Category
9,568 papers
It is suggested that likelihood preferences over controlled declarative alternatives and task-conditioned answer selection probe distinct aspects of model behavior, and should not be treated as interchangeable.
BanglaTurn is presented, a corpus for end-of-turn detection in Bangla conversational speech, and a model trained on it, which pairs a Whisper encoder with task-specific classification heads.
Sparse AutoEncoders (SAEs) offer a promising way to inspect language model representations, but it is still unclear what kind of linguistic structure their latents expose. We use part-of-speech (PoS) categories as a controlled test case to study whether morpho-syntactic information is encoded by individual latents or b...
Understanding how Large Language Models (LLMs) encode linguistic structures remains a fundamental challenge in interpretability research. While diagnostic classifiers (or"probes") are widely used for this task, they face significant methodological criticism: training auxiliary classifiers introduces capacity confounds...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Lexical borrowings are words from one language that are introduced into another language. Identifying lexical borrowings in text is a relevant task for data-centric fields in Linguistics such as lexicography or corpus linguistics, but none of the standard libraries for text processing offers such a functionality. In th...
End-to-end event extraction remains challenging for large language models as it requires simultaneous identification of event triggers, classification of event types, and extraction of schema-grounded argument spans. We present EAGER, a reinforcement learning framework for generative event extraction that combines fine...
Some documents that embedding-based topic models initially classify as noise later become founding members of emerging topics. At publication time, however, they appear as scattered points in embedding space and are difficult to distinguish from ordinary noise without the benefit of hindsight. We study whether such ant...
Bangla, the seventh most spoken language in the world, remains under-resourced for neural text-to-speech. Public Bangla speech corpora are dominated by short read-prompt utterances collected for speech recognition, leaving long-form prosody and consistent single-speaker narration uncovered. We present BanglaKontho, a s...
This work evaluates LLM politeness judgments using two English-language datasets with complementary annotation formats, finding that inter-model agreement is stronger than model--human agreement.
COILD, an Indic-centric parallel corpus comprising over 1.16 million human-translated and human-verified sentence pairs, covers 20 Indian language pairs across the Indo-Aryan, Dravidian, Tibeto-Burman, and Austro-Asiatic language families, and provides a valuable training and evaluation resource for advancing multiling...
This paper investigates how script knowledge is distributed across the layers of LLMs using two complementary interpretability methods: logistic regression probing and logit-lens analysis, which show that script commitment consistently occurs at the very last layers of the LLMs.
It is shown that single-snapshot fairness audits on full-precision models do not capture the deployment-time burden that compression places on already-marginalized speakers, and cast the temporal-taxation construct of Choi and Choi (2025) as a quantitative metric.
Natural Language Processing
Our most capable vision-language-action model enhances robot dexterity, reliability, and safety
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
