Researchers have developed a method to modify a learned world model's behavior by making targeted changes to its hidden state. In a controlled environ...
Researchers have proposed a new framework called RUPA (Relational Uncertainty Propagation for Agents) to improve uncertainty quantification in large l...
Researchers have developed a neurosymbolic agent that can perform household tasks by combining visual exploration and symbolic planning. The agent use...
Researchers have developed a new attack method called Environment State-Text Injection (ESTI) that targets large language model-driven embodied agents...
Researchers have created a new benchmark called LongNovel to detect hallucinations in long-context novel summarization. Hallucinations occur when AI s...
Researchers evaluated how well both humans and large language models can track entities in naturalistic narratives. They found that human performance ...
Researchers from Hangfeng He and colleagues propose a new framework for theorem proving in real-world projects using Lean 4. The framework balances ex...
Researchers have developed a framework for task-oriented dialogue systems that can adapt to the user's personality while completing tasks. They tested...
Researchers have developed a framework called MAVEN to evaluate whether multimedia content aligns with societal values such as peace and justice. The ...
Researchers have created a benchmark for classifying French news articles from different publishers. The FrenchNews-7 benchmark combines a large corpu...
Researchers have developed BERTilda, a framework for tracking topic lifecycles in longitudinal text streams. This involves identifying how topics spli...
Researchers have developed a new method for detecting machine-generated text called Pattern Stability Score (PSS). This approach uses local statistica...