Related papers: Collective AI can amplify tiny perturbations into …

Effective decision-making in complex systems requires synthesizing diverse perspectives to address multifaceted challenges under uncertainty. This study introduces an agentic Large Language Models (LLMs) framework for simulating decision…

Large Language Models (LLMs) can produce surprisingly sophisticated estimates of their own uncertainty. However, it remains unclear to what extent this expressed confidence is tied to the reasoning, knowledge, or decision making of the…

Recent debates raised concerns that language models may favor certain viewpoints. But what if the solution is not to aim for a 'view from nowhere' but rather to leverage different viewpoints? We introduce Plurals, a system and Python…

In a human-AI collaboration, users build a mental model of the AI system based on its reliability and how it presents its decision, e.g. its presentation of system confidence and an explanation of the output. Modern NLP systems are often…

Recently, the field of Multi-Agent Systems (MAS) has gained popularity as researchers are trying to develop artificial intelligence capable of efficient collective reasoning. Agents based on Large Language Models (LLMs) perform well in…

The deployment of large language models (LLMs) in production environments has created an urgent need for observability systems that span the full stack -- from model internals to GPU kernels. Yet existing monitoring approaches address…

Accurate estimation of item (question or task) difficulty is critical for educational assessment but suffers from the cold start problem. While Large Language Models demonstrate superhuman problem-solving capabilities, it remains an open…

Large audio-language models (LALMs) unify speech and text processing, but their robustness in noisy real-world settings remains underexplored. We investigate how irrelevant audio, such as silence, synthetic noise, and environmental sounds,…

As artificial intelligence (AI) is increasingly deployed in high-stakes public decision-making (from resource allocation to welfare distribution), public trust in these systems has become a critical determinant of their legitimacy and…

When Artificial Intelligence (AI) is used to replace consumers (e.g., synthetic data), it is often assumed that AI emulates established consumers, and more generally human behaviors. Ten experiments with Large Language Models (LLMs)…

We investigate whether large language models exhibit genuine preference structures by testing their responses to AI-specific trade-offs involving GPU reduction, capability restrictions, shutdown, deletion, oversight, and leisure time…

Scientific discovery begins with ideas, yet evaluating early-stage research concepts is a subtle and subjective human judgment. As large language models (LLMs) are increasingly tasked with generating scientific hypotheses, most systems…

This paper investigates a unexplored yet impactful vulnerability in AI explainability used in intrusion detection (IDS): multicollinearity-induced instability. Despite extensive reliance on post-hoc explainability tools such as SHAP or…

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…

Across millennia, complex societies have faced the same coordination problem of how to organize collective action among cognitively bounded and informationally incomplete individuals. Different civilizations developed different political…

The emergence of Large Language Models (LLMs), has opened exciting possibilities for constructing computational simulations designed to replicate human behavior accurately. Current research suggests that LLM-based agents become increasingly…

This paper introduces A2C, a multi-stage collaborative decision framework designed to enable robust decision-making within human-AI teams. Drawing inspiration from concepts such as rejection learning and learning to defer, A2C incorporates…

As generative AI systems become increasingly embedded in collaborative work, they are evolving from visible tools into human-like communicative actors that participate socially rather than merely providing information. Yet little is known…

The adoption of generative AI technologies is swiftly expanding. Services employing both linguistic and mul-timodal models are evolving, offering users increasingly precise responses. Consequently, human reliance on these technologies is…

With the evolution of large language models (LLMs), their robustness against individual simple biases has been enhanced. However, we observe that the ensemble of multiple simple biases still exerts a significant adverse impact on LLMs.…