- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes DP-MIND, a framework for differentially private long-context LLM inference. DP-MIND perturbs the input locally and process it chunk by chunk with a memory. They optimize the memory construction policy on the perturbed inputs using reinforcement learning. They perform experiments on RULER-HQA and NIAH with context lengths up to the million-token scale, and show that DP-MIND can outperform baseline methods.
Critical strengths
-
The paper focuses on differentially private inference over long contexts, which is an interesting problem.
-
The paper is easy to follow.
-
The experiments cover context lengths up to 1.8 million tokens, showing the scalability of the proposed framework.
Critical weaknesses
-
While DP inference to long contexts is an interesting problem, it is unclear to me why existing RL-based memory methods (e.g., MemAgent) are insufficient under DP perturbation.
-
The proposed framework mainly combines existing DP perturbation and RL-based memory inference methods. Could the authors further clarify the technical novelty of the proposed approach?
-
The experiments are limited to the Qwen2.5 model family. I recommend evaluating the proposed method on more model families to show its generalizability.
-
It would be better to perform ablation studies on the memory-consistency reward . I recommend comparing the performance with and without this reward.
-
I recommend including existing work on differentially private in-context learning [1, 2, 3] in the literature review and discussing its relevance to the proposed approach.
[1] Wu, Tong, et al. "Privacy-preserving in-context learning for large language models." International Conference on Learning Representations. 2024.
[2] Tang, Xinyu, et al. "Privacy-preserving in-context learning with differentially private few-shot generation." International conference on learning representations. Vol. 2024. 2024.
[3] Gao, Fengyu, et al. "Data-adaptive differentially private prompt synthesis for in-context learning." International Conference on Learning Representations. 2025.
Questions for authors
See Weaknesses.
6 comments
Response to Reviewer 9VZ1 (2/2)
W4: Missing ablation on the memory-consistency reward
As you suggested, we performed the requested ablation to isolate the contribution of the memory-consistency reward beyond the final-answer reward. The reference memory is generated by a policy first trained on clean inputs for task performance. We encourage the denoised memory from perturbed inputs to approach this reference, providing intermediate supervision for preserving task-relevant information under DP noise.
We compare DP-RL MemoryAgent with and without the memory-consistency reward at context lengths from 7K to 448K, alongside the original RL MemoryAgent baseline. The results are reported below.
| Method | 7K | 14K | 28K | 56K | 112K | 224K | 448K |
|---|---|---|---|---|---|---|---|
| RL MemoryAgent | 72.66 | 67.97 | 67.19 | 67.97 | 65.62 | 69.53 | 67.19 |
| DP-RL MemoryAgent w/o memory-consistency reward | 73.44 | 69.53 | 69.53 | 67.19 | 66.41 | 69.53 | 70.31 |
| DP-RL MemoryAgent w/ memory-consistency reward | 75.00 | 71.88 | 69.53 | 67.97 | 66.41 | 69.53 | 71.88 |
Adding the memory-consistency reward improves SubEM with gains of up to 2.34 percentage points, supporting its benefit beyond the final-answer reward.
W5: Missing discussion of differentially private in-context learning
We will include all three papers in the related work and discuss their connection to DP-MIND. These works enable privacy-preserving LLM inference by protecting in-context examples through differentially private response aggregation or synthetic demonstration generation, while DP-MIND focuses on protecting long context LLM inference.
Thank you & Looking forward to your feedback
We would like to extend heartfelt thanks to you for your time and efforts throughout the review process, and for your positive assessment of our work. Each of your comments has led to a concrete change in the paper. For your convenience, we briefly recap them here:
-
W1, necessity of DP-aware memory adaptation. We clarified that memory methods trained on clean inputs do not address the accumulation of perturbed entities and relations across memory updates. At 448K, DP-aware training improves Sub-EM from 67.19 to 71.88, showing that directly applying an existing RL memory method is insufficient under DP perturbation.
-
W2, technical novelty. We clarified that DP-MIND introduces a memory-consistency reward that supervises intermediate information retention under DP noise, together with local answer denoising that restores recoverable spans without exposing clean information to the server. We also provide an end-to-end privacy analysis and evaluation at context lengths up to 1.8M tokens.
-
W3, generalization across model families. As you suggested, we plan to extend the full evaluation to the Llama family, including RL training. As a first step, we conducted preliminary experiments with Llama-3-8B-Instruct and Llama-3-8B-Instruct-Gradient-1048k using the same perturbed inputs as in our Qwen experiments, thereby extending the current evaluation beyond the Qwen2.5 family.
-
W4, memory-consistency reward ablation. We added the requested comparison between DP-RL MemoryAgent with and without the memory-consistency reward over context lengths from 7K to 448K. The reward improves Sub-EM by up to 2.34 percentage points beyond training with the final-answer reward alone.
-
W5, differentially private in-context learning. We added the three suggested papers and clarified their relationship to DP-MIND. These methods protect in-context examples through private aggregation or synthetic demonstration generation, whereas DP-MIND protects long contexts during LLM inference.
We hope these revisions address your concerns and clarify the motivation, technical contributions, and generalizability of DP-MIND. We would be happy to provide any further clarification.
Response to Reviewer 9VZ1 (1/2)
We thank the reviewer for the detailed review and valuable suggestions. The reviewer raised important concerns about the motivation for DP-aware memory adaptation, technical novelty, ablations, and generalizability. We address each concern below.
W1: Insufficient justification for adapting existing memory methods to DP
We apologize for the confusion regarding the motivation for DP-aware memory adaptation. DP perturbed entities and relations can be stored in memory and persist through subsequent updates, causing errors to accumulate. Existing RL-based memory methods such as MemAgent are designed for memory construction on clean inputs, without explicitly addressing this noise-induced error accumulation. Consequently, directly applying them to DP-perturbed inputs provides insufficient robustness.
Figure 2 and Appendix Table 3 compare RL MemoryAgent, DP-RL MemoryAgent, and the full DP-MIND on RULER-HQA at ϵ=7. At 448K, DP-aware training improves SubEM from 67.19 to 71.88, with no further gain from local answer denoising. At 56K, training leaves the score unchanged at 67.97, while local denoising increases it to 73.44. These results show that RL-based memory inference alone does not fully address the utility loss introduced by DP perturbation,
W2: Technical novelty beyond combining existing methods
DP-MIND goes beyond combining an existing perturbation mechanism with a memory agent by introducing DP-aware optimization of memory construction together with local answer denoising.
Memory-consistency reward for robust memory construction. Final-answer correctness provides a terminal reward, but does not directly measure whether intermediate memories retain the supporting evidence. We therefore train a reference policy on clean data to generate memory trajectories. During RL on DP-perturbed inputs, the memory-consistency reward encourages denoised memories to match their clean references by penalizing the average embedding distance between them. Denoising reduces penalties for recoverable token substitutions. We combine this reward with correctness of the final locally denoised answer, supervising both intermediate information retention and final-answer utility.
Local answer recovery. The user retains the clean context and token alignment locally and uses them to restore recoverable perturbed answer spans. This improves answer utility while keeping restored sensitive information on the user's device.
Privacy analysis and evaluation at the million-token scale. We provide formal privacy guarantee of the whole framework and evaluate inference up to 1.8M tokens. We build on established DP and memory primitives; the contribution lies in adapting memory training and answer recovery to this setting.
We will clarify these contributions and add the clean-reference training details to the revised manuscript.
W3: Limited evaluation across model families
To evaluate whether the observed behavior generalizes beyond the Qwen2.5 family, we have conducted preliminary experiments using Llama-3-8B-Instruct (8K context window) and Llama-3-8B-Instruct-Gradient-1048k (approximately 1M context window), which share the Llama 3 base model. The results below cover direct inference, memory-augmented inference without RL, and the extended-context model. To ensure a fair comparison, all methods are evaluated on the same set of pre-generated perturbed inputs (ϵ=7) used in Qwen experiments, with performance measured by Sub-EM (%). Due to the substantial time required for RL training, we have not yet completed the full evaluation.
We will include these results and complete the remaining RL experiments in the revised manuscript.