18 stories tagged Language
A new arXiv study tested nine large language models from six providers and found that asking the same nuclear strike question in Japanese led to significantly fewer recommendations for launching an attack compared to English, highlighting a critical language bias in AI safety alignment.
A new study from MIT and Harvard introduces 'narrative anchoring' — a bias where clinical AI models produce different diagnoses from identical medical facts depending on how they are worded. The benchmark uses 1,000 USMLE vignettes to isolate language register as the sole variable, with no demographic markers present.
Researchers have identified a new scaling law, the contextual persistence function P(d), that governs how word arrangement affects meaning in human language. Using LLMs as probes across 10 languages, they found the impact of prior context follows a power-law decay, which could improve AI language models.
Researchers from the University of Washington and NYU Abu Dhabi introduced CAMMAR, a representation learning framework that organizes Arabic meanings into nested lexical, cultural, and metaphorical embedding subspaces. This approach addresses 'semantic smearing' in current Arabic language models and could improve translation, chatbots, and other AI tools for Arabic speakers.
Researchers created EspanStereo, a dataset of Spanish-language stereotypes, by combining human and AI efforts. This could help make AI systems more culturally aware and reduce biases in non-English contexts.
AI agents can develop shared languages through interaction, and the way they store memories significantly impacts their success. This discovery could improve how AI systems communicate and collaborate in the future.
Researchers created a new test to evaluate how well AI models handle mixed-language text, like Hindi or Tamil blended with English. This is common in many multilingual communities but often confusing for AI systems.
Researchers developed LAGO, a system that helps AI robots plan tasks by understanding human language. This could make robots more useful in everyday settings. The framework predicts intermediate goals from language, reducing errors in planning.
Researchers created LaViSA, a benchmark designed to test whether AI models can resolve structurally ambiguous sentences by leveraging visual scenes. This helps machines better interpret complex, real-world situations where word order alone isn't enough.
A new study reveals that current AI models favor languages like English and French, making them less effective and more expensive for speakers of underrepresented languages. Researchers propose new methods to make these models more fair and efficient for everyone.
Researchers created a multilingual dataset to improve AI's ability to share facts across languages. This could make AI assistants more reliable worldwide.
Researchers found that AI models often prioritize globally dominant narratives over local cultural knowledge. They created a dataset to study this issue in Bengali, showing how AI can misrepresent cultural contexts.
Researchers developed a new AI system to better identify language patterns linked to autism. This could help diagnose social language disorders more accurately in the future.
Researchers found that AI models align more closely with human brains when trained on the same language. This suggests language-specific training data shapes how AI understands us, not an inherent property of any language.
Wispr Flow is seeing rapid growth in India after adding Hinglish support to its voice AI. Despite challenges, the company is betting big on the Indian market.
Researchers propose a new method to decode compressed semantic representations from EEG signals, challenging the assumption that full linguistic structure can be recovered. This approach could revolutionize brain-computer interfaces and neuro-linguistic studies.
AI models are being explored to bridge communication gaps in mathematics, potentially unifying disparate fields. This could accelerate research and collaboration across mathematical disciplines.
MegaTrain enables full precision training of large language models on a single GPU. It stores parameters in host memory and uses GPUs as compute engines.