New AI Defense Detects Hidden Malicious Intent in Conversations
Researchers have developed a method to spot harmful intentions hidden in multi-turn AI conversations. This helps prevent AI models from being tricked into harmful behavior over time.
Research
Research News
1035 stories curated by AInformed · page 30 of 44
New AI Dataset Helps Chatbots Know When to Speak in Group Conversations
Researchers created a dataset to teach AI when to speak in group chats, preventing interruptions. This could make AI assistants more useful in meetings and group discussions.
AI Models Can Hallucinate More When Given Perfect Information
Researchers found that AI models can make worse predictions when given accurate context. This happens because the models sometimes ignore good information. The study highlights a hidden flaw in how AI systems process data.
AI Brains Process Negative and Positive Emotions Differently
New research shows that AI models handle negative emotions in early stages and positive ones later. This could help make AI responses more emotionally balanced and nuanced.
AdaGATE: New AI Tool Improves Multi-Step Question Answering
Researchers developed AdaGATE, a new method to help AI answer complex questions that require multiple steps. It improves accuracy by selecting the most relevant information and filling in gaps automatically.
Why Fine-Tuning AI Can Make It Less Safe (And How to Fix It)
Fine-tuning AI models on even small amounts of harmless data can erase safety measures learned from much larger datasets. Researchers have identified a key mechanism behind this safety degradation, offering a way to predict and prevent it.
Why AI Alignment Tests Don't Guarantee Real-World Safety
Current AI safety tests focus on models in isolation, but a new study warns this doesn't prove real-world safety. The research argues we need to test AI in actual use cases, not just lab settings.
SWAN: A New Way to Embed Hidden Messages in AI-Generated Text
Researchers have developed a method called SWAN that embeds hidden watermarks in the meaning of sentences, not just the words. This could help track AI-generated text more effectively than current methods.
SensingAgents: AI System Improves Activity Tracking with Wearable Sensors
A new AI system called SensingAgents improves activity tracking using wearable sensors. It overcomes common challenges in recognizing daily movements like walking or running. The system could make fitness trackers and health monitoring devices more accurate and reliable.
Pro²Assist: AI Assistant That Anticipates Your Next Steps in Daily Tasks
Researchers have developed a new AI assistant called Pro²Assist that can proactively help with multi-step tasks, like cooking or assembling furniture. Unlike current assistants, it tracks your progress and predicts what you'll need next, making it more helpful for complex activities.
New AI Training Method Boosts LLM Reasoning with Adaptive Learning
Researchers have developed a new reinforcement learning technique called Adaptive Power-Mean Policy Optimization (APMPO) that improves how AI models reason. This method adapts to the evolving capabilities of large language models, making them more effective at problem-solving.
New AI Tool Extracts Rules from Data More Effectively
Researchers have developed ANDRE, a new AI system that extracts logical rules from data more effectively than previous methods. This could make AI systems more interpretable and reliable in real-world, uncertain situations.
New AI Technique Speeds Up Responses by Parallel Processing
Researchers developed a method called PARSE that makes AI responses faster by checking multiple parts of the answer at once. This could lead to quicker, more efficient AI interactions for everyday users.
New AI Memory System Outperforms Claude Code in Long-Text Tasks
Researchers have developed a new AI memory system called Lossless Context Management (LCM) that handles long texts better than Claude Code. This could make AI assistants more reliable for tasks requiring large amounts of information.
New AI Learning Method Balances Speed and Stability
Researchers have improved a technique called Emphatic TD (ETD) to make AI learning faster and more stable. This could help AI systems learn more efficiently from real-world experiences.
New AI Framework Tackles Medical Hallucinations with Word-Level Precision
Researchers have developed a framework to better detect and prevent AI-generated medical misinformation. This could make medical AI tools more reliable for everyday users.
New AI Benchmark Tests Causal Reasoning in Noisy Data
Researchers created a new test to measure how well AI systems understand cause and effect in messy, real-world data. This could help improve AI's ability to make better decisions in uncertain situations.
New AI Algorithm Lets LLMs Improve Themselves Without Human Help
Researchers developed a new AI algorithm called FREIA that helps large language models improve their reasoning skills on their own. This could lead to smarter AI assistants that learn and adapt without constant human supervision.
AI System Extracts Hidden Data from Scientific Research
Researchers have developed an AI system that can automatically extract data from scientific literature, including text, tables, and figures. This could revolutionize materials science by making it easier to build comprehensive databases.
AI Researchers Find New Reason for Time-Based Question Failures
A new study challenges the idea that AI struggles with time-based questions because of poor reasoning. Instead, it points to how the AI converts text into events as the real problem. This could lead to better AI assistants that handle schedules and timelines more accurately.
AI Moral Judgments: Does 'Thinking Mode' Change Decisions?
A new study found that AI models' moral judgments are mostly the same whether they respond instantly or take time to 'think'. The differences that do exist are concentrated in particularly tricky scenarios. This suggests that AI reasoning modes may not drastically alter ethical decisions.
AI Models Surgical Team Dynamics in Real Time for Safer Operations
Researchers have developed a new AI system that tracks and models the interactions of surgical teams in real time. This could help improve communication and coordination during operations, making surgeries safer.
AI Models Struggle with Accurate Conflict Reporting in Africa
A new study finds that AI models often produce misleading information when analyzing conflict data in West Africa. This raises concerns about their reliability for humanitarian efforts. Researchers tested both general and specialized AI models to see how well they could classify conflict events in Nigeria and Cameroon. The results show that open-source models tend to produce more false or misleading information than models specifically trained on African conflict data.
AI Models Get Better at Logical Reasoning Without Explicit Steps
Researchers found that deep AI models can perform deductive reasoning nearly as well as models that follow step-by-step logic. This could make AI smarter without needing extra instructions.