Large Language Model (LLM) agents are increasingly deployed in settings where they interact with diverse users, including those who are unclear, impatient, or reluctant to share information. However, collecting real interaction data at scale remains expensive. The field has turned to LLM-based \emph{user simulators} as...
Harshita Chopra, Kshitish Ghate, Aylin Caliskan et al.· 0 citations
Misaligned artificial agents might resist shutdown. One proposed solution is to train agents to lack preferences between different-length trajectories. The Discounted Reward for Same-Length Trajectories (DReST) reward function does this by penalizing agents for repeatedly choosing same-length trajectories, and thus inc...
Carissa Cullen, Harry Garland, Alexander Roman et al.· 0 citations
The alignment of Multi-Agent Systems (MAS) for autonomous software engineering is constrained by evaluator epistemic uncertainty. Current paradigms, such as Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF), frequently induce model sycophancy, while execution-based environments suffer from adver...
As AI models grow more complex, explainability is essential for building trust, yet concept-based counterfactual methods still face a trade-off between expressivity and efficiency. Representing underlying concepts as atomic sets is fast but misses relational context, whereas full graph representations are more faithful...
Angeliki Dimitriou, Nikolaos Chaidos, Maria Lymperaiou et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
What-if analysis (WIA) lets users explore hypothetical scenarios by adjusting parameters, applying constraints, and scoping data through interactive interfaces. Current tools fall short: spreadsheet and BI tools require laborious setup, while LLM-generated interfaces frequently misinterpret analytical intent. It remain...
Sneha Gathani, Sirui Zeng, Diya Patel et al.· 0 citations
Applying computational methods to law at scale requires separating genuine legal reasoning from surface similarity. We study this through a concrete task: detecting implicit citations of the French Civil Code, where a court applies a statutory rule without naming it (a post-hoc question about the reasoning a court actu...
Avrile Floro, Tamara Dhorasoo, Soline Pellez et al.· 0 citations
TeachingCoach is a pedagogically grounded chatbot designed to support instructor professional development through real-time, conversational guidance that produces clearer, more reflective, and more responsive guidance than a GPT-4o mini baseline.
Izzy Molnar, Peiyu Li, Si Chen et al.· arXiv.org· 0 citations
Structured radiology reporting promises faster, more consistent communication than free text, but automation remains difficult as models must make many fine-grained, discrete decisions about rare findings and attributes from limited structured supervision. In contrast, free-text reports are produced at scale in routine...
Chantal Pellegrini, Adrian Delchev, Ege \"Ozsoy et al.· 0 citations
LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process is poorly understood. Existing faithfulness metrics have critical limitations, typically relying on identifying unfaithfulness via adversarial prompting or detecting reasoning err...
Harry Mayne, Justin Singh Kang, Dewi Gould et al.· 0 citations
It is shown that persuasive interaction leaves a measurable, task-dependent behavioral footprint on downstream agent execution, and agents that are more susceptible to persuasive conversational context do not reliably predict the magnitude of the downstream behavioral shifts.
Hyejun Jeong, Amir Houmansadr, S. Zilberstein et al.· 0 citations
Large language models increasingly function as artificial reasoners: they evaluate arguments, assign credibility, and express confidence. Yet their responses can leave the epistemic policies governing these evaluations implicit. This paper argues for an epistemic constitution for AI: explicit, contestable meta-norms re...
Healthcare systems around the world are grappling with issues such as inefficient diagnostics, rising costs, and limited access to specialists. These challenges often contribute to delays in treatment and poorer health outcomes. Most existing AI and deep learning based health assessment systems offer limited interactiv...
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
