Category
9,568 papers
Asked to choose between candidates and explain the choice, a language model often rejects a rival by naming a fact its profile lacks: no director, no date of death. That sentence is a claim about the text in front of the model, and it can be tested without any judge. We insert a real corpus sentence stating the named f...
Recent advances in paraphrase detection reveal a fundamental trade-off: large language models achieve high accuracy but require high computation, while efficient Siamese-BERT variants offer practical scalability with reduced transparency in rationale generation. We present R-DEIM Net, a 76M-parameter dual-expert archit...
Small-sample LLM evaluations can look far more definitive than their evidence supports, and it is recommended to report rank stability, per-cell provenance, executed sensitivity comparisons, raw per-run outputs, and a measurement date alongside any ranking.
Language models advise people, keep them company, and write software while they sleep. Measuring what they do is hard: behavior has to be sampled repeatedly across models, prompts and releases, most of it lives in unstructured text that has to be coded before it can be counted, and the result has to be legible and rigo...
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work studies whether a carefully domain-adapted retrieval-augmented generation pipeline closes the gap between compact and compact model quality in financial institutions under dense, frequently amended rulebooks.
Three of the strongest pipelines succeed on different questions, and an oracle that picks the best pipeline per question gains roughly thirteen points over the best single pipeline, though evidence-type routing recovers almost none of it.
Large language models (LLMs) are increasingly used as synthetic survey respondents to estimate population response distributions. In cross-cultural survey simulation, evaluations should assess not only distributional fidelity within countries but also whether differences across countries are preserved. However, existin...
The proposed sequence labeling scheme enables the use of a shared architecture that learns the syntactic structures from both grammatical structures simultaneously and hence improves generalization.
While Large Language Models (LLMs) rely on highly non-linear components, in this work we demonstrate that they exhibit fundamental linearity: when inputs from distinct text streams are linearly combined, the model outputs a superposition of the individual next-token distributions. We term this the \textit{Superposition...
An end-to-end study of automatic speech recognition (ASR) for adolescent health communication in three Ghanaian languages, validated through KasaHealth, a live voice-first ASRH application deployed in all three languages, complemented by Senti-Check, a technical evaluation harness.
TimeBraid, a series of unified time-series and language models that align pretrained language models and pretrained time-series foundation models through interleaved global residual attention layers, remains competitive with far larger general-purpose models and task-specific counterparts.
PPTBench establishes a measurable testbed for studying visual coding and advancing agents toward more reliable visual creation, and shows that agents can generally produce valid slide files, but struggle to produce high-quality reconstructions that faithfully recover the semantics and visual structure of the target.
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.
