pith. sign in

Zhen Xiang

Identifiers

  • name variant Zhen Xiang 0.60 · backfill

Papers (10)

  1. Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs cs.AI · 2026 · author #8
  2. Crafting Reversible SFT Behaviors in Large Language Models cs.LG · 2026 · author #8
  3. Green Shielding: A User-Centric Approach Towards Trustworthy AI cs.CL · 2026 · author #7
  4. IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review cs.IR · 2026 · author #8
  5. ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems cs.AI · 2026 · author #3
  6. Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models cs.CR · 2026 · author #5
  7. RealRoute: Dynamic Query Routing System via Retrieve-then-Verify Paradigm cs.IR · 2026 · author #6
  8. SoSBench: Benchmarking Safety Alignment on Six Scientific Domains cs.LG · 2025 · author #10
  9. GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning cs.LG · 2024 · author #1
  10. A Mixture Model Based Defense for Data Poisoning Attacks Against Naive Bayes Spam Filters cs.CR · 2018 · author #3

Mentions

  • 2605.24154 #8 · arxiv_oai · confidence 0.70 Zhen Xiang
  • 2406.09187 #1 · arxiv_oai · confidence 0.70 Zhen Xiang
  • 2605.06632 #8 · backfill · confidence 0.70 Zhen Xiang

Frequent Coauthors