Latest AI/ML News
2637 articles · 🧠 Research
arXiv:2608.17534v1 Announce Type: new Abstract: Large language models increasingly serve as persistent conversational assistants, requiring memory tha…
arXiv:2608.17516v1 Announce Type: new Abstract: Gender bias or other social biases in large language models (LLMs) are frequently evaluated with quest…
arXiv:2608.17454v1 Announce Type: new Abstract: This paper presents a pipeline for analyzing media bias and framing in online news. The pipeline group…
arXiv:2608.17399v1 Announce Type: new Abstract: Text which has been translated from another language tends to carry with it evidence of translation$\u…
arXiv:2608.17379v1 Announce Type: new Abstract: We introduce PTXBench, a benchmark for evaluating and adapting large language models (LLMs) to use arc…
arXiv:2608.17356v1 Announce Type: new Abstract: Most automated essay scoring (AES) systems output a single holistic score without interpretable eviden…
arXiv:2608.17325v1 Announce Type: new Abstract: Tokenization is a fundamental component of language modeling pipelines. Despite its importance, it is…
arXiv:2608.17288v1 Announce Type: new Abstract: GPT attention measures token compatibility through dot-product similarity. This mechanism is simple, e…
arXiv:2608.17223v1 Announce Type: new Abstract: Financial-news direction prediction has become a popular NLP benchmark, yet reported gains depend crit…
arXiv:2608.17218v1 Announce Type: new Abstract: Works of literature are complicated; they balance plot, suspense, surprise, and artistic expression. S…
arXiv:2608.17205v1 Announce Type: new Abstract: Vision-language models (VLMs) combine images and text, but when the two conflict and one becomes harde…
arXiv:2608.17188v1 Announce Type: new Abstract: Multi-agent AI workflows are limited not only by model quality but by token cost, latency, and context…
arXiv:2608.17184v1 Announce Type: new Abstract: Job Safety Analysis (JSA) and pre-task planning can benefit from prior incident records, yet historica…
arXiv:2608.17171v1 Announce Type: new Abstract: Many table-centric NLP tasks such as NL2SQL first retrieve relevant tables from large collections usin…
arXiv:2608.17168v1 Announce Type: new Abstract: Reasoning has become a standard technique and feature for contemporary LLMs; however, its application…
arXiv:2608.17153v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has significantly enhanced the performance of large language mode…
arXiv:2608.17120v1 Announce Type: new Abstract: Children learn hundreds of words over the first years of their lives, in a process that begins slowly…
arXiv:2608.17102v1 Announce Type: new Abstract: Modern multimodal foundation models (MFMs) have made rapid progress on tasks requiring integrated perc…
arXiv:2608.17096v1 Announce Type: new Abstract: The Voynich manuscript (Beinecke MS 408) is usually analysed on three unstated assumptions: that its g…
arXiv:2608.17088v1 Announce Type: new Abstract: A central goal of multilingual NLP is to achieve high monolingual performance per language and cross-l…