一作ACL 2026Poster· ACL Industry Track
F in H arm B ench: Financial Jailbreak Benchmark and Unsupervised Safety Fine-Tuning via Refusal Steering Distillation
Yubin Choi · Yujin Yang · Subin Kim · Seokil Ham · Seungju Cho · Jungmin Son · Youngjun Kwak · Changick Kim
摘要
Financial Large Language Models (LLMs) exhibit strong domain expertise but remain vulnerable to financially harmful prompts. To systematically assess this vulnerability, we introduce FinHarmBench , a benchmark designed to evaluate financially harmful and confusable benign prompts. Our analysis re...