LLMs displaying less cognitive bias are not necessarily better decision makers
Nature Machine Intelligence, Published online: 17 March 2026; doi:10.1038/s42256-026-01208-w Large language models (LLMs) include not only social stereotypes but also…
Auditing Student-AI Collaboration: A Case Study of Online Graduate CS Students
arXiv:2601.08697v4 Announce Type: replace-cross Abstract: As generative AI becomes embedded in higher education, it increasingly shapes how students complete academic…
Maximum Entropy Exploration Without the Rollouts
arXiv:2603.12325v1 Announce Type: cross Abstract: Efficient exploration remains a central challenge in reinforcement learning, serving as a useful pretraining objective…
TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Prediction
arXiv:2603.12500v1 Announce Type: cross Abstract: We present a Temporal Rule-Anchored Chain-of-Evidence (TRACE) on knowledge graphs for interpretable stock movement prediction…
Shattering the Shortcut: A Topology-Regularized Benchmark for Multi-hop Medical Reasoning in LLMs
arXiv:2603.12458v1 Announce Type: cross Abstract: While Large Language Models (LLMs) achieve expert-level performance on standard medical benchmarks through single-hop factual…
Human-Centered Evaluation of an LLM-Based Process Modeling Copilot: A Mixed-Methods Study with Domain Experts
arXiv:2603.12895v1 Announce Type: cross Abstract: Integrating Large Language Models (LLMs) into business process management tools promises to democratize Business Process…
One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies
arXiv:2603.12480v1 Announce Type: cross Abstract: Generative flow and diffusion models provide the continuous, multimodal action distributions needed for high-precision robotic…
Context-Enriched Natural Language Descriptions of Vessel Trajectories
arXiv:2603.12287v1 Announce Type: new Abstract: We address the problem of transforming raw vessel trajectory data collected from AIS into structured…
Proof-Carrying Materials: Falsifiable Safety Certificates for Machine-Learned Interatomic Potentials
arXiv:2603.12183v2 Announce Type: replace-cross Abstract: Machine-learned interatomic potentials (MLIPs) are deployed for high-throughput materials screening without formal reliability guarantees. We…
Team RAS in 10th ABAW Competition: Multimodal Valence and Arousal Estimation Approach
arXiv:2603.13056v1 Announce Type: cross Abstract: Continuous emotion recognition in terms of valence and arousal under in-the-wild (ITW) conditions remains a…