Related papers: Thought Virus: Viral Misalignment via Subliminal P…
Automating scientific computing workflows requires more than generating executable code: autonomous systems must also select appropriate computational strategies, implement them faithfully, and ensure that the resulting outcomes remain…
Large language models (LLMs) have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through…
Large Language Models (LLMs) leverage chain-of-thought (CoT) prompting to provide step-by-step rationales, improving performance on complex tasks. Despite its benefits, vanilla CoT often fails to fully verify intermediate inferences and can…
Large Language Models have garnered significant attention for their capabilities in multilingual natural language processing, while studies on risks associated with cross biases are limited to immediate context preferences. Cross-language…
We examine how misinformation spreads in social networks composed of individuals with long-term offline relationships. Especially, we focus on why misinformation persists and diffuses despite being recognized by most as false. In our…
Different from traditional task-specific vision models, recent large VLMs can readily adapt to different vision tasks by simply using different textual instructions, i.e., prompts. However, a well-known concern about traditional…
Emergent multi-agent communication protocols are very different from natural language and not easily interpretable by humans. We find that agents that were initially pretrained to produce natural language can also experience detrimental…
Disinformation campaigns can distort public perception and destabilize institutions. Understanding how different populations respond to information is crucial for designing effective interventions, yet real-world experimentation is…
One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a task or provide a correct answer to a question can depend unpredictably on the way the…
Large language models (LLMs) offer unprecedented opportunities for analyzing social phenomena at scale. This paper demonstrates the value of LLMs in psychological measurement by (1) compiling the first large-scale dataset of election rumors…
Semantic communication enhances transmission efficiency by conveying semantic information rather than raw input symbol sequences. Task-oriented semantic communication is a variant that tries to retains only task-specific information, thus…
Misinformation is on the rise, and the strong writing capabilities of LLMs lower the barrier for malicious actors to produce and disseminate false information. We study how LLMs behave when prompted to spread misinformation across languages…
Multi-agent systems - systems with multiple independent AI agents working together to achieve a common goal - are becoming increasingly prevalent in daily life. Drawing inspiration from the phenomenon of human group social influence, we…
The continued improvements in language model capability have unlocked their widespread use as drivers of autonomous agents, for example in coding or computer use applications. However, the core of these systems has not changed much since…
The rapid proliferation of recent Multi-Agent Systems (MAS), where Large Language Models (LLMs) and Large Reasoning Models (LRMs) usually collaborate to solve complex problems, necessitates a deep understanding of the persuasion dynamics…
Persistent language-model agents increasingly combine tool use, tiered memory, reflective prompting, and runtime adaptation. In such systems, behavior is shaped not only by current prompts but by mutable internal conditions that influence…
Large language model (LLM)-powered agents are increasingly used in recommender systems (RSs) to achieve personalized behavior modeling, where the memory mechanism plays a pivotal role in enabling the agents to autonomously explore, learn…
Large Language Models (LLMs) and multi-agent systems have shown impressive capabilities in natural language tasks but face challenges in clinical trial applications, primarily due to limited access to external knowledge. Recognizing the…
Detecting biases in the outputs produced by generative models is essential to reduce the potential risks associated with their application in critical settings. However, the majority of existing methodologies for identifying biases in…
Recent advances in embodied Vision-Language Agentic Systems (VLAS), powered by large vision-language models (LVLMs), enable AI systems to perceive and reason over real-world scenes. Within this context, environmental signals such as traffic…