ArgMining 2027

Monday, October 12, 2026 The 1st Call for Papers is out!

Argument mining (also known as "argumentation mining") is a well-established research area in computational linguistics that focuses on the automatic identification of argumentative structures, such as premises, conclusions, and inference schemes. Since its beginnings, the focus has been on the development of large-scale argumentation datasets and tasks like argument quality assessment, argument persuasiveness, and the synthesis of argumentative texts, spanning domains such as legal, social, medical, political, and scientific settings.

Mirroring advancements in CL and NLP at large, argument mining has expanded to explainable argumentation, multimodal settings, and modeling human label variation. The field also investigates the performance of generative models in producing and analyzing human-like argumentation. While LLMs can generate persuasive essays and convincing arguments, their ability to identify fallacies, avoid biases, and demonstrate a deeper understanding of argumentation remains an open research challenge.

Building on the previous edition's focus on understanding and evaluating arguments in both human and machine reasoning, ArgMining 2027 places a special focus on Argumentation in Agentic and Human-AI Settings. Reasoning is tightly connected to argumentation: both involve reaching conclusions on the basis of available information. Argument mining provides a framework for examining how humans and machines construct, exchange, and evaluate those reasons.

Multi-agent debate offers new ways to investigate and improve LLM reasoning, while human-AI interactive systems offer opportunities to support critical thinking and collaborative decision-making. These developments raise questions about the argumentative properties of interactions between agents and humans, and how established argumentation frameworks can help inform them. We welcome research that analyzes these interactions, develops systems to support human reasoning, or uses multi-agent debate for argument mining itself.

The 14th Workshop on Argument Mining and Reasoning will be co-located with EACL 2027 in Athens, Greece.

Program

To be announced soon.

Keynote

To be announced soon.

Panel

To be announced soon.

Important Dates

Direct paper submission deadline: December 15, 2026
Pre-reviewed ARR commitment deadline: December 22, 2026
Notification of acceptance: January 5, 2027
Camera-ready paper due: January 19, 2027
Proceedings due (hard deadline): February 9, 2027
Pre-recorded video due (hard deadline): February 12, 2027
Conference dates: March 9–14, 2027

All deadlines are 11:59 pm UTC−12 (“anywhere on Earth”).

Call for Papers

We invite submissions on computational argumentation and LLM reasoning, with a special theme on Argumentation in Agentic and Human-AI Settings. We particularly welcome work on:

Evaluation and analysis of argumentative properties of multi-agent debate
Development of human-AI interactive systems to support human reasoning and critical thinking
Application of established argumentation frameworks to agentic and human-AI interactions
Employment of multi-agent debate for argument mining tasks themselves

Topics of Interest.

The topics for submissions include but are not limited to:

Argumentation-driven agent architectures for planning, deliberation, negotiation, and collaborative decision-making
Multi-agent debate protocols and analysis of support, attack, rebuttal, and consensus across interacting agents
Construction, completion, and evaluation of argument graphs from human dialogues and multi-agent reasoning traces
Graph-based representations of claims, evidence, and argumentative relations for agent reasoning and explanation
Integration of knowledge graphs with argument graphs to ground claims, track evidence provenance, and resolve conflicting information
Retrieval-augmented and tool-using agents for evidence-based argument generation, verification, and counterargument construction
Human-AI co-construction and critique of arguments, including interactive argument mapping and support for critical thinking
Evaluation of argument quality, faithfulness, robustness, and diversity in multi-agent deliberation, including sycophancy and error propagation
Automatic extraction of textual patterns that describe argument components in human and machine argumentation
Cross-lingual, cross-cultural and multi-perspective argument mining and reasoning
Argument mining and generation from multi-modal and/or multilingual data
Explainability in argument mining through reasoning
Modeling, assessing, and critically reflecting on the argumentation capabilities of LLMs
Novel benchmarks in argument mining that cater to the recent developments in LLM reasoning as a whole
Guidelines for assessing and documenting the reasoning process(es) reflected in benchmarks
Annotation guidelines, linguistic analysis and argumentation corpora
Real-world applications, e.g., supporting analysis of argument and discourse in the social sciences, education, law, or scientific writing; opinion analysis, argument analysis in meetings, and misinformation detection
Integration of commonsense and domain knowledge into argumentation models for mining and generation
Combination of information retrieval methods with argument mining, e.g., in order to build argumentative (web) search engines
Reflection on ethical aspects and societal impact of argument mining and LLM reasoning

We welcome submissions from all areas of application.

Submission Details.

The organizing committee welcomes submitting long papers, short papers, extended abstracts and PhD proposals. Accepted papers will be presented via oral or poster presentations. Long and short papers will be included in the ACL proceedings as workshop papers. Extended abstracts and PhD proposals will be non-archival.

Archival submissions.

Long paper submissions must describe substantial, original, completed, and unpublished work. Wherever appropriate, concrete evaluation and analysis should be included. Long papers must be at most eight pages, including title, text, figures, and tables. An unlimited number of pages is allowed for references. Two additional pages are allowed for appendices, and an extra page is allowed in the final version to address reviewers’ comments.

Short paper submissions must describe original and unpublished work. Please note that a short paper is not a shortened long paper. Instead, short papers should have a point that can be made in a few pages, such as a small, focused contribution, a negative result, or an interesting application nugget. Short papers must be at most four pages, including title, text, figures, and tables. An unlimited number of pages is allowed for references. One additional page is allowed for the appendix, and an extra page is allowed in the final version to address reviewers’ comments.

Non-Archival submissions.

Extended abstracts must be at most two pages including references and an additional page as an appendix for tables/figures describing ongoing projects, interesting pieces of data or results, or already published work. While selecting the abstracts, we will keep two constraints in mind: a) Fit to the workshop, in particular to the special theme "Argumentation in Agentic and Human-AI Settings"; b) Priority to papers with doctoral students as 1st authors that could not be presented at a *CL conference due to visa restrictions.

PhD proposals must describe PhD projects being or to be developed within the broad field of natural language argumentation processing. PhD proposals must be at most four pages including the main research directions or challenges being investigated, the specific contributions made (on the research direction), and the directions for the remaining work. A dedicated poster session will be hosted, allowing students to get feedback and discuss their work with a broad and multidisciplinary community.

Multiple Submissions.

ArgMining 2027 will not consider any paper under review in a journal or another conference or workshop at the time of submission, and submitted papers must not be submitted elsewhere during the review period.

ArgMining 2027 will accept submissions of ARR-reviewed papers, provided that the ARR reviews and meta-reviews are available by the ARR commitment deadline. However, ArgMining 2027 will not accept direct submissions that are actively under review in ARR, or that overlap significantly (>25%) with such submissions.

Submission Format.

All submissions must follow the two-column ACL style guidelines and templates. Submissions must be electronic and in PDF format.

Submission Links.

Submissions will be made through OpenReview. We will accept direct submissions, commitments of ARR-reviewed papers, and non-archival submissions.

To be announced soon.

Double Blind Review.

ArgMining 2027 will follow the ACL policies preserving the integrity of double-blind review for long and short paper submissions. Papers must not include authors' names and affiliations. Furthermore, self-references or links (such as GitHub) that reveal the author’s identity, e.g., “We previously showed (Smith, 1991) …” must be avoided. Instead, use citations such as “Smith previously showed (Smith, 1991) …” Papers that do not conform to these requirements will be rejected without review. Papers should not refer, for further detail, to documents that are not available to the reviewers. For example, do not omit or redact important citation information to preserve anonymity. Instead, use the third person or named reference to this work, as described above (“Smith showed” rather than “we showed”). Papers may be accompanied by a resource (software and/or data) described in the paper, but these resources should also be anonymized. Unlike long and short papers, demo descriptions will not be anonymous. Demo descriptions should include the authors’ names and affiliations, and self-references are allowed.

Anonymity Period

We follow the ACL Policies for Review and Citation. Submissions must be anonymized, but there is no anonymity period or limitation on posting or discussing non-anonymous preprints while the work is under peer review.

Best Paper Award.

In order to recognize significant advancements in argument mining science and technology, ArgMining 2027 will include the Best Paper award. All papers at the workshop are eligible for the best paper award, and a selection committee consisting of prominent researchers in the fields of interest will select the award recipients.