paper-with-me

홈 › Papers

Few-shot Personalization of LLMs with Mis-aligned Responses

2024-06-26 · Jaehyung Kim, Yiming Yang

As the diversity of users increases, the capability of providing personalized responses by large language models (LLMs) has become increasingly important. Existing approaches have only limited successes in LLM personalization, due to the absence of personalized learning or the reliance on shared personal data. This paper proposes a new approach for a few-shot personalization of LLMs with their mis-aligned responses (Fermi). Our key idea is to learn a set of personalized prompts for each user by progressively improving the prompts using LLMs, based on user profile (e.g., demographic information) and a few examples of previous opinions. During an iterative process of prompt improvement, we incorporate the contexts of mis-aligned responses by LLMs, which are especially crucial for the effective personalization of LLMs. In addition, we develop an effective inference method to further leverage the context of the test query and the personalized prompts. Our experimental results demonstrate that Fermi significantly improves performance across various benchmarks, compared to the best-performing baselines.

📄 PDF Abstract BibTeX arXiv:2406.18678

Code (1)

bbuing9/fermi 공식 구현

Tasks

Diversity

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas

2025-01-20 · Nishant Balepur, Vishakh Padmakumar, Fumeng Yang, Shi Feng 외

LLMs are tuned to follow instructions (aligned) by learning which of two outputs users prefer for a prompt. However, this preference data format does not convey why users prefer responses that are chosen or rejected, so …

Language Model Personalization via Reward Factorization

2025-03-08 · Idan Shenfeld, Felix Faltings, Pulkit Agrawal, Aldo Pacchiano

Modern large language models (LLMs) are optimized for human-aligned responses using Reinforcement Learning from Human Feedback (RLHF). However, existing RLHF approaches assume a universal preference model and fail to acc…

Language ModelingLanguage Modellingmodel

PersoBench: Benchmarking Personalized Response Generation in Large Language Models

2024-10-04 · Saleh Afzoon, Usman Naseem, Amin Beheshti, Zahra Jamali

While large language models (LLMs) have exhibited impressive conversational capabilities, their proficiency in delivering personalized responses remains unclear. Although recent benchmarks automatically evaluate persona …

BenchmarkingDialogue GenerationDiversityResponse Generation

Re-Centering Humans in LLM Personalization

2026-06-04 · Lechen Zhang, Jiarui Liu, Tal August arxiv

Despite growing interest, most evaluations of large language models' (LLMs') personalization abilities have relied on synthetic data. It remains unclear how well current personalization systems work for real users. In th…

Benchmarking and Improving LLM Robustness for Personalized Generation

2025-09-18 · Chimaobi Okite, Naihao Deng, Kiran Bodipati, Huaidian Hou 외 arxiv

Recent years have witnessed a growing interest in personalizing the responses of large language models (LLMs). While existing evaluations primarily focus on whether a response aligns with a user's preferences, we argue t…