# Federated Fine-Tuning of Large Language Models: Kahneman-Tversky vs. Direct Preference Optimization

arXiv: https://arxiv.org/abs/2502.14187 · HTML: https://mlsanity.com/paper/2502.14187/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 13 of 13)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [Federated Multi-Task Learning](https://mlsanity.com/paper/1705.10467/) (2017)
- [LoRA+: Efficient Low Rank Adaptation of Large Models](https://mlsanity.com/paper/2402.12354/) (2024)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning](https://mlsanity.com/paper/2402.06954/) (2024)

## Built on by (most cited first, 4 of 4)

- [Federated Personal Knowledge Graph Completion with Lightweight Large Language Models for Personalized Recommendations](https://mlsanity.com/paper/2603.13264/) (2026)
- [Aligning Language Models with Investor and Market Behavior for Financial Recommendations](https://mlsanity.com/paper/2510.15993/) (2025)
- [Parallel and Multi-Stage Knowledge Graph Retrieval for Behaviorally Aligned Financial Asset Recommendations](https://mlsanity.com/paper/2511.11583/) (2025)
- [From Baselines to Preferences: A Comparative Study of LoRA/QLoRA and Preference Optimization for Mental Health Text Classification](https://mlsanity.com/paper/2604.00773/) (2026)

## Abstract (arXiv)

We evaluate Kahneman-Tversky Optimization (KTO) as a fine-tuning method for large language models (LLMs) in federated learning (FL) settings, comparing it against Direct Preference Optimization (DPO). Using Alpaca-7B as the base model, we fine-tune on a realistic dataset under both methods and evaluate performance using MT-Bench-1, Vicuna, and AdvBench benchmarks. Additionally, we introduce a redistributed dataset setup, where only KTO is applicable due to its ability to handle single-response feedback, unlike DPO's reliance on paired responses. Our results demonstrate that KTO, in both its original (KTOO) and redistributed (KTOR) configurations, consistently outperforms DPO across all benchmarks. In the redistributed setup, KTO further validates its flexibility and resilience by maintaining superior performance in scenarios where DPO cannot be applied. These findings establish KTO as a robust and scalable fine-tuning method for FL, motivating its adoption for privacy-preserving, decentralized, and heterogeneous environments.