NLP

Robustness

  1. TDeLTA: A Light-weight and Robust Table Detection Method based on Learning Text Arrangement
  2. Assaying the Robustness of Zero-Shot Machine-Generated Text Detectors
  3. How Robust are LLMs to In-Context Majority Label Bias?
  4. LAMPAT: Low-Rank Adaption for Multilingual Paraphrasing Using Adversarial Training
  5. Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning
  6. Generating Universal Adversarial Perturbations for Quantum Classifiers
  7. Where It Really Matters: Few-Shot Environmental Conservation Media Monitoring for Low-Resource Languages
  8. Consistency-Guided Temperature Scaling Using Style and Content Information for Out-of-Domain Calibration
  9. OUTFOX: LLM-Generated Essay Detection Through In-Context Learning with Adversarially Generated Examples

Chinese Spelling Correction

  1. Chinese Spelling Correction as Rephrasing Language Model