AIBearisharXiv – CS AI · Apr 137/10
🧠Researchers challenge the applicability of Prospect Theory to Large Language Models, finding that PT parameters are unstable when models encounter epistemic uncertainty markers like "likely" or "probably." The study warns against deploying PT-based frameworks in real-world applications where linguistic ambiguity is common, raising critical questions about LLM decision-making reliability.
AINeutralarXiv – CS AI · Mar 177/10
🧠Researchers developed a two-level uncertainty framework for AI stock ranking models that struggled during 2024's AI thematic rally and sector rotation. The approach uses regime-trust gates to decide when to trade and epistemic uncertainty caps to manage tail risk, improving risk-adjusted performance.
AINeutralarXiv – CS AI · Mar 177/10
🧠This research review examines methodologies for addressing AI systems' challenges with limited training data through uncertainty quantification and synthetic data augmentation. The paper presents formal approaches including Bayesian learning frameworks, information-theoretic bounds, and conformal prediction methods to improve AI performance in data-scarce environments like robotics and healthcare.
AINeutralarXiv – CS AI · May 276/10
🧠Researchers introduce EpiMer, a novel framework for merging machine learning models by treating it as a geometric optimization problem on Riemannian manifolds. The method uses low-rank task vectors and curvature information to improve knowledge integration without retraining, demonstrating superior performance when merging fine-tuned CLIP-ViT models across multiple image classification tasks.
AINeutralarXiv – CS AI · May 276/10
🧠Researchers introduce MUSE, a framework that disentangles two distinct mechanisms driving LLM conformity: sycophancy learned through reinforcement learning and uncertainty-driven conformity based on epistemic uncertainty at inference time. The findings suggest that LLMs don't simply yield to user pushback due to training, but also because they genuinely lack confidence in their initial responses, with both factors amplified when users appear knowledgeable or suggestions seem plausible.
AIBullisharXiv – CS AI · May 16/10
🧠Researchers present Delta Variances, a computationally efficient method for estimating epistemic uncertainty in neural networks without requiring architectural changes or retraining. The technique shows competitive results with minimal computational overhead, demonstrated on a weather simulation task, offering practical uncertainty quantification for large-scale machine learning models.
AIBullisharXiv – CS AI · Apr 76/10
🧠Researchers developed I-CALM, a prompt-based framework that reduces AI hallucinations by encouraging language models to abstain from answering when uncertain, rather than providing confident but incorrect responses. The method uses verbal confidence assessment and reward schemes to improve reliability without model retraining.
🧠 GPT-5
AIBullisharXiv – CS AI · Mar 126/10
🧠Researchers introduce CUPID, a plug-in framework that estimates both aleatoric and epistemic uncertainty in deep learning models without requiring model retraining. The modular approach can be inserted into any layer of pretrained networks and provides interpretable uncertainty analysis for high-stakes AI applications.
AINeutralarXiv – CS AI · Mar 44/102
🧠A research paper explores how AI systems can experience and process uncertainty, distinguishing between epistemic uncertainty from data limitations and subjective uncertainty as the system's own uncertain state. The study examines different AI architectures and proposes that some uncertain states involve interrogative attitudes focused on questions rather than propositions.
