Rik Koncel-Kedziorski

ML Scientist, Apple

prof_pic.jpg

My research builds AI systems that reason transparently about the people they interact with. I work on methods for interpersonal reasoning — training language models to make sense of the psychological states, beliefs, and preferences underlying observed user behavior — with the broader goal of turning AI from monolithic knowledge sources into collaborators capable of on-the-fly personalization.

This builds on a decade of work on reasoning in AI. Early in my career I focused on formal reasoning, developing foundational datasets and methods for mathematical problem solving (MAWPS, MathQA) and scientific text generation (Text Generation from Knowledge Graphs with Graph Transformers). In industry I extended these ideas to financial reasoning (DocFinQA, BizBench) and to one of the first production-scale generative QA systems at Alexa. My current work brings these threads together by grounding LLM reasoning in validated psychological theory — see PrimeX and Improving Language Model Personas via Rationalization with Psychological Scaffolds (both EMNLP 2025).

I completed my PhD in Computational Linguistics at the University of Washington in 2019, advised by Hanna Hajishirzi and Gina-Anne Levow, and continued as a postdoctoral researcher with Noah Smith at UW CSE. Before Apple, I was a Research Scientist at S&P Global Kensho and an Applied Scientist at Amazon.

news

Nov 06, 2025 Gave a keynote at the PALS (Personalization of Language Systems) workshop at EMNLP 2025.
Nov 05, 2025 Improving Language Model Personas via Rationalization with Psychological Scaffolds accepted at EMNLP 2025 (with Brihi Joshi, Xiang Ren, Swabha Swayamdipta, Tim Paek).
Nov 05, 2025 PrimeX: A Dataset of Worldview, Opinion, and Explanation accepted at EMNLP 2025.
Aug 01, 2024 DocFinQA: A Long-Context Financial Reasoning Dataset accepted at ACL 2024.
Jun 01, 2024 Received an Apple AI Research Grant for User Representations and Reasoning for Natural Dialogue Systems (with Swabha Swayamdipta, USC).

selected publications

  1. ACL
    DocFinQA: A Long-Context Financial Reasoning Dataset
    Varshini Reddy, Rik Koncel-Kedziorski, V. Lai, and 2 more authors
    In Annual Meeting of the Association for Computational Linguistics, 2024
  2. ACL
    Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text
    Yao Dou, Maxwell Forbes, Rik Koncel-Kedziorski, and 2 more authors
    In Annual Meeting of the Association for Computational Linguistics, 2022
  3. AAAI
    A Controllable Model of Grounded Response Generation
    Zeqiu Wu, Michel Galley, Chris Brockett, and 8 more authors
    In AAAI Conference on Artificial Intelligence, 2021
  4. ACL
    Explaining Relationships Between Scientific Documents
    Kelvin Luu, Xinyi Wu, Rik Koncel-Kedziorski, and 3 more authors
    In Annual Meeting of the Association for Computational Linguistics, 2021
  5. NAACL
    Text Generation from Knowledge Graphs with Graph Transformers
    Rik Koncel-Kedziorski, Dhanush Bekal, Yi Luan, and 2 more authors
    In North American Chapter of the Association for Computational Linguistics, 2019
  6. NAACL
    MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms
    Aida Amini, Saadia Gabriel, Shanchuan Lin, and 3 more authors
    In North American Chapter of the Association for Computational Linguistics, 2019
  7. NAACL
    MAWPS: A Math Word Problem Repository
    Rik Koncel-Kedziorski, Subhro Roy, Aida Amini, and 2 more authors
    In North American Chapter of the Association for Computational Linguistics, 2016
  8. ACL
    Parsing Algebraic Word Problems into Equations
    Rik Koncel-Kedziorski, Hannaneh Hajishirzi, Ashish Sabharwal, and 2 more authors
    Transactions of the Association for Computational Linguistics, 2015