REALISTA optimizes continuous combinations of valid editing directions in latent space to produce realistic adversarial prompts that elicit hallucinations more effectively than prior methods, including on large reasoning models.
and Sudderth, Erik B
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
Local LMO is a new projection-free method that achieves the convergence rates of projected gradient descent for constrained optimization by using local linear minimization oracles over small balls.
Joint resource allocation and routing for multi-model LLM serving can produce up to 87% variation in achievable output quality across setups on the same GPU cluster.
Sticky factorial HDP-HMMs applied to multimodal valence-arousal trajectories identify interpretable persistent emotional regimes in conversations, outperforming Gaussian HMM baselines in consistency metrics and enabling context-augmented LLM responses.
A feedback-based dynamic pricing framework reduces peak demand and load variation in simulated distribution networks with hundreds of automated home energy management systems controlling HVAC, batteries, and flexible loads.
citing papers explorer
-
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
REALISTA optimizes continuous combinations of valid editing directions in latent space to produce realistic adversarial prompts that elicit hallucinations more effectively than prior methods, including on large reasoning models.
-
Local LMO: Constrained Gradient Optimization via a Local Linear Minimization Oracle
Local LMO is a new projection-free method that achieves the convergence rates of projected gradient descent for constrained optimization by using local linear minimization oracles over small balls.
-
RouterWise: Joint Resource Allocation and Routing for Latency-Aware Multi-Model LLM Serving
Joint resource allocation and routing for multi-model LLM serving can produce up to 87% variation in achievable output quality across setups on the same GPU cluster.
-
Multimodal Hidden Markov Models for Persistent Emotional State Tracking
Sticky factorial HDP-HMMs applied to multimodal valence-arousal trajectories identify interpretable persistent emotional regimes in conversations, outperforming Gaussian HMM baselines in consistency metrics and enabling context-augmented LLM responses.
-
Unlocking Deep Demand Flexibility via Dynamic Signals
A feedback-based dynamic pricing framework reduces peak demand and load variation in simulated distribution networks with hundreds of automated home energy management systems controlling HVAC, batteries, and flexible loads.