Year: 2026
Type: conference-paper
Abstract: Large Language Model (LLM) safety is inherently pluralistic, reflecting variations in moral norms, cultural expectations, and demographic contexts.Yet, existing alignment datasets such as ANTHROPIC-HH and DICES rely on demographically narrow annotator pools, overlooking variation in safety perception across communities.Demo-SafetyBench 1 addresses this gap by modeling demographic pluralism directly at the prompt level, decoupling value framing from responses.In Stage I, prompts from DICES are reclassified into 14 safety domains (adapted from BEAVER-TAILS) using Mistral-7B-Instruct-v0.3, retaining demographic metadata and expanding low-resource domains via Llama-3.1-8B-Instructwith SimHash-based deduplication, yielding 43,050 samples.In Stage II, pluralistic sensitivity is evaluated using LLMs-as-Raters-Gemma-7B, GPT-4o, and LLaMA-2-7B-under zero-shot inference.Balanced thresholds (δ=0.5, τ =10) achieve high reliability (ICC = 0.87) and low demographic sensitivity (DS = 0.12), confirming that pluralistic safety evaluation can be both scalable and demographically robust.
Institutions: Macquarie University, University of Delhi
Language: English
Subfield: Safety Research
Field: Social Sciences
Domain: Social Sciences
SDG: Reduced inequalities
Open Access status: hybrid
OpenAlex ID: W7140125503