← back to paper

Review history

arxiv: 2608.04286 · 2 revisions

Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attacks

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
   127810 ms 20583 in 16040 out 2026-08-15T14:40:54.424542+00:00
2. 2026-08-08 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
   138103 ms 20588 in 16108 out 2026-08-08T00:05:22.984831+00:00