# Communication-Aware Knowledge Distillation for Federated LLM Fine-Tuning over Wireless Networks

arXiv: https://arxiv.org/abs/2509.01750 · HTML: https://mlsanity.com/paper/2509.01750/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Federated, robust and private distillation, one of 12 directions in Knowledge distillation.
- Builds on 11 of its 13 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Placed in

- Knowledge distillation / [Federated, robust and private distillation](https://mlsanity.com/distill/federated-robust-and-private-distillation/)

## Builds on (most cited first, 11 of 11)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://mlsanity.com/paper/2105.10056/) (2021)
- [FedKD: Communication Efficient Federated Learning via Knowledge Distillation](https://mlsanity.com/paper/2108.13323/) (2021)
- [Towards Building the Federated GPT: Federated Instruction Tuning](https://mlsanity.com/paper/2305.05644/) (2023)
- [FedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Models](https://mlsanity.com/paper/2406.02224/) (2024)
- [Federated Fine-Tuning of LLMs: Framework Comparison and Research Directions](https://mlsanity.com/paper/2501.04436/) (2025)
- [Joint Model Pruning and Resource Allocation for Wireless Time-triggered Federated Learning](https://mlsanity.com/paper/2408.01765/) (2024)

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

- [When Top-K Misses the Decision: Tool-Call Drift in Multi-Teacher On-Policy Distillation](https://mlsanity.com/paper/2607.07050/) (2026)
- [FLoKD: Adaptive Knowledge Distillation for Federated Low-Rank LLM over Wireless Networks](https://mlsanity.com/paper/2609.13580/) (2026)
- [Joint Movement and Compression Ratio Design for Mobile Embodied AI Networks (MEAN)](https://mlsanity.com/paper/2610.02334/) (2026)

## Abstract (arXiv)

Federated learning (FL) for large language models (LLMs) offers a privacy-preserving scheme, enabling clients to collaboratively fine-tune locally deployed LLMs or smaller language models (SLMs) without exchanging raw data. While parameter-sharing methods in traditional FL models solves number of technical challenges, they still incur high communication overhead and struggle with adapting to heterogeneous model architectures. Federated distillation, a framework for mutual knowledge transfer via shared logits, typically offers lower communication overhead than parameter-sharing methods. However, transmitting logits from LLMs remains challenging for bandwidth-limited clients due to their high dimensionality. In this work, we focus on a federated LLM distillation with efficient communication overhead. To achieve this, we first propose an adaptive Top-k logit selection mechanism, dynamically sparsifying logits according to real-time communication conditions. Then to tackle the dimensional inconsistency introduced by the adaptive sparsification, we design an adaptive logits aggregation scheme, effectively alleviating the artificial and uninformative inputs introduced by conventional zero-padding methods. Finally, to enhance the distillation effect, we incorporate LoRA-adapted hidden-layer projection from LLM into the distillation loss, reducing the communication overhead further while providing richer representation. Experimental results demonstrate that our scheme achieves superior performance compared to baseline methods while effectively reducing communication overhead by approximately 50%.