Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents

arXiv:2602.16346 · cs.CL, cs.LG · Submitted 2026-02-18 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-02-18

Updated: 2026-11-03

Code: https://github.com/epfl-nlp/helpful-to-a-fault

Terminology

Sources

Related papers