Related papers: SampoNLP: A Self-Referential Toolkit for Morpholog…

Tokenization remains a fundamental yet underexplored bottleneck in natural language processing, with strategies largely static despite remarkable progress in model architectures. We present SupraTok, a novel tokenization architecture that…

This study introduces SLLMBO, an innovative framework leveraging large language models (LLMs) for hyperparameter optimization (HPO), incorporating dynamic search space adaptability, enhanced parameter space exploitation, and a novel…

This paper presents a fully self-supervised approach to borrowing detection in multilingual wordlists. The method combines two sources of information: PMI similarities based on a global correspondence model and a lightweight contrastive…

Large language models (LLMs) have achieved impressive results in high-resource languages like English, yet their effectiveness in low-resource and morphologically rich languages remains underexplored. In this paper, we present a…

The impact of subword tokenization on language model performance is well-documented for perplexity, with finer granularity consistently reducing this intrinsic metric. However, research on how different tokenization schemes affect a model's…

Understanding the internal mechanisms of large language models (LLMs) is integral to enhancing their reliability, interpretability, and inference processes. We present Constituent-Aware Pooling (CAP), a methodology designed to analyse how…

We propose a language-independent approach for improving statistical machine translation for morphologically rich languages using a hybrid morpheme-word representation where the basic unit of translation is the morpheme, but word boundaries…

Improving the reasoning capabilities of large language models (LLMs) typically requires supervised fine-tuning with labeled data or computationally expensive sampling. We introduce Unsupervised Prefix Fine-Tuning (UPFT), which leverages the…

Large Language Models (LLMs) exhibit a puzzling disparity in their formal linguistic competence: while they learn some linguistic phenomena with near-perfect mastery, they often perform below chance on others, even after training on…

The rapid progress of text-to-image (T2I) models has unlocked unprecedented creative potential, yet their ability to faithfully render complex prompts involving multiple objects, attributes, and spatial relationships remains a significant…

We introduce Multi-SimLex, a large-scale lexical resource and evaluation benchmark covering datasets for 12 typologically diverse languages, including major languages (e.g., Mandarin Chinese, Spanish, Russian) as well as less-resourced ones…

With the advancements of transformer-based architectures, we observe the rise of natural language preprocessing (NLPre) tools capable of solving preliminary NLP tasks (e.g. tokenisation, part-of-speech tagging, dependency parsing, or…

Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM). This unified input paradigm enables VLMs to…

Text compression for large language model (LLM) systems is usually framed as token deletion, retrieval, summarization, or exact reconstruction. We study a more aggressive but explicitly lossy setting: compress text into compact codes that…

The widespread application of pre-trained language models (PLMs) in natural language processing (NLP) has led to increasing concerns about their explainability. Selective rationalization is a self-explanatory framework that selects…

We introduce DecompSR, decomposed spatial reasoning, a large benchmark dataset (over 5m datapoints) and generation framework designed to analyse compositional spatial reasoning ability. The generation of DecompSR allows users to…

Category-agnostic pose estimation (CAPE) has traditionally relied on support images with annotated keypoints, a process that is often cumbersome and may fail to fully capture the necessary correspondences across diverse object categories.…

Scientific literature is increasingly siloed by complex language, static disciplinary structures, and potentially sparse keyword systems, making it cumbersome to capture the dynamic nature of modern science. This study addresses these…

Unsupervised methods are widely used to induce latent semantic structure from large text collections, yet their outputs often contain incoherent, redundant, or poorly grounded clusters that are difficult to validate without labeled data. We…

Language models require tokenized inputs. However, tokenization strategies for continuous data like audio and vision are often based on simple heuristics such as fixed sized convolutions or discrete clustering, which do not necessarily…