arXiv:2603.29875v1 Announce Type: cross
Abstract: One of the key problems in Retrieval-augmented generation (RAG) systems is that chunk-based retrieval pipelines represent the source chunks as atomic objects, mixing the information contained within su…
arXiv:2603.29552v1 Announce Type: new
Abstract: Multilingualism is incredibly common around the world, leading to many important theoretical and practical questions about how children learn multiple languages at once. For example, does multilingual ac…
arXiv:2603.29791v1 Announce Type: cross
Abstract: Although many AI applications of interest require specialized multi-modal models, relevant data to train such models is inherently scarce or inaccessible. Filling these gaps with human annotators is pr…
arXiv:2603.29541v1 Announce Type: new
Abstract: Due to the scarcity of labeled dialectal speech, audio dialect classification is a challenging task for most languages, including Swiss German. In this work, we explore the ability of large language mode…
arXiv:2603.29676v1 Announce Type: cross
Abstract: Large vision-language models (LVLMs) achieve impressive performance, yet their internal decision-making processes remain opaque, making it difficult to determine if the success stems from true multimod…
arXiv:2603.29522v1 Announce Type: new
Abstract: Modern language models (LMs) must be trained on many orders of magnitude more words of training data than human children receive before they begin to produce useful behavior. Assessing the nature and ori…
arXiv:2603.29617v1 Announce Type: cross
Abstract: Understanding how the brain processes linguistic constructions is a central challenge in cognitive neuroscience and linguistics. Recent computational studies show that artificial neural language models…
arXiv:2603.29518v1 Announce Type: new
Abstract: Conversational systems should generate diverse language forms to interact fluently and accurately with users. In this context, Natural Language Generation (NLG) engines convert Meaning Representations (M…
arXiv:2603.28913v1 Announce Type: new
Abstract: Polarity detection becomes substantially more challenging under domain shift, particularly in heterogeneous, long-form narratives with complex discourse structure, such as Holocaust oral histories. This …
arXiv:2603.29517v1 Announce Type: new
Abstract: Despite rapid advances in large language models (LLMs), their linguistic abilities in low-resource and morphologically rich languages are still not well understood due to limited annotated resources and …