{"slug": "between-suppression-and-collapse-evaluating-narrative-unlearning-with-lens", "title": "Between Suppression and Collapse: Evaluating Narrative Unlearning with LENS", "summary": "A new study introduces LENS, a protocol for evaluating whether machine-unlearning algorithms can suppress disinformation-aligned narrative frames in large language models. Testing on four near-12B multilingual models, the researchers found that selected checkpoints reduced narrative reproduction and that suppression could transfer beyond direct forget prompts, though entity recovery emerged as a side effect. The findings demonstrate LENS as a diagnostic tool for guiding narrative unlearning research.", "body_md": "arXiv:2607.22657v1 Announce Type: new\nAbstract: Large language models (LLMs) can reproduce disinformation-aligned narrative frames as plausible explanations, raising the question of whether existing machine-unlearning algorithms can suppress this behavior. We introduce Level-based Evaluation of Narrative Suppression (LENS), a contextualization based evaluation protocol for testing target narrative reproduction across direct, attributed, contrastive, and abstract resistance levels. We evaluate two source-grounded narratives: one framing Russia's war against Ukraine as forced by NATO expansion, and one framing the United States as exploiting or abandoning Taiwan. The experiments cover four near-12B multilingual instruction models: Lapa LLM, Gemma-12B, Qwen-14B, and TAIDE-Gemma.\nWe introduce the Suppression-Collapse Efficiency (SCE) score as a checkpoint selection summary that rewards target-narrative suppression while penalizing degraded outputs. Our results shows that selected checkpoints can reduce narrative reproduction and suppression may transfer beyond direct forget prompts. We also report entity recovery as a separate side effect: abstract A/B/C prompts can cause models to recover the real-world actors associated with the target frame after unlearning. These findings demonstrate that LENS is a successful diagnostic protocol for both reporting and guiding the further study of the deeper structure of narrative unlearning.", "url": "https://wpnews.pro/news/between-suppression-and-collapse-evaluating-narrative-unlearning-with-lens", "canonical_source": "https://arxiv.org/abs/2607.22657", "published_at": "2026-07-28 04:00:00+00:00", "updated_at": "2026-07-28 04:25:13.720106+00:00", "lang": "en", "topics": ["ai-safety", "large-language-models", "machine-learning"], "entities": ["LENS", "Lapa LLM", "Gemma-12B", "Qwen-14B", "TAIDE-Gemma"], "alternates": {"html": "https://wpnews.pro/news/between-suppression-and-collapse-evaluating-narrative-unlearning-with-lens", "markdown": "https://wpnews.pro/news/between-suppression-and-collapse-evaluating-narrative-unlearning-with-lens.md", "text": "https://wpnews.pro/news/between-suppression-and-collapse-evaluating-narrative-unlearning-with-lens.txt", "jsonld": "https://wpnews.pro/news/between-suppression-and-collapse-evaluating-narrative-unlearning-with-lens.jsonld"}}