST fine-tuning, including direct E2E fine-tuning, multi-task training, and parameter initialization using components from fine-tuned ASR and/or MT models. Our results show that (1) direct E2E fine-tuning yields strong results; (2) initializing with a fine-tuned ASR encoder improves ST performance on languages SeamlessM4T-v2 has not been trained on; (3) multi-task training can be slightly helpful.

cs.CL↗

arXiv2025

Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning

Multilingual alignment of sentence representations has mostly required bitexts to bridge the gap between languages. We investigate whether visual information can bridge this gap instead. Image caption datasets are very easy to create without requiring multilingual expertise, so this offers a more efficient alternative for low-resource languages. We find that multilingual image-caption alignment can implicitly align the text representations between languages, languages unseen by the encoder in pretraining can be incorporated into this alignment post-hoc, and these aligned representations are usable for cross-lingual Natural Language Understanding (NLU) and bitext retrieval.

cs.CL↗

arXiv2025

Automated Python Translation

Python is one of the most commonly used programming languages in industry and education. Its English keywords and built-in functions/modules allow it to come close to pseudo-code in terms of its readability and ease of writing. However, those who do not speak English may not experience these advantages. In fact, they may even be hindered in their ability to understand Python code, as the English nature of its terms creates an additional layer of overhead. To that end, we introduce the task of automatically translating Python's natural modality (keywords, error types, identifiers, etc.) into other human languages. This presents a unique challenge, considering the abbreviated nature of these forms, as well as potential untranslatability of advanced mathematical/programming concepts across languages. We therefore create an automated pipeline to translate Python into other human languages, comparing strategies using machine translation and large language models. We then use this pipeline to acquire translations from five common Python libraries (pytorch, pandas, tensorflow, numpy, and random) in seven languages, and do a quality test on a subset of these terms in French, Greek, and Bengali. We hope this will provide a clearer path forward towards creating a universal Python, accessible to anyone regardless of nationality or language background.

cs.CL↗