AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Category
7,776 papers
Safety auditing under compression should rely on several judges matched to the serving context rather than on keyword rates alone, because the gap is not universal and weakens under short fillers and paired SnapKV, so safety auditing should rely on several judges matched to the serving context rather than on keyword ra...
DoteBench is introduced, a bilingual evaluation suite that measures precise instruction following, local preservation, and audio quality across the four controls and their composition, while audio quality remains comparable to existing open-source systems.
The findings support evaluation practices that separate preference from safety, report safety-critical failure rates directly, and incorporate clinically grounded adjustments when ranking LLMs for clinical decision making.
Despite the growing use of large language models (LLMs) as creativity evaluators, evidence of their alignment with human evaluations remains mixed, raising the question of when and why their judgments converge with or diverge from those of humans. Across three studies and six widely used LLMs, we addressed this gap by...
Reach audiences
Advertise in front of researchers, engineers, and readers.
It is demonstrated that when producing deceptive rather than honest responses, models exhibit a gap between their belief and their commitment, which shows how confidence can be a practical tool for detecting and diagnosing deceptive behaviour in LLMs.
This paper introduces tool efficiency, a new quantitative metric to evaluate the rate of useful tool calls in an LLM agent trajectory, and determines the sign of marginal tool utility for each tool call in a trajectory using LLM-as-a-Judge.
LACUNA is introduced: the first unlearning testbed with ground-truth parameter-level localization and shows that when localization is successful, even a simple gradient-based unlearning method achieves strong erasure and robustness to resurfacing attacks, highlighting the importance of precise unlearning.
GDP-RAG is proposed, a plan-based framework that targets only the information delta based on three simple design choices, and achieves the highest accuracy among all compared systems while maintaining a cost-of-pass of 0.51.
This work presents agentic hybrid RAG, an evidence-grounded RAG framework for muon collider research, which consistently outperforms representative retrieval and RAG baselines in retrieval effectiveness, answer quality, evidence coverage, and factual grounding.
This work introduces Sci-Rho (Science Rhobustness), a dynamic benchmark for visually-grounded STEM problems spanning five subjects and seven languages, comprising 4,242 problem templates crafted by domain experts, including Olympiad medalists.
Patcher is a novel and efficient adversarial training algorithm that alternates between an attack stage and a defense stage: the attack stage simulates many-step malicious finetuning and computes the resulting parameter displacement as an"attack vector", while the defense stage aims to preserve safe behavior under such...
To study this phenomenon, SocioHack is introduced, a sandbox of 72 societal environments, and it is found that within these environments, reward hacking naturally emerges and leads to regulatory loophole discovery.
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.
