# Can LLMs get help from other LLMs without revealing private information?

arXiv: https://arxiv.org/abs/2404.01041 · HTML: https://mlsanity.com/paper/2404.01041/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 1 Apr 2024.

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Prompt Injection attack against LLM-integrated Applications](https://mlsanity.com/paper/2306.05499/) (2023)
- [Are Emergent Abilities of Large Language Models a Mirage?](https://mlsanity.com/paper/2304.15004/) (2023)
- [SentEval: An Evaluation Toolkit for Universal Sentence Representations](https://mlsanity.com/paper/1803.05449/) (2018)
- [The Tatoeba Translation Challenge -- Realistic Data Sets for Low Resource and Multilingual MT](https://mlsanity.com/paper/2010.06354/) (2020)
- [Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems](https://mlsanity.com/paper/2312.15234/) (2023)
- [Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models](https://mlsanity.com/paper/2302.00618/) (2023)
- [Privacy-Preserving In-Context Learning for Large Language Models](https://mlsanity.com/paper/2305.01639/) (2023)
- [CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade](https://mlsanity.com/paper/2012.14682/) (2020)
- [Social Learning: Towards Collaborative Learning with Large Language Models](https://mlsanity.com/paper/2312.11441/) (2023)
- [Recovering from Privacy-Preserving Masking with Large Language Models](https://mlsanity.com/paper/2309.08628/) (2023)

## Built on by (most cited first, 9 of 9)

- [Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents](https://mlsanity.com/paper/2502.18509/) (2025)
- [1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning](https://mlsanity.com/paper/2508.07667/) (2025)
- [Privacy-preserved LLM Cascade via CoT-enhanced Policy Learning](https://mlsanity.com/paper/2410.08014/) (2024)
- [A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness](https://mlsanity.com/paper/2510.13890/) (2025)
- [Can Large Language Models Really Recognize Your Name?](https://mlsanity.com/paper/2505.14549/) (2025)
- [Privacy Meets Explainability: Managing Confidential Data and Transparency Policies in LLM-Empowered Science](https://mlsanity.com/paper/2504.09961/) (2025)
- [Collaborative LLM Numerical Reasoning with Local Data Protection](https://mlsanity.com/paper/2504.00299/) (2025)
- [PrivMeSA: Privacy-Aware Self-Evolving Multi-Agent System for Medicine via Local-Remote LLM Collaboration](https://mlsanity.com/paper/2609.38458/) (2026)
- [ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning](https://mlsanity.com/paper/2610.01184/) (2026)

## Abstract (arXiv)

Cascades are a common type of machine learning systems in which a large, remote model can be queried if a local model is not able to accurately label a user's data by itself. Serving stacks for large language models (LLMs) increasingly use cascades due to their ability to preserve task performance while dramatically reducing inference costs. However, applying cascade systems in situations where the local model has access to sensitive data constitutes a significant privacy risk for users since such data could be forwarded to the remote model. In this work, we show the feasibility of applying cascade systems in such setups by equipping the local model with privacy-preserving techniques that reduce the risk of leaking private information when querying the remote model. To quantify information leakage in such setups, we introduce two privacy measures. We then propose a system that leverages the recently introduced social learning paradigm in which LLMs collaboratively learn from each other by exchanging natural language. Using this paradigm, we demonstrate on several datasets that our methods minimize the privacy loss while at the same time improving task performance compared to a non-cascade baseline.