conftrace_

adversarial paraphrasing

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (1) text autoencoder (1) reasoning segmentation (1) hard negative mining (1) language model detoxification (1) text detoxification (1) controlled text generation (1) multimodal large language model (1) toxicity detection (1) knowledge editing (1)

Papers

SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space EACL 2026 Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models ACL 2025