The 2025 Conference on Empirical Methods in Natural Language Processing

Date: 05-Nov-2025 - 09-Nov-2025
Location: Suzhou, China
Meeting URL: https://2025.emnlp.org

Linguistic Field(s): Computational Linguistics

EMNLP 2025 will be held in Suzhou, China from November 5th to November 9th, 2025. EMNLP 2025 invites the submission of long and short papers featuring substantial, original, and unpublished research on empirical methods for Natural Language Processing. EMNLP 2025 has a goal of curating a diverse technical program—in addition to traditional research results, papers may contribute negative findings, survey an area, announce the creation of a new resource, argue a position, report novel linguistic insights derived using existing computational techniques, and reproduce, or fail to reproduce, previous results.

Paper Submission Information
Note that we are following a new ARR cycle schedule (5 cycles/year)! Papers may be submitted to the ARR 2025 May cycle. Papers that have received reviews and a meta-review from ARR (whether from the ARR 2025 May cycle or an earlier ARR cycle) may be committed to EMNLP via the commitment link.

Important Dates for EMNLP 2025
* ARR submission deadline (long & short papers): May 19, 2025
* Commitment deadline: July 31, 2025
* Notification of acceptance (long & short papers): August 20, 2025
* Camera-ready papers due (long & short): September 19, 2025
* Main Conference (dates for Workshops/Tutorials TBD): November 5-9, 2025

Submission Topics

EMNLP 2025 aims to have a broad technical program. Relevant topics for the conference include, but are not limited to, the following areas:

* Safety and Alignment in LLMs
* AI/LLM Agents
* Human-AI Interaction/Cooperation
* Retrieval-Augmented Language Models
* Mathematical, Symbolic, and Logical Reasoning in NLP
* Computational Social Science, Cultural Analytics, and NLP for Social Good
* Code Models
* Interpretability, Model Editing, Transparency, and Explainability
* LLM Efficiency
* Generalizability and Transfer
* Dialogue and Interactive Systems
* Discourse, Pragmatics, and Reasoning
* Low-resource Methods for NLP
* Ethics, Bias, and Fairness
* Natural Language Generation
* Information Extraction and Retrieval
* Linguistic theories, Cognitive Modeling and Psycholinguistics
* Machine Translation
* Multilinguality and Language Diversity
* Multimodality and Language Grounding to Vision, Robotics and Beyond
* Neurosymbolic approaches to NLP
* Phonology, Morphology and Word Segmentation
* Question Answering
* Resources and Evaluation
* Semantics: Lexical, Sentence-level Semantics, Textual Inference and Other areas
* Sentiment Analysis, Stylistic Analysis, and Argument Mining
* Speech Processing and Spoken Language Understanding
* Summarization
* Hierarchical Structure Prediction, Syntax, and Parsing
* NLP Applications
* Special Theme: Interdisciplinary Recontextualization of NLP

EMNLP 2025 Theme Track: Interdisciplinary Recontextualization of NLP
The core interests of the ACL community are rooted in human-language technologies but also have broad reach into other fields. A couple of recent examples are the burgeoning areas of Code models and Vision models. Earlier cases are exemplified through SIGs connected with the fields of education, medicine, and humanities. Movements such as NLP for Social Good and Computational Social Science show a desire for broad impact, which requires expertise beyond the borders of our own community to achieve. This year’s theme of Advancing our Reach: Interdisciplinary Recontextualization of NLP aims to highlight this need for broader connections with other fields to understand and intensify NLP’s impact. The goal is to increase our awareness of how advances in NLP can impact other fields, and design better strategies to measure that impact both within and across disciplines.

Over the past two decades, the field has advanced at an exponential rate. The term language models is now a household word, industry is booming, and the publication rate is dizzying, but what does that mean about fundamental scientific impact and broader impact on real societal problems? How can we measure that in a rigorous way? Scores on benchmarks are increasing, however, to what extent do our benchmarks reflect the true impact of our technology advances? If we make a distinction between impact within our own field versus impact from our field into other fields, would we see the same magnitude of growth? The conventional measures of success don’t facilitate making critical distinctions, like incremental improvement versus transformative change, or within-field uptake versus broad impact across fields.

So this year we invite engagement with the theme first through theme-specific submission tracks for papers addressing the fundamental technology advances and papers addressing the evaluation methodology issues. However, we also invite Fireside Chat session proposals designed to bring together NLP researchers with leaders from other fields for agenda setting and new collaboration formation. Finally, we invite multi-disciplinary panel proposals that provide opportunities to engage the broader community in reflection related to the theme.

Contact Information
General Chair: Dirk Hovy, Bocconi University

Program Chairs:
Christos Christodoulopoulos, Amazon
Tanmoy Chakraborty, Indian Institute of Technology Delhi
Carolyn Rose, Carnegie Mellon University
Violet Peng, University of California, Los Angeles

For questions related to paper submission, and the review process in general, email: [email protected]

For questions about commitment and post review related topics, email: [email protected]

For more information on the conference and submission process, please see the full call for papers: https://2025.emnlp.org/calls/main-conference-papers/