# Between Suppression and Collapse: Evaluating Narrative Unlearning with LENS

arXiv: https://arxiv.org/abs/2607.22657 · HTML: https://mlsanity.com/paper/2607.22657/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 27 Jun 2026.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 16 of 16)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning](https://mlsanity.com/paper/2403.03218/) (2024)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.10512/) (2023)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [Data Programming: Creating Large Training Sets, Quickly](https://mlsanity.com/paper/1605.07723/) (2016)
- [Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples](https://mlsanity.com/paper/2510.07192/) (2025)
- [Model Editing by Standard Fine-Tuning](https://mlsanity.com/paper/2402.11078/) (2024)
- [Probing Knowledge Holes in Unlearned LLMs](https://mlsanity.com/paper/2511.00030/) (2025)

## Abstract (arXiv)

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. We 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.