Call for Papers

We invite submissions to the 3rd Conference on Language Modeling (COLM).

Submission link: https://openreview.net/group?id=colmweb.org/COLM/2026/Conference/Authors (opens in February 2026)

Questions can be directed to: [email protected]

Key Dates

All deadlines are 23:59 AoE (anywhere on earth)

  • Abstract deadline: Thursday, March 26, 2026
  • Full paper submission deadline: Tuesday, March 31, 2026
  • Rebuttal period: May 22 to June 8, 2026
  • Decision notifications: July 8, 2026
  • Conference dates: October 6-9, 2026

We consider a broad range of subject areas focused on language modeling for the second iteration of COLM. We consider the term "language model" in the broadest way. A non-exhaustive list of topics of interests includes:

  1. All about training: fine-tuning, instruction-tuning, reinforcement learning, prompt tuning, and in-context learning
  2. All about data: all types of data for pre-training, post-training, and other training stages
  3. All about evaluation: benchmarks (static and dynamic), simulation environments, scalable oversight, evaluation protocols and metrics, human and/or machine evaluation, evaluation for bias/equity/potential for misuse
  4. All about safety: security, privacy, misinformation, adversarial attacks and defenses
  5. Science of LMs: scaling laws, fundamental limitations, emergent capabilities, interpretability, training dynamics, grokking, learning theory for LMs
  6. Compute efficient LMs: distillation, compression, quantization, sample efficient methods, memory efficient methods
  7. Engineering for large LMs: distributed training and inference on different hardware setups, training dynamics, optimization instability
  8. Learning algorithms for LMs: learning (SFT/RL/etc.), unlearning, meta learning, model mixing methods, continual learning
  9. Inference algorithms for LMs: decoding algorithms, reasoning algorithms, search algorithms, planning algorithms
  10. Human mind, brain, philosophy, laws and LMs: cognitive science, neuroscience, linguistics, psycholinguistics, philosophical, or legal perspectives on LMs
  11. LMs with tools and code: integration with tools and APIs, LM-driven software engineering
  12. LMs for everyone: multilinguality, dialects, low-resource languages, vernacular languages, multiculturalism, value pluralism, fairness
  13. LMs and the world: factuality, retrieval-augmented LMs, knowledge models, commonsense reasoning, theory of mind, social norms, pragmatics, and world models
  14. Multimodal LMs: multimodality, perception, audio, time series, and other modalities, both for reasoning and synthesis.
  15. LMs and embodiment: perception, action, and robotics
  16. LMs and interactions: conversation, interactive learning, and multi-agents learning
  17. LMs on diverse domains and novel applications: medicine, education, science, and beyond

Review Process

Submissions will be double blind: reviewers and ACs cannot see author names when conducting reviews, and authors cannot see reviewer and AC names. This means that the submission must not contain acknowledgments or any link (e.g., github) that would reveal authors' identity.

We will use OpenReview to manage submissions. The reviews and author responses will not be public initially. Submissions under review will be visible only to their assigned program committee. We will not be soliciting comments from the general public during the reviewing process. Accepted papers and their reviews will be made public after decisions are made. Discussions between reviewers and program committee members and with the authors of accepted papers will be made public. Rejected or withdrawn papers, their discussions and meta data will not be published.

Anyone who plans to submit a paper as an author or a co-author will need to create (or update) their OpenReview profile by the abstract submission deadline. The information entered in the profile is critical for ensuring that conflicts of interest are handled properly.

The program will include oral presentations and posters of accepted papers. Authors can revise their paper as many times as needed up to the paper submission deadline. Changes to the paper will not be allowed while the paper is being reviewed.

Ethics Review

Reviewers and ACs may flag submissions for ethics review. Flagged submissions will be sent to an ethics review committee for comments. Comments from ethics reviewers will be considered by the primary reviewers and AC as part of their deliberation. They will also be visible to authors, who will have an opportunity to respond. Ethics reviewers do not have the authority to reject papers, but in extreme cases papers may be rejected by the program chairs on ethical grounds, regardless of scientific quality or contribution.

Submission Instructions

Authors must submit paper abstracts by the abstract submission deadline. Please make sure that all authors have an OpenReview profile with up-to-date information. Abstracts submitted by the abstract submission deadline must be genuine; placeholder or duplicate abstracts will be removed. Please avoid meaningfully changing (i.e., making more than minor changes to) your abstract and title after the abstract deadline. Such changes will likely lead to sub-optimal assignment of AC and reviewers to your paper, hurting the quality of reviewing your paper will receive. The complete paper must be submitted by the full paper submission deadline, after which the modification of submissions will be locked, except for withdrawal. Please triple-verify the list of authors – no modification of authors is possible after the submission deadline for any reason.

Paper Length and Template

There is a strict upper limit of 9 pages for the main text of the submission, with unlimited additional pages for citations.

  • Authors may use as many pages of appendices (after the bibliography) as they wish, but reviewers are not required to read the appendix.
  • Authors can add an optional ethics statement to the paper; it will not count toward the page limit, but should not be more than 1 page.
  • Authors can add an optional reproducibility statement as well, which will not count toward the page limit, but should not be more than 1 page.
  • The optional acknowledgment will not count toward the page limit, but should not be more than 1 page.

Authors are required to follow the formatting directives of the template, including the font specifications, title formatting, and margin settings.

Style Files and Templates

To prepare your submission to COLM 2026, please use the LaTeX style files provided at:

https://github.com/COLM-org/Template/releases/tag/2026

Reciprocal Reviewing

COLM has two reciprocal reviewing requirements: a 'per-submission' requirement, and a 'per-reviewer' requirement.

Per-submission: Each submission is expected to contribute a reviewer to the pool. ​Multiple submissions cannot have the same reciprocal reviewer, unless all other authors do not qualify or are serving in other roles. The submission form will allow submitters to designate an author to fulfill the per-submission requirement, or to indicate that the submission is exempt from the requirement.

Per reviewer: Any author with 4 or more submissions will automatically be added to the reviewer pool, unless they are already part of the program committee or the COLM organization.

More information about this requirement and its rationale is available in our FAQ.

Guides and Policies

Conflict of Interest Policy. The COLM program committee and all submitting authors must follow the COLM conflict of interest policy (https://colmweb.org/coi-policy.html). Please consult the policy to update your OpenReview profile as requested.

Author Guidelines. Authors are expected to follow the COLM Author Guide (https://colmweb.org/AuthorGuide.html).

AC Guidelines. Authors are expected to follow the COLM Author Guide (https://colmweb.org/ac-guidelines.html).

Code of Conduct. All COLM participants, including authors, are required to adhere to the COLM code of conduct (https://colmweb.org/CoC.html). More detailed guidance for authors, reviewers, and all other participants will be made available in due course, and participation will require acknowledging and adhering to the provided guidelines.

Code of Ethics. All participants of COLM, including the submission and reviewing process, must abide by COLM’s code of ethics (https://colmweb.org/CoE.html).

Policy on the use of Large Language Models: COLM 2026 will adopt the ICLR 2026 Policy on Large Language Model Usage, modified to not require LLM disclosure for minor assistance in the paper writing or code implementation of a paper. Our policy is:

Policy 1. Disclosure of LLM use in both research and reviewing.

  1. In research, use of LLMs should be disclosed in the submitted paper, except for minor usage in paper writing or code implementation.
    🛑Must be disclosed: using an LLM to originate research ideas, using an LLM to write original content in the paper (including references), using an LLM to generate data or plots, using an LLM for evaluation
    🟢Okay not to disclose: using automated grammar-checking tools, feeding a paragraph to an LLM and asking it to fix typos, programming with a tool like CoPilot or Cursor.
  2. In reviewing, any use of an LLM should be disclosed, whether cosmetic or not.

Policy 2. COLM authors and reviewers are ultimately responsible for their contributions, following the Code of Ethics policy that “researchers must not deliberately make false or misleading claims, fabricate or falsify data, or misrepresent results.”

(These policies are also consistent with arXiv’s policy on LLM use, which was previously used at COLM 2025.)

More detailed guidelines are forthcoming.

Reviewing Guidelines. Reviewers and area chairs will be asked to follow the COLM reviewing guidelines (https://colmweb.org/ReviewGuide.html).

OpenReview User Moderation Policy. New profiles created without an institutional email will go through a moderation process that can take up to two weeks. New profiles created with an institutional email will be activated automatically.

Submission cap: No single person can be an author on more than 25 submissions to COLM.

Double submission policy: Full papers submitted to COLM (i.e., those in the review process after the abstract deadline has passed) cannot be under review for another conference simultaneously. If your paper was submitted to another venue such as ICML, it must be withdrawn from that venue prior to the COLM full paper submission deadline. If you want to submit your paper to another venue after COLM, you must withdraw it from COLM prior to submitting the full paper to that venue. Concurrent submissions to non-archival workshops (i.e., workshops without proceedings) do not count as double submissions for the purpose of this policy.