publications

Visit Google Scholar for a full list.

2024

1. 

   Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections

   Lingjun Zhao, Nguyen X. Khanh, and Hal Daumé III

   EMNLP, 2024

   TL;DR Paper Bib

   A system that can successfully guide humans in simulated residential environments despite generating potentially inaccurate instructions

   @inproceedings{zhao2024successfully,
     title = {Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections},
     author = {Zhao, Lingjun and X. Khanh, Nguyen and Daum{\'e} III, Hal},
     booktitle = {EMNLP},
     year = {2024},
   }

2. 

   Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A

   Benjamin Plaut, Nguyen X. Khanh, and Tu Trinh

   ArXiv, 2024

   TL;DR Paper Bib

   Probabilities of Chat LLMs are miscalibrated but predictive of the correctness of their answers on Q&A tasks

   @article{plaut2024softmax,
     author = {Plaut, Benjamin and X. Khanh, Nguyen and Trinh, Tu},
     title = {Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q\&A},
     journal = {ArXiv},
     month = {},
     year = {2024},
   }

3. 

   Language-guided world models: A model-based approach to AI control

   Alex Zhang, Albert Lin, Jens Tuyls, Khanh Nguyen, and Karthik Narasimhan

   Workshop on Spatial Language Understanding and Grounded Communication for Robotics (ACL), 2024

   TL;DR Paper Bib

   Models that can read texts to simulate environments

   @inproceedings{zhang2024lwm,
     author = {Zhang, Alex and Lin, Albert and Tuyls, Jens and Nguyen, Khanh and Narasimhan, Karthik},
     title = {Language-guided world models: A model-based approach to AI control},
     booktitle = {Workshop on Spatial Language Understanding and Grounded Communication for Robotics (ACL)},
     month = {},
     year = {2024},
   }

2023

1. 

   Progressively efficient learning

   Ruijie Zheng, Khanh Nguyen, Furong Huang, Hal Daumé III, and Karthik Narasimhan

   Workshop on Intrinsically Motivated Open-ended Learning (NeurIPS), 2023

   TL;DR Paper Bib

   Learn increasingly abstract language to reduce communication effort

   @inproceedings{zheng2023progressive,
     author = {Zheng, Ruijie and Nguyen, Khanh and Huang, Furong and Daum{\'e} III, Hal and Narasimhan, Karthik},
     title = {Progressively efficient learning},
     booktitle = {Workshop on Intrinsically Motivated Open-ended Learning
      (NeurIPS)},
     month = {},
     year = {2023},
   }

2. 

   Hallucination detection for instruction generation models

   Lingjun Zhao, Khanh Nguyen, and Hal Daumé III

   EMNLP Findings, 2023

   TL;DR Paper Bib

   Detect hallucinations in model-generated navigation instructions

   @inproceedings{zhao2023hallucination,
     author = {Zhao, Lingjun and Nguyen, Khanh and Daum{\'e} III, Hal},
     title = {Hallucination detection for instruction generation models},
     booktitle = {EMNLP Findings},
     month = {},
     year = {2023},
   }

3. 

   Language models are bounded pragmatic speakers: Understanding RLHF from a Bayesian cognitive modeling perspective

   Khanh Nguyen

   Workshop on Theory of Mind (ICML), 2023

   TL;DR Paper Bib

   LLMs as limited communicative agents and how to augment them

   @inproceedings{nguyen2023bounded,
     author = {Nguyen, Khanh},
     title = {Language models are bounded pragmatic speakers: Understanding RLHF from a Bayesian cognitive modeling perspective},
     booktitle = {Workshop on Theory of Mind (ICML)},
     month = {},
     year = {2023},
   }

4. 

   Define, evaluate, and improve task-oriented cognitive capabilities for instruction generation models

   Lingjun Zhao, Khanh Nguyen, and Hal Daumé III

   ACL Findings, 2023

   TL;DR Paper Bib

   Improve instruction generation by predicting human interpretation

   @inproceedings{zhao2023cognitive,
     author = {Zhao, Lingjun and Nguyen, Khanh and Daum{\'e} III, Hal},
     title = {Define, evaluate, and improve task-oriented cognitive capabilities for instruction generation models},
     booktitle = {ACL Findings},
     month = {},
     year = {2023},
   }

2022

1. 

   A framework for learning to request rich and contextually useful information from humans

   Khanh Nguyen, Yonatan Bisk, and Hal Daumé III

   ICML, Jul 2022

   TL;DR Paper Bib

   Agents that can decide when and what question to ask, and incoporate answer to make progress

   @inproceedings{nguyen2022hari,
     author = {Nguyen, Khanh and Bisk, Yonatan and Daum{\'e} III, Hal},
     title = {A framework for learning to request rich and contextually useful information from humans},
     booktitle = {ICML},
     month = jul,
     year = {2022},
   }

2021

1. 

   Interactive learning from activity description

   Khanh Nguyen, Dipendra Misra, Robert Schapire, Miro Dudı́k, and Patrick Shafto

   ICML, Jul 2021

   TL;DR Paper Bib

   Framework for learning from language feedback with theoretical guarantees

   @inproceedings{nguyen2021iliad,
     title = {Interactive learning from activity description},
     author = {Nguyen, Khanh and Misra, Dipendra and Schapire, Robert and Dud{\'\i}k, Miro and Shafto, Patrick},
     booktitle = {ICML},
     year = {2021},
   }

2019

1. 

   Help, Anna! Visual navigation with natural multimodal assistance via retrospective curiosity-encouraging imitation learning

   Khanh Nguyen, and Hal Daumé III

   EMNLP, 2019

   TL;DR Paper Bib

   Agents that can ask for help and interpret language instructions

   @inproceedings{nguyen2019hanna,
     author = {Nguyen, Khanh and Daum{\'e} III, Hal},
     title = {Help, Anna! Visual navigation with natural multimodal assistance via retrospective curiosity-encouraging imitation learning},
     booktitle = {EMNLP},
     month = {},
     year = {2019},
   }

2. 

   Vision-based navigation with language-based assistance via imitation learning with indirect intervention

   Khanh Nguyen, Debadeepta Dey, Chris Brockett, and Bill Dolan

   CVPR, 2019

   TL;DR Paper Bib

   Agent that can ask for help

   @inproceedings{nguyen2019vnla,
     author = {Nguyen, Khanh and Dey, Debadeepta and Brockett, Chris and Dolan, Bill},
     title = {Vision-based navigation with language-based assistance via imitation learning with indirect intervention},
     booktitle = {CVPR},
     month = {},
     year = {2019},
   }

3. 

   Global Voices: Crossing borders in automatic news summarization

   Khanh Nguyen, and Hal Daumé III

   New Frontiers in Summarization Workshop at EMNLP, Nov 2019

   TL;DR Paper Bib

   Evaluation dataset for cross-lingual summarization

   @inproceedings{nguyen2019gv,
     title = {Global Voices: Crossing borders in automatic news summarization},
     author = {Nguyen, Khanh and Daum{\'e} III, Hal},
     booktitle = {New Frontiers in Summarization Workshop at EMNLP},
     month = nov,
     year = {2019},
   }

2017

1. 

   Reinforcement learning for bandit neural machine translation with simulated human feedback

   Khanh Nguyen, Hal Daumé III, and Jordan Boyd-Graber

   EMNLP, Sep 2017

   TL;DR Abs Paper Bib

   Improve machine translation with reinforcement learning from noisy ratings

   Machine translation is a natural candidate problem for reinforcement learning from human feedback: users provide quick, dirty ratings on candidate translations to guide a system to improve. Yet, current neural machine translation training focuses on expensive human-generated reference translations. We describe a reinforcement learning algorithm that improves neural machine translation systems from simulated human feedback. Our algorithm combines the advantage actor-critic algorithm (Mnih et al., 2016) with the attention-based neural encoder-decoder architecture (Luong et al., 2015). This algorithm (a) is well-designed for problems with a large action space and delayed rewards, (b) effectively optimizes traditional corpus-level machine translation metrics, and (c) is robust to skewed, high-variance, granular feedback modeled after actual human behaviors.

   @inproceedings{nguyen2017banditnmt,
     title = {Reinforcement learning for bandit neural machine translation with simulated human feedback},
     author = {Nguyen, Khanh and Daum{\'e} III, Hal and Boyd-Graber, Jordan},
     booktitle = {EMNLP},
     month = sep,
     year = {2017},
     address = {Copenhagen, Denmark},
     publisher = {Association for Computational Linguistics},
     url = {https://www.aclweb.org/anthology/D17-1153},
     doi = {10.18653/v1/D17-1153},
     pages = {1464--1474},
   }

2. The UMD neural machine translation systems at WMT17 bandit learning task

   Amr Sharaf, Shi Feng, Khanh Nguyen, Kiante Brantley, and Hal Daumé III

   WMT, Sep 2017

   Paper Bib

   @inproceedings{sharaf17wmt,
     title = {The UMD neural machine translation systems at WMT17 bandit learning task},
     author = {Sharaf, Amr and Feng, Shi and Nguyen, Khanh and Brantley, Kiante and Daum{\'e} III, Hal},
     booktitle = {WMT},
     month = sep,
     year = {2017},
     address = {Copenhagen, Denmark},
     publisher = {Association for Computational Linguistics},
     url = {https://www.aclweb.org/anthology/W17-4778},
     doi = {10.18653/v1/W17-4778},
     pages = {667--673},
   }

2015

1. 

   Posterior calibration and exploratory analysis for natural language processing models

   Khanh Nguyen, and Brendan O’Connor

   EMNLP, Sep 2015

   TL;DR Paper Bib

   Calibrated probabilities for detecting errors of NLP models

   @inproceedings{nguyen15calibration,
     title = {Posterior calibration and exploratory analysis for natural language processing models},
     author = {Nguyen, Khanh and O{'}Connor, Brendan},
     booktitle = {EMNLP},
     year = {2015},
     address = {Lisbon, Portugal},
     publisher = {Association for Computational Linguistics},
     url = {https://www.aclweb.org/anthology/D15-1182},
     doi = {10.18653/v1/D15-1182},
     pages = {1587--1598},
   }