Related papers: A Dynamic Logic for Information Evaluation in Inte…

Traditionally, an agent's beliefs would come from what the agent can see, hear, or sense. In the modern world, beliefs are often based on the data available to the agents. In this work, we investigate a dynamic logic of such beliefs that…

Step-by-step reasoning is widely used to enhance the reasoning ability of large language models (LLMs) in complex problems. Evaluating the quality of reasoning traces is crucial for understanding and improving LLM reasoning. However,…

This paper primarily demonstrates a method to quantitatively assess the alignment between multi-step, structured reasoning in large language models and human preferences. We introduce the Alignment Score, a semantic-level metric that…

Since Artificial Intelligence (AI) software uses techniques like deep lookahead search and stochastic optimization of huge neural networks to fit mammoth datasets, it often results in complex behavior that is difficult for people to…

In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still violate logical or evidential constraints, allowing…

Information security plays a significant role in recent information society. Increasing number and impact of cyber attacks on information assets have resulted the increasing awareness among managers that attack on information is actually…

Large language models (LLMs) are increasingly used in social science simulations. While their performance on reasoning and optimization tasks has been extensively evaluated, less attention has been paid to their ability to simulate human…

While the existence of many security elements can be measured (e.g., vulnerabilities, security controls, or privacy controls), it is challenging to measure their relative security impact. In the physical world we can often measure the…

Reliability and failure detection of large language models (LLMs) is critical for their deployment in high-stakes, multi-step reasoning tasks. Prior work explores confidence estimation for self-evaluating LLM-scorer systems, with confidence…

As intelligent systems become more autonomous, the scientific community focuses on creating decision-making mechanisms that include ethical and moral considerations, unlike traditional utility-maximisation models. To achieve this, a key…

Recent advancements in large language models (LLMs) have demonstrated their potential in automating the scientific research ideation. Existing approaches primarily focus on prompting techniques, often producing ideas misaligned with expert…

The Department of Defense (DoD) has significantly increased its investment in the design, evaluation, and deployment of Artificial Intelligence and Machine Learning (AI/ML) capabilities to address national security needs. While there are…

Large language models (LLMs) are increasingly used as raters for evaluation tasks. However, their reliability is often limited for subjective tasks, when human judgments involve subtle reasoning beyond annotation labels. Thinking traces,…

The Uniform Information Density (UID) hypothesis proposes that effective communication is achieved by maintaining a stable flow of information. In this work, we revisit this principle in the context of Large Language Model (LLM) reasoning,…

While multi-agent LLM systems show strong capabilities in various domains, they are highly vulnerable to adversarial and low-performing agents. To resolve this issue, in this paper, we introduce a general and adversary-resistant multi-agent…

Large Language Model-based Multi-Agent Systems (LLM-MAS) have demonstrated strong capabilities in solving complex tasks but remain vulnerable when agents receive unreliable messages. This vulnerability stems from a fundamental gap: LLM…

There has been increasing interest in evaluations of language models for a variety of risks and characteristics. Evaluations relying on natural language understanding for grading can often be performed at scale by using other language…

Intelligence analysts' roles include analyzing reports, identifying important information relevant to the current state of affairs, and communicating their takeaways. These reports are then analyzed and reported to decision-makers or…

Clinical personality assessment screens response validity before interpreting substantive scales. LLM evaluation does not. We apply the validity scaling framework from the PAI and MMPI-3 to metacognitive probe data from 20 frontier models…

The traditional evaluation of information retrieval (IR) systems is generally very costly as it requires manual relevance annotation from human experts. Recent advancements in generative artificial intelligence -- specifically large…