Summary of Proxyqa: An Alternative Framework For Evaluating Long-form Text Generation with Large Language Models, by Haochen Tan et al.
PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models
by Haochen Tan, Zhijiang Guo, Zhan Shi, Lu Xu, Zhili Liu, Yunlong Feng, Xiaoguang Li, Yasheng Wang, Lifeng Shang, Qun Liu, Linqi Song
First submitted to arxiv on: 26 Jan 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 This research paper proposes a novel framework called ProxyQA for evaluating the quality of long-form text generation by Large Language Models (LLMs). The existing evaluation methods, which rely on crowdsourcing or automated metrics like ROUGE score, have limitations. ProxyQA addresses these shortcomings by using in-depth human-curated meta-questions and proxy-questions with pre-annotated answers. LLMs generate content in response to these questions, and the quality is assessed through an evaluator’s accuracy in addressing the proxy-questions. The framework is designed to be demanding and aligns closely with human evaluative standards. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a new way to test how well Large Language Models can write long texts like reports or articles. Right now, we use methods that rely on people doing a lot of work or automated tools that don’t always agree with what humans think is good writing. The new method, called ProxyQA, uses questions about specific topics and pre-written answers to see how well the models do. Humans then look at the model’s writing and check if it matches the correct answers. This way, we can see which models are doing a better job of generating high-quality text. |
Keywords
» Artificial intelligence » Rouge » Text generation
