# Weightless Fine-Tuning: Personalizing LLMs via Logit-Space Transport

arXiv: https://arxiv.org/abs/2608.11342 · HTML: https://mlsanity.com/paper/2608.11342/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 34 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Builds on (most cited first, 27 of 27)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Transformers learn in-context by gradient descent](https://mlsanity.com/paper/2212.07677/) (2022)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Scaling Data-Constrained Language Models](https://mlsanity.com/paper/2305.16264/) (2023)
- [Learning to (Learn at Test Time): RNNs with Expressive Hidden States](https://mlsanity.com/paper/2407.04620/) (2024)
- [In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering](https://mlsanity.com/paper/2311.06668/) (2023)
- [Personalization of Large Language Models: A Survey](https://mlsanity.com/paper/2411.00027/) (2024)
- [When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities](https://mlsanity.com/paper/2307.16376/) (2023)
- [A Survey of Personalized Large Language Models: Progress and Future Directions](https://mlsanity.com/paper/2502.11528/) (2025)
- [Test-Time Learning for Large Language Models](https://mlsanity.com/paper/2505.20633/) (2025)
- [Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping](https://mlsanity.com/paper/2102.11343/) (2021)
- [RECAP: Retrieval-Enhanced Context-Aware Prefix Encoder for Personalized Dialogue Response Generation](https://mlsanity.com/paper/2306.07206/) (2023)
- [In-context Learning and Gradient Descent Revisited](https://mlsanity.com/paper/2311.07772/) (2023)
- [Personalize Your LLM: Fake it then Align it](https://mlsanity.com/paper/2503.01048/) (2025)
- [Drift: Decoding-time Personalized Alignments with Implicit User Preferences](https://mlsanity.com/paper/2502.14289/) (2025)
- [CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering](https://mlsanity.com/paper/2507.04756/) (2025)
- [Compute-Constrained Data Selection](https://mlsanity.com/paper/2410.16208/) (2024)
- [Embedding-to-Prefix: Parameter-Efficient Personalization for Pre-Trained Large Language Models](https://mlsanity.com/paper/2505.17051/) (2025)
- [Can Good Writing Be Generative? Expert-Level AI Writing Emerges through Fine-Tuning on High-Quality Books](https://mlsanity.com/paper/2601.18353/) (2026)
- [Readers Prefer Outputs of AI Trained on Copyrighted Books over Expert Human Writers](https://mlsanity.com/paper/2510.13939/) (2025)
- [Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning](https://mlsanity.com/paper/2602.11149/) (2026)
- [A Scaling Law for Token Efficiency in LLM Fine-Tuning Under Fixed Compute Budgets](https://mlsanity.com/paper/2505.06150/) (2025)

## Abstract (arXiv)

Supervised fine-tuning (SFT) is a standard approach for adapting LLMs to a target distribution, but in settings such as personalization, where each author requires separate weight access, optimization, storage, and retraining, its costs become prohibitive. We propose Weightless Fine-Tuning (WFT), a training-free decoding-time method that approximates the distributional effect of SFT without weight updates. WFT computes supervised residuals on an author's training sequence and transports them to the current prompt through a cross-prefix transport operator estimated from dropout-induced cross-covariance. The operator captures how a perturbation at one context propagates to predictions at another, replacing gradient-based parameter updates with logit-space corrections. On three LaMP personalization benchmarks, WFT achieves the best average performance across datasets, matches or exceeds SFT on individual tasks, and outperforms other lightweight baselines on average. In a budget-controlled comparison, WFT approaches SFT performance using less than 7% of the effective computation. Logit-level analysis shows a cosine similarity of 0.875 between the logit shifts induced by WFT and SFT over 95% of the next-token probability mass, suggesting that WFT captures the distributional effect of supervised adaptation without modifying model weights.