Yumo Xu

I am an NLP scientist at AWS AI Labs researching and building intelligent language services for enterprises.

My current interests lie in the following areas:

  • Effective Retrieval-Augmented Generation (RAG) systems,
  • Accurate faithfulness evaluation and source attribution, and
  • Reliable autonomous agents with generalizable tool-use capabilities.

Prior to Amazon, I received my PhD in NLP at the University of Edinburgh, advised by Prof. Mirella Lapata. My PhD research was on text summarization, the process of condensing a source text into a shorter version while preserving its salient information.


Sep 7, 2023 I will serve as an Area Chair for NLG at LREC-COLING’24.
May 1, 2023 Generative modeling for eXtractive summarization (GenX) was accepted by ACL’23.
Apr 18, 2023 Excited to join AWS AI Labs in Seattle as a scientist.
Mar 31, 2023 Happy to join the Organizing Committee of SIGSUMM.
Jan 21, 2023 Working on extractive summarization? Check out our latest work accepted by ICLR’23.

(Recent) Selected Publications

  1. Summarization
    QTSumm: Query-Focused Summarization over Tabular Data
    In EMNLP 2023
  2. Summarization
    Abstractive Summarizers are Excellent Extractive Summarizers
    Varab, Daniel, and Xu, Yumo
    In ACL 2023
  3. Summarization
    Text Summarization with Oracle Expectation
    Xu, Yumo, and Lapata, Mirella
    In ICLR 2023
  4. Summarization
    Document Summarization with Latent Queries
    Xu, Yumo, and Lapata, Mirella
    TACL 2022