pith. sign in

Zheng-Xin Yong

Identifiers

  • name variant Zheng-Xin Yong 0.60 · backfill

Papers (6)

  1. An Independent Safety Evaluation of Kimi K2.5 cs.CR · 2026 · author #1
  2. Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training cs.CR · 2025 · author #1
  3. Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling cs.CL · 2025 · author #4
  4. Humanity's Last Exam cs.LG · 2025 · author #493
  5. Low-Resource Languages Jailbreak GPT-4 cs.CL · 2023 · author #1
  6. BLOOM: A 176B-Parameter Open-Access Multilingual Language Model cs.CL · 2022 · author #166

Mentions

  • 2310.02446 #1 · arxiv_oai · confidence 0.70 Zheng-Xin Yong

Frequent Coauthors