REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-source and reasoning LLMs.
Title resolution pending
2 Pith papers cite this work, alongside 3 external citations. Polarity classification is still indexing.
2
Pith papers citing it
3
external citations · external index
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Binary rewards make the set of reward-maximizing policies infinite in policy gradients; KL control selects the filtered base model but misspecification drives collapse to concentrated valid outputs instead.
citing papers explorer
-
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-source and reasoning LLMs.
-
Binary Rewards and Reinforcement Learning: Fundamental Challenges
Binary rewards make the set of reward-maximizing policies infinite in policy gradients; KL control selects the filtered base model but misspecification drives collapse to concentrated valid outputs instead.