Optimizing User Profiles via Contextual Bandits for Retrieval-Augmented LLM Personalization (2026.acl-long)
Copied to clipboard
Linfeng Du, Ye Yuan, Zichen Zhao, Fuyuan Lyu, Emiliano Penaloza, Xiuying Chen, Zipeng Sun, Jikun Kang, Laurent Charlin, Xue Liu, Haolun Wu
| Challenge: | Existing approaches for personalizing large language models require modifying parameters. |
| Approach: | They propose a lightweight approach to personalizing large language models via retrieval augmentation . relevance serves as an unreliable proxy for utility, they argue . |
| Outcome: | The proposed framework outperforms strong heuristic and retrieval-augmented baselines on nine personalization tasks. |
Similar Papers
Personalize Your LLM: Fake it then Align it (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing personalization methods require fine-tuning of large language models for each user, rendering them prohibitively expensive for widespread adoption. |
| Approach: | They propose a retrieval-based personalization approach that uses self-generated personal preference data and representation editing to enable quick and cost-effective personalization. |
| Outcome: | The proposed approach outperforms two personalization baselines by 40% on various tasks. |
Few-shot Personalization of LLMs with Mis-aligned Responses (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing approaches have limited successes in personalizing large language models due to the lack of personalized learning or the reliance on shared personal data. |
| Approach: | They propose a few-shot personalization of large language models with mis-aligned responses using LLMs by learning a set of personalized prompts for each user based on user profile and examples of previous opinions. |
| Outcome: | The proposed method significantly improves performance across benchmarks compared to best-performing baselines. |
GRAVITY: A Framework for Personalized Text Generation via Profile-Grounded Synthetic Preferences (2026.eacl-long)
Copied to clipboard
| Challenge: | Personalization in LLMs often relies on costly human feedback or interaction logs, limiting scalability and neglecting deeper user attributes. |
| Approach: | They propose a framework for generating synthetic, profile-grounded preference data that captures users’ interests, values, beliefs, and personality traits. |
| Outcome: | The proposed framework improves on book descriptions for 400 Amazon users across multiple cultures, with user studies showing that outputs are preferred over 86% of the time. |
Guided Profile Generation Improves Personalization with Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to personalization with LLMs rely on sparse and complex personal contexts, resulting in incomplete interpretation. |
| Approach: | They propose a general method to generate personal profiles in natural language that extracts important, distinctive features from the personal context into concise, descriptive sentences. |
| Outcome: | The proposed method improves personalization ability across different tasks, for example, it increases 37% accuracy in predicting personal preference compared to directly feeding the LLMs with raw personal context. |
Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement (2025.coling-main)
Copied to clipboard
Chenkai Sun, Ke Yang, Revanth Gangi Reddy, Yi Fung, Hou Pong Chan, Kevin Small, ChengXiang Zhai, Heng Ji
| Challenge: | Existing research has focused on enhancing the retrieval stage and optimizing the representation of the database. |
| Approach: | They propose a framework to improve generalization across task contexts and collaborative refinement to bridge knowledge gaps among users. |
| Outcome: | The proposed framework improves generalization across task contexts and collaborative refinement to bridge knowledge gaps among users. |
LLM Program Optimization via Retrieval Augmented Search (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent work shows that large language models have difficulty with program optimization out-of-the-box. |
| Approach: | They propose a blackbox adaptation method that performs beam search over candidate optimizations by a training dataset. |
| Outcome: | The proposed method outperforms retrieval based on the source code in a number of ways. |
Retrieval Enhancements for RAG: Insights from a Deployed Customer Support Chatbot (2026.eacl-industry)
Copied to clipboard
Daniel González Juclà, Mohit Tuteja, Marcos Esteve Casademunt, Keshav Unnikrishnan, Yasir Usmani, Arvind Roshaan
| Challenge: | a persistent gap remains between Recall@10 and Recall @50 across datasets . |
| Approach: | They evaluate embedding model comparison, Reciprocal Rank Fusion and embedded concatenation techniques to improve retrieval quality. |
| Outcome: | The proposed methods outperform traditional cross-encoders in identifying high-relevance passages. |
Benchmarking and Improving LLM Robustness for Personalized Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluations focus on whether a model’s responses align with a user’s preferences, but factuality is an important yet overlooked dimension. |
| Approach: | They propose a scalable framework for evaluating robustness of large language models in personalization and a new dataset, PERGData. |
| Outcome: | The proposed framework improves robustness by 25% across models. |
Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts (2025.emnlp-industry)
Copied to clipboard
Anwesan Pal, Karen Hovsepian, Tinghao Guo, Mengnan Zhao, Somendra Tripathi, Nikos Kanakaris, George Mihaila, Sumit Nigam
| Challenge: | Recent studies into effective context lengths of flagship large language models (LLMs) have revealed major limitations in effective question answering (QA) and reasoning over long and complex contexts for even the largest and most impressive cadre of models. |
| Approach: | They propose a lightweight data augmentation strategy that boosts LLM performance in long-context scenarios without degrading and altering the integrity and composition of retrieved documents. |
| Outcome: | The proposed strategy boosts performance in long-context scenarios without degrading and altering the integrity and composition of retrieved documents. |
Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Recent LLMs like Gemini-1.5 and GPT-4 show exceptional capabilities to understand long contexts directly. |
| Approach: | They propose a method that routes queries to RAG or LC based on model self-reflection. |
| Outcome: | The proposed method significantly reduces the computation cost while maintaining a comparable performance to RAG. |