Summary of Large Language Models Empowered Personalized Web Agents, by Hongru Cai et al.
Large Language Models Empowered Personalized Web Agents
by Hongru Cai, Yongqi Li, Wenjie Wang, Fengbin Zhu, Xiaoyu Shen, Wenjie Li, Tat-Seng Chua
First submitted to arxiv on: 22 Oct 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper introduces a new direction in automating web task completion using Large Language Models (LLMs). Existing LLM-based web agents overlook the importance of personalized data, such as user profiles and historical web behaviors, in understanding users’ instructions and executing customized actions. To address this limitation, the authors formulate the task of LLM-empowered personalized web agents that integrate personalized data and user instructions to personalize instruction comprehension and action execution. A comprehensive evaluation benchmark, Personalized Web Agent Benchmark (PersonalWAB), is constructed featuring user instructions, personalized user data, web functions, and two evaluation paradigms across three personalized web tasks. The authors propose a Personalized User Memory-enhanced Alignment (PUMA) framework that utilizes a memory bank with a task-specific retrieval strategy to filter relevant historical web behaviors and align LLMs for personalized action execution through fine-tuning and direct preference optimization. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about making computers better at understanding what people want them to do online. Right now, computers can already help people complete tasks on the internet, but they don’t take into account what’s important to each individual person. To fix this, the authors came up with a new way for computers to understand and follow personalized instructions by combining different types of data about each person. They also created a special test to see how well these new computer systems work. |
Keywords
» Artificial intelligence » Alignment » Fine tuning » Optimization
