George Mason NLP

George Mason NLP

George Mason University

George Mason Natural Language Processing Group

Natural language processing (NLP) aims to enable computers to use human languages – so that people can, for example, interact with computers naturally; or communicate with people who don’t speak a common language; or manipulate speech or text data at scales not otherwise possible. The NLP group at George Mason Computer Science is interested in all aspects of NLP, from building language technologies for under-served languages and communities, to understanding and improving the reasoning abilities of large language models (LLMs).

The group is comprised of three faculty (Antonios Anastasopoulos, Ziyu Yao, and Kenton Murray) and their students and collaborators. We are currently working on multilingual NLP, on machine translation and speech recognition for dialects, low-resource, and endangered languages, on LLMs for reasoning and planning, on the actionable interpretability of LLMs, and on human-AI interaction.

News

  • August 2026 - Kenton Murray joins GMU CS as an Assistant Professor!
  • August 2026 - 3 papers accepted at EMNLP Main and 1 paper accepted at Findings! Congratulations to Anjishnu, Hao, and Antik!
  • July 2026 - 2 papers accepted at COLM! Congratulations to Anjishnu, Chutong, and Prabin!
  • July 2026 - Congratulations to Dr. Saurabh Srivastava who defended his PhD and will join Adobe to continue his research on LLMs!
  • May 2026 - Congratulations to Dr. Fahim Faisal who defended his PhD and will continue for a postdoc at Oak Ridge National Lab!
  • August 2024 - GMNLP will be at ACL with 5 papers (ACL main, ACL Findings, IWSLT, ClimateNLP).
  • June 2024 - GMNLP will be at NAACL with 5 papers (NAACL main, Findings, and various workshops).
  • May 2024 - GMNLP will be at LREC-COLING with 1 paper on NLP for Kurdish Varieties .
  • March 2024 - GMNLP will be at EACL with 1 paper on Dialectal Translation.
  • August 2023 - GMNLP will be at EMNLP with 5 papers (EMNLP main, Findings, and various workshops).
  • August 2023 - Congratulations to Prabin Bhandari, whose paper was accepted at INLG!
  • July 2023 - Join us at ACL, were GMNLP will present 5 papers (ACL main, IWSLT; Twitter thread summary). Congratulations to Daking Rai, Hao Yan, Saurabh Srivastava, Jonathan Mbuya, and collaborator Claytone Sikasote! Papers, code, and data are online!
  • George Mason organized MASC-SLL 2023, an annual NLP event for students and researchers in the Mid-Atlantic area, on April 22!
  • January 2023 - Congratulations to Roy Xie, whose paper was accepted at EACL (Findings)! GMNLP also had another paper at the EACL main conference. Preprints are online.
  • February 2022 - GMNLP has 3 papers accepted at ACL (2 main, 1 Findings)! Preprints are online!

Courses

Projects

Our research is/has been supported by the following organizations/companies:

NSF logo NEH logo Google logo Amazon logo VRIF logo
META AI logo CCI logo ARLIS logo Microsoft logo
Foresight Institute logo 4VA logo
*
All Multilingual NLP Machine Translation OCR Fairness Language and Code Human-AI Interaction LLM Interpretability LLM Agents LLM for X Morphology Robustness Language Documentation Speech

LLM Agents

We study autonomous agents built on large language models, including tool use, planning, and multi-agent collaboration.

LLM for X

We explore applications of large language models to other disciplines and domains, such as healthcare, education, and software engineering.

LLM Interpretability

We investigate methods for understanding and interpreting the internal mechanisms and behaviors of large language models.

Reasoning and Planning

We study advanced modeling approaches for machine reasoning and planning.

Human-AI Interaction

We explore how machine learning systems can interact with humans effectively. This includes being able to converse with humans through dialogues, as well as proactively collaborate with and learn from humans during decision making.

Information Intelligence

We explore computational approaches for information intelligence tasks such as Question Answering, Information Extraction, etc.

Language and Code

We seek to build natural language interfaces that allow humans to communicate with computers/machines easily. This requires modeling natural language, programming language, and their interplay. Applications of this research include semantic parsing and general-purpose code generation.

Language Models

Language model-relevant research including prompt engineering, LLM reasoning, LLM interpretability, applications of LLMs for other disciplines, etc.

OCR

This NEH-funded project focuses on the development of modern Optical Character Recognition (OCR) and post-correction tools tailored for Indigenous Latin American Languages.

Fairness

Advances in natural language processing (NLP) technology now make it possible to perform many tasks through natural language or over natural language data – automatic systems can answer questions, perform web search, or command our computers to perform specific tasks. However, “language” is not monolithic; people vary in the language they speak, the dialect they use, the relative ease with which they produce language, or the words they choose with which to express themselves. In benchmarking of NLP systems however, this linguistic variety is generally unattested. Most commonly tasks are formulated using canonical American English, designed with little regard for whether systems will work on language of any other variety. In this work we ask a simple question: can we measure the extent to which the diversity of language that we use affects the quality of results that we can expect from language technology systems? This will allow for the development and deployment of fair accuracy measures for a variety of tasks regarding language technology, encouraging advances in the state of the art in these technologies to focus on all, not just a select few. Funded by Amazon and the NSF through the NSF-FAI program.

Speech

Most languages of the world are “oral”: they are not traditionally written and even if an alphabet exists, the community doesn’t usually use it. Hence, building NLP systems that can directly operate on speech input is paramount. At GMU NLP we work on speech transcription (ASR) and translation, as well as on building multilingual ASR systems for under-served langauges.

Morphology

Human language is marked by considerable diversity around the world, and the surface form of languages varies substantially. Morphology describes the way through which different word forms arise from lexemes. Computational morphology attempts to reproduce this process across languages, or uses machine learning models to model/discover the morphophonological processes that exist in a language.

Robustness

NLP systems are typically trained and evaluated in “clean” settings, over data without significant noise. However, systems deployed in the real world need to deal with vast amounts of noise. At GMU NLP we work towards making NLP systems more robust to several types of noise (adversarial or naturally occuring).

Language Documentation

Language Documentation aims at producing a permanent record that describes a language as used by its language community by producing a formal grammatical description along with a lexicon. Our group works on integrating NLP systems into the documentation workflow, aiming to speed-up the process and help the work of field linguists and language communities.

Machine Translation

Machine Translation is the task of translating between human languages using computers. Starting from simple word-for-word rule-based system in 1950s, we now have large multilingual neural models that can learn translate between dozens of languages. In our group we are particularly interested in MT for low-resource languages, in making MT systems robust to language variations (such as dialects or L2-speakers), in using MT for language documentation and education, and in direct speech translation.

Multilingual NLP

An exciting research direction that we pursue at GMU NLP is building multi-lingual and polyglot systems. The languages of the world often share similar characteristics, and training systems cross-lingually allows us to leverage these similarities and overcome data scarcity issues.

Recent Posts

Browse all blog posts here.

NACLO 2026 Open Round - George Mason

University Site Details

George Mason is a University Site for the NACLO 2026 Open Round. Please see below for details and instructions to participants.

Jan 25, 2026 2 min read

NACLO 2025 Open Round - George Mason

University Site Details

George Mason is a University Site for the NACLO 2025 Open Round. Please see below for details and instructions to participants.

Jan 1, 2025 2 min read

Language Technology for Crisis Preparedness and Response

June 1-2, George Mason University, Fairfax, VA.

The advent of digital era has made natural language processing (NLP) technology both promising and important for disaster response. Language technologies can, for instance, be used for triaging the need for immediate assistance based on text messages, translating vast amounts of data related to ongoing pandemics, or engage in conversations to guide natural disaster victims. However, these advances are only limited to a few dozen of the more than 6500 languages spoken or signed in the world today, neglecting millions of people and widening the "digital divide", effectively reducing the technologies' real-world utility.

Apr 1, 2023 5 min read

Predicting Performance for Natural Language Processing Tasks

This is a post regarding our paper that will be presented at ACL 2020. tl;dr: You can use previously published results to get an estimation of the performance on a new experiment, before running it! We describe NLP experiments with a set of interpretable features, and train prediction models which are actually pretty good at producing such estimations, and show how they can be useful in various scenarios.

Last updated on Aug 1, 2020 6 min read
Predicting Performance for Natural Language Processing Tasks

Should All Cross-Lingual Embeddings Speak English?

This is a post regarding our paper that got accepted at ACL 2020.

Word embeddings are ubiquitous in modern NLP, from static ones (like word2vec or fasttext) to contextual representations obtained from ELMo, BERT, and other models. One very interesting property of learned word embeddings is that, since they (ideally) model the syntactic or semantic relations between words, the embedding space that we learn in two different languages will have somewhat similar properties and structure.

Jun 1, 2020 11 min read
Should All Cross-Lingual Embeddings Speak English?
See all posts

Members

Faculty

Avatar

Ziyu Yao

Assistant Professor

LLMs for Reasoning and Planning, Interpretability of LLMs, Human-AI/LLM Interaction, Language and Code, Efficient NLP/AI, AI for Education

Avatar

Antonios Anastasopoulos

Associate Professor

Computational Linguistics, Machine Translation, Speech Recognition, NLP for Endangered Languages

Avatar

Kenton Murray

Assistant Professor

multilingual NLP, multimodal NLP, LLMs, Efficient NLP/AI

Students

Avatar

Daking Rai

PhD Student

Mechanistic Interpretability, Natural Language Processing, LLM Reasoning

Avatar

Mohamed Aghzal

PhD Student

Planning and Reasoning with Foundation Models, Explainability and Interpretability of AI Agents, Causal Inference and Causal Reasoning

Avatar

Anjishnu Mukherjee

PhD Student

Large Language Models, Fairness and Biases

Avatar

Joshua Otten

PhD Student

Natural language processing, Ancient Languages, Artificial Interlligence, Linguistics, Embedded Systems

Avatar

Syeda Sabrina Akter

CS PhD Student

Multilingual NLP, Speech Translation, NLP for Low-Resource and Endangered Languages

Avatar

Murong Yue

PhD Student

LLM Reasoning, LLM Agents, Trustworthy LLMs

Avatar

Prabin Bhandari

PhD Student

Natural language processing, Machine learning, Endangered Languages

Avatar

Hao Yan

PhD Student

Natural Language Processing, Human-AI Interaction, Code Generation, LLM Safety

Avatar

Nathaniel (Nate) Krasner

PhD Student

Natural language processing

Avatar

Ayan Antik Khan

PhD Student

Mechanistic Interpretability, AI Agents, LLM Explainability, AI Safety

Avatar

Belu Ticona

PhD Student

Natural Language Processing and Speech, Computational Social Science, Communication and Representation of Culture

Avatar

Chutong Meng

PhD Student

Speech and Language Processing

Avatar

Kourosh T Baghaei

PhD Student

Natural Language Processing, Machine Learning, Reinforcement Learning, Game Development

Avatar

Yitao Xu

PhD Student

Mechanistic Interpretability, Explainable AI, Trustworthy LLMs, AI Safety

Alumni

Avatar

Saurabh Srivastava

PhD Student → Adobe

Natural Language Processing, Machine Learning, Deep Learning

Avatar

Milind Agarwal

PhD Student → Senior Forward Deployed Engineer @ LILT AI

Natural language processing, Machine learning, Endangered Languages

Avatar

Fahim Faisal

PhD Student → Postdoc @ Oak Ridge National Lab

Computational linguistics, Natural language processing, Machine learning

Avatar

Ruoyu (Roy) Xie

Undergraduate → PhD@Duke CS

Natural Language Processing, Machine Learning, Computer Vision

Avatar

Md Mahfuz Ibn Alam

PhD Student → Term Faculty @ William & Mary

Natural Language Processing, Machine Learning, Computer Vision, Common Sense Reasoning

Avatar

Sina Ahmadi

Postdoctoral Researcher → Postdoc@U.Zurich

Computational Linguistics, NLP for Endangered Languages, Language Resources

Avatar

Jonathan Mbuya Kabala

PhD Student → Visa

Natural language processing

Avatar

Yinkai Wang

Undergraduate → PhD@Tufts

Natural Language Processing

Avatar

Sharlina Keshava

CS MSc → Amazon

Natural Language Processing, Fairness in AI, Multilingual NLP, Machine Learning, Deep Learning

Avatar

Reva Hirave

Undergraduate Student → MS CS @Princeton

Natural Language Processing, Computational Social Science and Sociolinguistics

Avatar

Wijdane Mifdal

Undergraduate

Natural Language Processing

Collaborators

Chahat Raj

CS PhD Student

NLP, ML

Claytone Sikasote

MS@African Masters of Machine Intelligence and Lecturer@University of Zambia

Language Processing for Bemba

Sam Blouir

CS PhD Student

NLP, ML

Recent Publications

Browse all publications.

Daking Rai, Ziyu Yao. An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs. ACL, 2024.

PDF Code

Mohamed Aghzal, Erion Plaku, Ziyu Yao. Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning. ICLR Workshop on Large Language Model (LLM) Agents, 2024.

PDF Code

Saurabh Srivastava, Chengyue Huang, Weiguo Fan, Ziyu Yao. Instances Need More Care: Rewriting Prompts for Instances with {LLM}s in the Loop Yields Better Zero-Shot Performance. ACL Findings, 2024.

PDF Code

Mohamed Aghzal, Erion Plaku, Ziyu Yao. Look Further Ahead: Testing the Limits of GPT-4 in Path Planning. IEEE CASE, 2024.

PDF Code

Chahat Raj, Anjishnu Mukherjee, Aylin Caliskan, Antonios Anastasopoulos, Ziwei Zhu. Breaking Bias, Building Bridges: Evaluation and Mitigation of Social Biases in LLMs via Contact Hypothesis. Proceedings AIES 2024, 2024.

PDF Code Dataset Project Project

Pooya Fayyazsanavi, Antonios Anastasopoulos, Jana Košecká. Gloss2Text: Sign Language Gloss translation using LLMs and Semantically Aware Label Smoothing. arXiv preprint, 2024.

PDF Code Project

Michael Fore, Simranjit Singh, Chaehong Lee, Amritanshu Pandey, Antonios Anastasopoulos, Dimitrios Stamoulis. Unlearning Climate Misinformation in Large Language Models. Proceedings of ClimateNLP 2024, 2024.

PDF Project

See all publications