TrustNLP 2027 heads to Macau, co-located with COLING, papers due Jan 5
kaiwei_chang · x · 2026-11-10
The 7th TrustNLP workshop moves to Asia for the first time, co-located with COLING 2027 in Macau, China (May 2027), with papers due January 5, 2027.
- Topics include privacy-preserving training, unlearning and model editing, fairness and bias, explainability, culturally-aware LLMs, safety and robustness, red-teaming/backdoor/adversarial attacks, ethics and dual-use, and causal inference
- The workshop continues its mentorship and diversity mission; keynotes to be announced
More from Research
- How AA-3D Works: Models as Agents in Sandboxes Building 3D Scenes — ArtificialAnlys · 2026-11-10
- System 1/2 thinking is popsci oversimplification, but it inspires real AI architectures — burny_tech · 2026-11-10
- arXiv hits 42K new papers in October, up 81% since January — burny_tech · 2026-11-10
- PSI-Bench shows purpose-built patient simulators beat assistant LLMs at modeling depression — alexisjross · 2026-11-10
- Microsoft FORGE Lab uses agentic AI tools to find memory-safety bugs in Rust core libs — jedisct1 · 2026-11-10
- Holon-S1, never trained on osteosarcoma, still matched the real treatment target — iScienceLuvr · 2026-11-10