FSPO: Few-Shot Preference Optimization of Synthetic Preference Data in LLMs Elicits Effective Personalization to Real Users

• URL: http://arxiv.org/abs/2502.19312v1
• Date: Wed, 26 Feb 2025 17:08:46 GMT
• Title: FSPO: Few-Shot Preference Optimization of Synthetic Preference Data in LLMs Elicits Effective Personalization to Real Users
• Authors: Anikait Singh, Sheryl Hsu, Kyle Hsu, Eric Mitchell, Stefano Ermon, Tatsunori Hashimoto, Archit Sharma, Chelsea Finn,
• Abstract summary: We propose Few-Shot Preference Optimization, which reframes reward modeling as a meta-learning problem.<n>Under this framework, an LLM learns to quickly adapt to a user via a few labeled preferences from that user, constructing a personalized reward function for them.<n>We generate over 1M synthetic personalized preferences using publicly available LLMs.<n>We evaluate FSPO on personalized open-ended generation for up to 1,500 synthetic users across three domains: movie reviews, pedagogical adaptation based on educational background, and general question answering, along with a controlled human study.
• Score: 111.56469697145519
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Effective personalization of LLMs is critical for a broad range of user-interfacing applications such as virtual assistants and content curation. Inspired by the strong in-context learning capabilities of LLMs, we propose Few-Shot Preference Optimization (FSPO), which reframes reward modeling as a meta-learning problem. Under this framework, an LLM learns to quickly adapt to a user via a few labeled preferences from that user, constructing a personalized reward function for them. Additionally, since real-world preference data is scarce and challenging to collect at scale, we propose careful design choices to construct synthetic preference datasets for personalization, generating over 1M synthetic personalized preferences using publicly available LLMs. In particular, to successfully transfer from synthetic data to real users, we find it crucial for the data to exhibit both high diversity and coherent, self-consistent structure. We evaluate FSPO on personalized open-ended generation for up to 1,500 synthetic users across across three domains: movie reviews, pedagogical adaptation based on educational background, and general question answering, along with a controlled human study. Overall, FSPO achieves an 87% Alpaca Eval winrate on average in generating responses that are personalized to synthetic users and a 72% winrate with real human users in open-ended question answering.

Related papers

• LoRe: Personalizing LLMs via Low-Rank Reward Modeling [47.12507639759984]
  We introduce a novel framework that leverages low-rank preference modeling to efficiently learn and generalize user-specific reward functions. We validate our method on multiple preference datasets, demonstrating superior generalization to unseen users and improved accuracy in preference prediction tasks.
  arXiv  Detail & Related papers  (2025-04-20T01:16:24Z)
• Language Model Personalization via Reward Factorization [38.30745045315918]
  We introduce a framework that extends RLHF to enable user personalization. We represent user-specific rewards as a linear combination of base reward functions. In human evaluations, our method achieves a 67% win rate over default GPT-4o responses.
  arXiv  Detail & Related papers  (2025-03-08T23:41:20Z)
• Amulet: ReAlignment During Test Time for Personalized Preference Adaptation of LLMs [28.759591573106917]
  We introduce Amulet, a training-free framework that formulates the decoding process of every token as a separate online learning problem.<n>We show that Amulet can achieve significant performance improvements in rich settings with combinations of different LLMs, datasets, and user preferences.
  arXiv  Detail & Related papers  (2025-02-26T14:07:37Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications.<n> Ensuring their alignment with the diverse preferences of individual users has become a critical challenge.<n>We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• Self-Boosting Large Language Models with Synthetic Preference Data [97.94185115047999]
  We introduce SynPO, a self-boosting paradigm that leverages synthetic preference data for model alignment. After four SynPO iterations, Llama3-8B and Mistral-7B show significant enhancements in instruction-following abilities. SynPO improves the general performance of LLMs on various tasks, validated by a 3.2 to 5.0 average score increase on the well-recognized Open LLM leaderboard.
  arXiv  Detail & Related papers  (2024-10-09T14:57:31Z)
• Aligning LLMs with Individual Preferences via Interaction [51.72200436159636]
  We train large language models (LLMs) that can ''interact to align''<n>We develop a multi-turn preference dataset containing 3K+ multi-turn conversations in tree structures.<n>For evaluation, we establish the ALOE benchmark, consisting of 100 carefully selected examples and well-designed metrics to measure the customized alignment performance during conversations.
  arXiv  Detail & Related papers  (2024-10-04T17:48:29Z)
• PersonalLLM: Tailoring LLMs to Individual Preferences [11.717169516971856]
  We present a public benchmark, PersonalLLM, focusing on adapting LLMs to provide maximal benefits for a particular user.<n>We curate open-ended prompts paired with many high-quality answers over which users would be expected to display heterogeneous latent preferences.<n>Our dataset and generated personalities offer an innovative testbed for developing personalization algorithms.
  arXiv  Detail & Related papers  (2024-09-30T13:55:42Z)
• Adaptive Self-Supervised Learning Strategies for Dynamic On-Device LLM Personalization [3.1944843830667766]
  Large language models (LLMs) have revolutionized how we interact with technology, but their personalization to individual user preferences remains a significant challenge. We present Adaptive Self-Supervised Learning Strategies (ASLS), which utilize self-supervised learning techniques to personalize LLMs dynamically.
  arXiv  Detail & Related papers  (2024-09-25T14:35:06Z)
• Aligning Large Language Models with Self-generated Preference Data [72.99676237703099]
  We propose a new framework that boosts the alignment of large language models (LLMs) with human preferences. Our key idea is leveraging the human prior knowledge within the small (seed) data. We introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data.
  arXiv  Detail & Related papers  (2024-06-06T18:01:02Z)
• Personalized Language Modeling from Personalized Human Feedback [45.16986573937782]
  Personalized large language models (LLMs) are designed to tailor responses to individual user preferences.<n>We propose Personalized-RLHF, an efficient framework that utilizes a lightweight user model to capture individual user preferences.<n>We show that personalized LLMs trained using P-RLHF generate responses that are more closely aligned with individual user preferences.
  arXiv  Detail & Related papers  (2024-02-06T04:18:58Z)
• Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models [52.98743860365194]
  We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN) At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself. This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents.
  arXiv  Detail & Related papers  (2024-01-02T18:53:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.