Category
2,658 papers
A current high-capability model can be used as the user-facing component of an automated, multi-stage workflow serving an explicitly manipulative objective, and this result exposes a compositional safety gap.
Archival Summary Package: Cyber-Biological Synchronization and Behavioral Vector Injection (BVI) Title: Cyber-Biological Synchronization and Behavioral Vector Injection (BVI): Axiomatic Foundations, Topo-Information Dynamics, and Radix 00–32 Systemic Homeostasis Authors: Kasiulevicius, Egidijus; Kasiulevicius, Azuolas;...
Visual impairments affect upwards of 2.2 billion people worldwide. As AI systems increasingly support navigation for people with visual impairments, how uncertainty is communicated becomes critical. Prior work shows that communicating uncertainty can improve trust calibration and decision-making, yet it remains underex...
Tier 3 (direct effect forecast) entry to the Silicon Sample Benchmark from team_15. We predict all 208 average treatment effects (16 message interventions x 13 preregistered outcomes) of a sealed ~18,000-person US megastudy on trust in climate scientists, blind and before any human data were released. The approach uses...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Abstract: General-purpose probabilistic programming makes Bayesian data analysis broadly accessible, but its computational cost can become prohibitive as model dimension grows. The R package hobbs (High dimensiOnal Bayesian omniBus Sampler) is a probabilistic programming language and system designed to make high-dimens...
Agent Skills are reusable packages of procedural knowledge that augment large language model (LLM) agents at inference time. Educational agents are a natural target for such augmentation, because high-quality teaching behavior depends not only on factual knowledge but also on procedures for diagnosing misconceptions, s...
Reproducibility artifact for the manuscript Evaluating LLM-Based Credit Rating Systems: A Pre-Registered Specification-Curve Analysis. A pre-registered specification-curve (multiverse) study of large-language-model credit-rating instability. From a frozen corpus of 8,640 elicitations (90-item firm-profile battery with...
The emergence of conspiracy theories in the wake of major events is a significant societal challenge. Here we test whether conversational dialogues with a large language model (LLM) can reduce belief in immediately unfolding conspiracies. In experiments conducted in the days following the July 2024 assassination attemp...
It is argued that the properties that make these models attractive - their generality, accessibility, and low deployment cost - undermine the conditions under which AI safety has historically been pursued, and safety assurance shifts from an intrinsic feature of building an AI tool to an optional add-on.
Large language models often generate confident but fabricated content, yet whether they maintain internal representations of their own epistemic states is unknown. To address this question, contrastive activation vectors were extracted for 15 epistemic states from five language models, using 100 matched present-neutral...
Supplemental materials for a study benchmarking retrieval-augmented large language models for predicting green building project cost and duration. Forty-one configurations from Anthropic, Google and OpenAI, across their reasoning-effort settings, each predicted 20 held-out Hong Kong BEAM Plus projects three times (2,46...
Whether analytic theology can supply a symbolic logical framework apt to encode moral safeguards inside LLM pipelines is investigated, which targets the engineering of moral computation: a formal language placed between metaphysical content and machine implementation.
A Blog post by NVIDIA on Hugging Face
Data Mining & Modeling
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A Blog post by IBM Granite on Hugging Face
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
