# SCOPE: Intrinsic Semantic Space Control for Mitigating Copyright Infringement in LLMs

arXiv: https://arxiv.org/abs/2511.07001 · HTML: https://mlsanity.com/paper/2511.07001/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## Builds on (most cited first, 8 of 8)

- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Deduplicating Training Data Mitigates Privacy Risks in Language Models](https://mlsanity.com/paper/2202.06539/) (2022)
- [Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models](https://mlsanity.com/paper/2411.14257/) (2024)
- [Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy](https://mlsanity.com/paper/2210.17546/) (2022)
- [Evaluating Copyright Takedown Methods for Language Models](https://mlsanity.com/paper/2406.18664/) (2024)
- [SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation](https://mlsanity.com/paper/2406.12975/) (2024)
- [SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning](https://mlsanity.com/paper/2503.22948/) (2025)

## Built on by (most cited first, 3 of 3)

- [Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation](https://mlsanity.com/paper/2512.23260/) (2025)
- [Output Vector Editing for Memorization Mitigation in Large Language Models](https://mlsanity.com/paper/2606.18767/) (2026)
- [CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMs](https://mlsanity.com/paper/2609.01161/) (2026)

## Abstract (arXiv)

Large language models sometimes inadvertently reproduce passages that are copyrighted, exposing downstream applications to legal risk. Most existing studies for inference-time defences focus on surface-level token matching and rely on external blocklists or filters, which add deployment complexity and may overlook semantically paraphrased leakage. In this work, we reframe copyright infringement mitigation as intrinsic semantic-space control and introduce SCOPE, an inference-time method that requires no parameter updates or auxiliary filters. Specifically, the sparse autoencoder (SAE) projects hidden states into a high-dimensional, near-monosemantic space; benefiting from this representation, we identify a copyright-sensitive subspace and clamp its activations during decoding. Experiments on widely recognized benchmarks show that SCOPE mitigates copyright infringement without degrading general utility. Further interpretability analyses confirm that the isolated subspace captures high-level semantics.