238 stories tagged LLMs · page 2 of 10
Researchers developed a way to measure the quality of written explanations using AI. They analyzed over 55,000 predictions from a forecasting tournament and found patterns that help assess how well people justify their decisions. This could improve how we evaluate expert opinions and AI reasoning alike.
Researchers have introduced Yuvion, a large language model specifically built to handle adversarial attacks. This could make AI systems safer by preventing harmful or misleading outputs, especially in scenarios involving planning, tool use, and multi-step reasoning.
Researchers developed a new method to improve AI's ability to plan complex tasks. This could make AI assistants more reliable for long-term decision-making.
Researchers created a new benchmark called DiscoBench to evaluate how well AI search tools ask clarifying questions when users' requests are unclear, vague, or even factually incorrect. This helps AI assistants avoid cascading errors in multi-step searches.
A new position paper argues that the term 'machine unlearning' is overused in LLM research. It should be reserved for precisely removing the influence of a specific dataset from a model. Many current applications of the term are misleading and dilute its meaning. (2026-06-29)
Researchers introduced ContextForge, a system that helps large language models maintain relevant information across long conversations by recycling context instead of replaying entire histories. This could slash token usage and improve multiturn reasoning.
Researchers evaluated AI agents on complex energy market tasks, including live data retrieval, regulatory knowledge, and multi-step quantitative reasoning. The study fills a critical gap, with 243 expert-designed tasks showing how tool-augmented LLMs could make energy systems more efficient and responsive.
OpenAI and Broadcom have introduced Jalapeño, a custom AI chip built specifically for LLM inference. The chip aims to improve performance, efficiency, and scalability of AI systems, potentially making AI tools faster and more cost-effective for everyday users.
Researchers developed a method using large language models to automatically generate challenging test problems for AI reasoning. This could lead to better evaluations of AI's ability to apply knowledge to new, harder tasks.
Apple researchers found a single parameter in AI models that can dramatically change how they behave. This discovery could make AI more predictable and easier to control.
Scientists developed a new method using Shapley values to measure how adjectives influence AI responses. Their findings reveal how small word choices can significantly impact AI performance and alignment.
Researchers developed PeerCheck, a system to enhance AI-generated academic reviews toward human-level quality. It addresses challenges in the traditional peer review process as academic submissions grow.
Researchers have identified key ways AI models fail when translating programming logic into hardware design. The findings highlight a 90.8% success rate ceiling for current models, with specific types of errors limiting their effectiveness.
Researchers have developed TreeTracer, a visual analytics tool that reveals hidden biases in AI language models by analyzing multiple possible outputs instead of just one. This approach uncovers representational and syntactic biases that standard auditing methods miss, making AI fairness assessment more thorough.
Researchers found that large language models (LLMs) often overestimate their confidence when analyzing medical data. The study suggests new methods to help AI recognize what it doesn't know, improving reliability in healthcare applications.
Researchers have developed a method that lets AI models review and correct their own outputs for ethical alignment, using a new 'conscience step' technique. This could improve AI safety in training, fine-tuning, and real-time use.
Researchers created a benchmark to test if AI models can handle complex executive decisions. The study simulates real-world leadership challenges, like balancing conflicting advice and managing resources under constraints.
Researchers developed an AI system that translates natural language queries into requests for satellite imagery and environmental data. This could make complex geospatial data more accessible to non-experts.
Researchers introduced ToolSense, a diagnostic framework for auditing parametric tool knowledge in LLMs. It helps AI agents select tools more accurately by encoding each tool as a virtual token and fine-tuning the model in two stages, outperforming traditional embedding-based retrieval on standard benchmarks.
Researchers developed a method to predict when AI assistants in healthcare might fail. This could make clinical AI tools safer and more reliable for doctors and patients. The study analyzed real-world use of AI in electronic health records to identify risky responses before they happen.
A new study shows AI agents work better when they focus on recent, relevant information instead of keeping full conversation histories. This could make business AI tools faster and more reliable. Researchers tested this with expense-processing tasks in Microsoft Dynamics 365.
Researchers developed a new memory system called Engram that improves AI accuracy by focusing on relevant information rather than full history. This could make AI assistants faster and more precise in their responses.
Researchers developed a new AI system that uses large language models to optimize mine scheduling. This could make mining operations more efficient and adaptable to real-time changes.
Researchers developed a system that helps AI models save effort by quickly deciding whether a problem needs deep thought. This could make AI tools faster and more efficient for everyday users.