# Learning from Natural Language Feedback for Personalized Question Answering

arXiv: https://arxiv.org/abs/2508.10695 · HTML: https://mlsanity.com/paper/2508.10695/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 45 references that are in the map.
- First posted on arXiv 14 Aug 2025.

## Builds on (most cited first, 30 of 30)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Deep Learning Recommendation Model for Personalization and Recommendation Systems](https://mlsanity.com/paper/1906.00091/) (2019)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [REFINER: Reasoning Feedback on Intermediate Representations](https://mlsanity.com/paper/2304.01904/) (2023)
- [Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation](https://mlsanity.com/paper/2404.05970/) (2024)
- [LongLaMP: A Benchmark for Personalized Long-form Text Generation](https://mlsanity.com/paper/2407.11016/) (2024)
- [Pearl: Personalizing Large Language Model Writing Assistants with Generation-Calibrated Retrievers](https://mlsanity.com/paper/2311.09180/) (2023)
- [LLM-Rec: Personalized Recommendation via Prompting Large Language Models](https://mlsanity.com/paper/2307.15780/) (2023)
- [Improving Code Generation by Training with Natural Language Feedback](https://mlsanity.com/paper/2303.16749/) (2023)
- [Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts](https://mlsanity.com/paper/2406.10471/) (2024)
- [Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision](https://mlsanity.com/paper/2411.16579/) (2024)
- [LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordination](https://mlsanity.com/paper/2309.11696/) (2023)
- [Personalized Generation In Large Model Era: A Survey](https://mlsanity.com/paper/2503.02614/) (2025)
- [Learning to Rewrite Prompts for Personalized Text Generation](https://mlsanity.com/paper/2310.00152/) (2023)
- [LaMP-QA: A Benchmark for Personalized Long-form Question Answering](https://mlsanity.com/paper/2506.00137/) (2025)
- [Reasoning-Enhanced Self-Training for Long-Form Personalized Text Generation](https://mlsanity.com/paper/2501.04167/) (2025)
- [ExPerT: Effective and Explainable Evaluation of Personalized Long-Form Text Generation](https://mlsanity.com/paper/2501.14956/) (2025)
- [Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Models](https://mlsanity.com/paper/2409.09510/) (2024)
- [Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing](https://mlsanity.com/paper/2305.08195/) (2023)
- [Corporate Communication Companion (CCC): An LLM-empowered Writing Assistant for Workplace Social Media](https://mlsanity.com/paper/2405.04656/) (2024)
- [Learning to Reason from Feedback at Test-Time](https://mlsanity.com/paper/2502.15771/) (2025)
- [JDsearch: A Personalized Product Search Dataset with Real Queries and Full Interactions](https://mlsanity.com/paper/2305.14810/) (2023)
- [Analysis and Design of a Personalized Recommendation System Based on a Dynamic User Interest Model](https://mlsanity.com/paper/2410.09923/) (2024)

## Built on by (most cited first, 5 of 5)

- [Language Models Can Learn from Verbal Feedback Without Scalar Rewards](https://mlsanity.com/paper/2509.22638/) (2025)
- [Pathways of Thoughts: Multi-Directional Thinking for Long-form Personalized Question Answering](https://mlsanity.com/paper/2509.19094/) (2025)
- [Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning](https://mlsanity.com/paper/2510.18849/) (2025)
- [Improving User Privacy in Personalized Generation: Client-Side Retrieval-Augmented Modification of Server-Side Generated Speculations](https://mlsanity.com/paper/2601.17569/) (2026)
- [Rubric-Aware On-Policy Self-Distillation for LLM Personalization](https://mlsanity.com/paper/2609.35262/) (2026)

## Abstract (arXiv)

Personalization is crucial for enhancing both the effectiveness and user satisfaction of language technologies, particularly in information-seeking tasks like question answering. Current approaches for personalizing large language models (LLMs) often rely on retrieval-augmented generation (RAG), followed by reinforcement learning with scalar reward signals to teach models how to use retrieved personal context. We believe that these scalar rewards sometimes provide weak, non-instructive feedback, limiting learning efficiency and personalization quality. We introduce VAC, a novel framework for personalized response generation that replaces scalar rewards with natural language feedback (NLF) that are generated conditioned on the user profiles and the question narratives. NLF serves as a rich and actionable supervision signal, allowing the policy model to iteratively refine its outputs and internalize effective personalization strategies. Training alternates between optimizing the feedback model and fine-tuning the policy model on the improved responses, resulting in a policy model that no longer requires feedback at inference. Evaluation on the LaMP-QA benchmark that consists of three diverse domains demonstrates consistent and significant improvements over the state-of-the-art results. Human evaluations further confirm the superior quality of the generated responses. These results demonstrate that NLF provides more effective signals for optimizing personalized question answering.