Category
7,776 papers
PACT is proposed, which turns this structure into four training terms that need no new annotation: a difference-in-differences margin over each pair that is invariant to any shared logit offset, a permutation-consistency term against answer-code position bias, an evidence-necessity term on certificate-verified ablated...
These findings show that aggregate detection metrics conceal persistent, model dependent heterogeneity in language model failures and motivate regime conditioned evaluation.
Intrinsic self-correction asks a language model to revise its own answer without receiving new external evidence. A second pass can recover mistakes, but it can also overturn answers that were already correct. We study this trade-off across 29 open-weight LLMs on BoolQ, GSM8K, and Corr2Cause by tracking correctness tra...
Across 4,500 full-duplex calls and five voice configurations, Spanish, Portuguese, and Hindi remain within 3.2 task-completion points of English, but Korean and Mandarin fall by 14.7 and 8.4 points, respectively.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Although uniform diffusion language models (UDLMs) represent a promising diffusion paradigm, scaling them remains challenging. We identify the core obstacle as an over-uniform training objective and condition-target confusion during sampling. To address these, we propose Less Uniform Diffusion (LUDI), a novel UDLM fram...
Large language model search agents are often trained with synthetic questions whose difficulty is increased through larger evidence graphs, additional hops, and longer trajectories. These global properties, however, are only indirect proxies for the local retrieval capabilities required during search. To address this m...
To help researchers understand how to run statistics over LLM judges responsibly, guidance and tooling for the statistical analysis of mixed human-AI judge designs are presented, and recommendations for what CI, p-value, and FWER correction methods to use for small-sample AI evaluations are derived, and researchers are...
This paper evaluates six strong browser-use agents, three GUI-only agents that see only screenshots, and humans, evaluating the construction of challenging instances from tasks agents already solve, turning difficulty into a programmable property of the environment.
Neighbor information improves individual prediction in all 16 public-data settings and pooled collective forecasts on held-out questions, although collective gains depend on transfer conditions.
Lookahead-R is proposed, a planning-based framework that reformulates tool retrieval as a resource-constrained sequential decision-making problem that introduces a lightweight execution-aware surrogate world model that jointly predicts tool execution success, latency cost, and semantic utility—without invoking real API...
TRACE is presented, a deployable tree-relational enhancement framework for oncology LLMs that separates expensive offline structure learning from lightweight online inference, and suggests that explicit, updatable medical structure is a practical path toward more accurate and auditable oncology LLM deployment.
A multi-agent framework in which a story agent, an image agent, and a critic agent collaborate to produce fake social media posts that plausibly counter true news is introduced, providing a foundation for developing robust defenses against social media fake news.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
A Blog post by Liquid AI on Hugging Face
Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking are our most advanced live dialogue models yet, built for natural conversation.
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
