iiinova — where your digital self keeps evolving

Computational Linguistics Journal @complingjournal.bsky.social · 31/08/2026

While we're waiting for the next issue of the CL journal, feel free to check the upcoming articles, using the @mitpress.bsky.social online early: direct.mit.edu/coli/online-... #CLJorunal #NLProc

041

Computational Linguistics Journal @complingjournal.bsky.social · 30/08/2026

For those interested in grammars, esp. weak generative capacity, this squib has some novel insights. It demonstrates that the proofs given in prominent and well-established weak generative capacity arguments for natural language are flawed: doi.org/10.1162/COLI... #CLJournal #NLProc

070

Computational Linguistics Journal @complingjournal.bsky.social · 25/08/2026

CL journal has long accepted some articles as "squib". In absolute terms, an squib is "A short, witty, or satirical piece of writing". That is almost what we expect. Squibs is reserved for very short articles that constitute more than programmatic versions of regular papers. (1/3) #CLJournal #NLProc

1102

Computational Linguistics Journal @complingjournal.bsky.social · 24/08/2026

Have you wondered if personally identifiable information removal techniques truly protect privacy in real-world scenarios? The authors of this article suspect that reported success of these attacks is largely overestimated. Read what they find here: doi.org/10.1162/COLI... @ivanhabernal.bsky.social

051

Computational Linguistics Journal @complingjournal.bsky.social · 23/08/2026

Real-world tasks often involve complex, multi-step instructions that remain challenging for current NLP systems. This article provides a comprehensive survey that systematically analyses the landscape of complex instruction understanding & processing: doi.org/10.1162/COLI... #CLJournal #NLProc

050

Computational Linguistics Journal @complingjournal.bsky.social · 17/08/2026

How do LLMs compare against other semantic measure algorithms in assessing semantic relation (SR) strength? Are LLMs’ evaluations of SRs influenced by exposure to datasets during training? Can SR dataset characteristics influence the performance of LLMs?Answers in: doi.org/10.1162/COLI... #CLJournal

030

Computational Linguistics Journal @complingjournal.bsky.social · 14/08/2026

If you're an author of an upcoming paper in the CL journal, please make yourself known (follow us or make your affiliation and field clear in your profile), so we can tag you when your paper is out! Thanks! #NLPRoc #CLJournal PS. Ok, the photo is from the past, but hope it gets your attention 🙃

083

Computational Linguistics Journal @complingjournal.bsky.social · 13/08/2026

Mis- and disinformation continue to propagate online & cause significant harm due to the rapid evolution of such content. Out-of-Distribution generalisation datasets can be very difficult to build & this is the major focus of this paper: doi.org/10.1162/COLI... #CLJournal @ioverho.eurosky.social

050

Computational Linguistics Journal @complingjournal.bsky.social · 10/08/2026

Have you noticed that preference datasets in reinforcement learning/DPO are not fully utilised? This article proposes a framework called Vote-based Preference Optimisation that leverages user voting data to better align language models with diverse subjective preferences: doi.org/10.1162/COLI...

021

Computational Linguistics Journal @complingjournal.bsky.social · 05/08/2026

Do you know what Multimodal OXYmorons are? If you're curious, read this research, which introduces this concept by constructing and communicating meaning through the interplay of multiple modalities: doi.org/10.1162/COLI... #CLjournal #NLProc @elidp.bsky.social

020

Computational Linguistics Journal @complingjournal.bsky.social · 04/08/2026

This paper introduces a wide range of encodings for constituent parsing as sequence adaptations of parsers from other paradigms that had not previously been cast under the sequence-labeling framework. Code: github.com/Polifack/CoD... and paper:https://doi.org/10.1162/COLI.a.603 @carlosg.bsky.social

141

Computational Linguistics Journal @complingjournal.bsky.social · 03/08/2026

How do prompt language and cultural framing influence model responses and their alignment with human values in different countries? Answer to this and more insights at: doi.org/10.1162/COLI... #NLProc #CLjournal @aylart.bsky.social

061

Computational Linguistics Journal @complingjournal.bsky.social · 17/07/2026

🏆The Computational Linguistics High Impact Paper Award recognises papers published in Computational Linguistics within the past 3–5 years that have already demonstrated exceptional scholarly impact. Congratulations to the authors of doi.org/10.1162/coli... #NLProc #CLjournal @chrmanning.bsky.social

093

Computational Linguistics Journal @complingjournal.bsky.social · 13/07/2026

🏆 2026 Computational Linguistics Distinguished Reviewer Awards: It aims to highlight and promote high standards in peer review and to acknowledge reviewers whose contributions have had a meaningful impact on the quality of our journal. Congratulations to our 2026 awardees! #NLProc #CLjournal

063

Computational Linguistics Journal @complingjournal.bsky.social · 10/07/2026

The ACL Computational Linguistics Doctoral Dissertation Award (ACL Dissertation Award) recognises three honourable mentions: Dennis Ulmer, Shen-Chieh Lin, and Haoran Xu. Congratulations to all three for this achievement! #NLproc #CLJournal @dnnslmr.bsky.social

071

Computational Linguistics Journal @complingjournal.bsky.social · 09/07/2026

We are pleased to announce the winner of the ACL Computational Linguistics Doctoral Dissertation Award (ACL Dissertation Award)! Congratulations, Verna Dankers! @vernadankers.bsky.social #NLproc #CLJournal

0132

Computational Linguistics Journal @complingjournal.bsky.social · 02/07/2026

She shared invaluable research strategies that can help lead to success, and she encouraged every researcher never to take no for an answer. Her speech is published here: doi.org/10.1162/COLI... #CLJournal #NLProc

020

Computational Linguistics Journal @complingjournal.bsky.social · 02/07/2026

The second issue of Computational Linguistics Journal (Volume 52, Issue 2, June 2026) is finally out! Read it here: direct.mit.edu/coli/issue/5.... We'll introduce all the articles one by one soon. #CLJournal #NLProc

050

Computational Linguistics Journal @complingjournal.bsky.social · 24/05/2026

CL Journal has over 50 years of history in the field. While the field is moving, some of the articles from decades ago provide perspective and still relevant content. What do you think of these articles from 20 and 40 years ago? (2006 and 1986) & yes, they used to come in paper format too! #NLProc

2114

Computational Linguistics Journal @complingjournal.bsky.social · 14/05/2026

Like humans, LLMs can be right for the wrong reasons. They can also be wrong for the wrong reasons. Anthropocentric bias has gone largely unexamined, posing a serious obstacle to the objective assessment of LLM capacities. Read more at doi.org/10.1162/COLI... #NLProc #CLJournal @raphaelmilliere.com

0167

Computational Linguistics Journal @complingjournal.bsky.social · 13/05/2026

Interpretability provides a toolset for understanding how and why LMs behave in certain ways. This survey proposes a perspective on interpretability research grounded in causal mediation analysis: doi.org/10.1162/COLI... #NLProc #CLJournal @jannikbrinkmann.bsky.social @amuuueller.bsky.social

0111

Computational Linguistics Journal @complingjournal.bsky.social · 12/05/2026

How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text? This article explores a very important question for low-resource languages by experimenting with various techniques across 10 languages. A must-read at:https://doi.org/10.1162/COLI.a.581 @gucciiiii.bsky.social

040

Computational Linguistics Journal @complingjournal.bsky.social · 11/05/2026

Should NLP metrics for bilingual code-switching use words as the token level or Intonation Units? Authors of this article show that intonation units will enhance comparisons between bilingual individuals, settings, and communities: doi.org/10.1162/COLI... #NLProc #NLP @pennlinguistics.bsky.social

010

Computational Linguistics Journal @complingjournal.bsky.social · 11/05/2026

Have you heard of soft metrics such as soft micro F1? In this article, the authors argue that for evaluating model predictions with human label variation, the standard metrics may not be sufficient. Read more at: doi.org/10.1162/COLI... @kmkurn.sigmoid.social.ap.brid.gy #NLProc #NLP

061

Computational Linguistics Journal @complingjournal.bsky.social · 11/05/2026

To assess whether multilingual NLP performs well across languages, we need to evaluate it on all world languages.That is not feasible.This paper implements two sampling methods from linguistic typology and provides a Python package to facilitate this: doi.org/10.1162/COLI... @andreashhp.bsky.social

073

Computational Linguistics Journal @complingjournal.bsky.social · 05/05/2026

Developing methods to assess the factuality of LLMs has become urgent. This paper presents LLM-OASIS for the factuality evaluation task. It turns out it significantly challenges SOTA LLMs. If you're up for improving over what's out there, start reading: doi.org/10.1162/COLI... #CLjournal #NLProc

010

Computational Linguistics Journal @complingjournal.bsky.social · 05/05/2026

Language Models are susceptible to adversarial attacks, where even subtle perturbations to input texts adversely affect model performance. Yang et al. propose a novel method to tackle this called Defensive Dual Masking (DDM). Read more at: doi.org/10.1162/COLI... #NLProc #NLP

010

Computational Linguistics Journal @complingjournal.bsky.social · 04/05/2026

Do current LLMs with fast-improving functional linguistic abilities exhibit distinct localization of formal (e.g., producing fluent, grammatical text) and functional (e.g., reasoning and consistent fact retrieval) linguistic mechanisms? Answer in: doi.org/10.1162/COLI... @michaelwhanna.bsky.social

060

Computational Linguistics Journal @complingjournal.bsky.social · 04/05/2026

Have you heard of linguistic steganography? It seeks to conceal secret information within natural language text. Liu et al. propose a novel method called SA-ANS. It's a self-adaptive framework based on a self-adjusting Asymmetric Numeral System: doi.org/10.1162/COLI... #NLProc #NLP

040

Computational Linguistics Journal @complingjournal.bsky.social · 03/05/2026

If your research is around metaphor detection and interpretation, this article is for you! It introduces Meta4XNLI, the first parallel dataset for Natural Language Inference (NLI), in both English and Spanish: doi.org/10.1162/COLI... #NLProc @ragerri.bsky.social

0123

Computational Linguistics Journal @complingjournal.bsky.social · 02/05/2026

What % of the NLP papers measure their impact in the real world? This paper proposes an impact evaluation of NLP models or systems for real-world usage, changing the research culture of NLP to focus more on real-world impact and less on SOTA-chasing: doi.org/10.1162/COLI... @ehudreiter.bsky.social

0146

Computational Linguistics Journal @complingjournal.bsky.social · 01/05/2026

Hallucinations pose a substantial challenge to the reliability of LLMs in real-world scenarios. Zhang et al. survey methods of detection, explanation, & mitigation of hallucination, & provide a taxonomy & list of benchmarks for evaluation in this paper: doi.org/10.1162/COLI... @fredashi.bsky.social

031

Computational Linguistics Journal @complingjournal.bsky.social · 01/05/2026

Generative AI has advanced. But, for complex problems, it's lagging. In this position paper, the authors propose Human–AI Co-Construction (HAI-Co2), a framework for human–AI cooperative problem solving that facilitates such interaction. Read more at: doi.org/10.1162/COLI... @igurevych.bsky.social

150

Computational Linguistics Journal @complingjournal.bsky.social · 01/05/2026

Tasks such as summarization, QA & timeline creation need temporal expression normalization. The authors propose a novel method that deals with the known problems of temporal expression normalization on data scarcity, language and domain adaptation: doi.org/10.1162/COLI... @jmartinezromo.bsky.social

010

Computational Linguistics Journal @complingjournal.bsky.social · 30/04/2026

Have you heard of BLiMP for evaluating English LMs? Well, the authors of this paper introduce the Dutch version: BLiMP-NL. It's a benchmark set of linguistic minimal pairs for grammatical evaluation of Dutch LMs. Read more at: doi.org/10.1162/COLI... @stefanfrank.bsky.social @illc-uva.bsky.social

030

Computational Linguistics Journal @complingjournal.bsky.social · 30/04/2026

Interested in the semantic neighborhood of words? LGDE is a graph-based, local-diffusion framework for the discovery of keywords that are semantically similar to a seed dictionary. The authors release their code and data for a hate speech dataset too: doi.org/10.1162/COLI... #NLP

030

Computational Linguistics Journal @complingjournal.bsky.social · 29/04/2026

Tokenisation and Finite-State Transducers are two well-known concepts in computing. This article combines them for neural networks. Cognetta & Okazaki introduce a finite-state transduction framework that can encode all possible tokenizations of a regular language: doi.org/10.1162/COLI... #NLProc

020

Computational Linguistics Journal @complingjournal.bsky.social · 29/04/2026

Are you looking for measuring "syntactic diversity"? Martin, in this article, proposes derivational entropy rate, a metric that links grammar’s derivational entropy and the mean length of the utterances (MLU). Check it out: doi.org/10.1162/COLI... #NLProc

072

Computational Linguistics Journal @complingjournal.bsky.social · 29/04/2026

Private attributes of writers, such as age or native language, can be detectable. The authors of this article propose IDT (Interpretable Dual-Task), a method based on adversarial attacks for rewriting text to prevent detection of such private attributes: doi.org/10.1162/COLI... #NLP #NLProc

020

Computational Linguistics Journal @complingjournal.bsky.social · 29/04/2026

Tokenisation and Finite-State Transducers are two well-known concepts in computing. This article comes them for neural networks. They introduce a finite-state transduction framework that can encode all possible tokenizations of a regular language: doi.org/10.1162/COLI... #NLProc #NLP

020

Computational Linguistics Journal @complingjournal.bsky.social · 27/04/2026

LLMs transformed our field. This article addresses (1) ways to better understand how LLMs work & (2) ways to rethink how the next generation of models should use data at scale. Authors also propose SILO to advance responsible data use: doi.org/10.1162/COLI... @sewonm.bsky.social #NLP #NLProc

040

Computational Linguistics Journal @complingjournal.bsky.social · 26/04/2026

NLP relies on Linguistics & that's capital RELIES! It encapsulates 6 major facets where linguistics contributes to NLP: Resources, Evaluation, Low-resource settings, Interpretability, Explanation, & the Study of language. Read it at doi.org/10.1162/coli... @nlopitz.bsky.social @complingy.bsky.social

0203

Computational Linguistics Journal @complingjournal.bsky.social · 26/04/2026

Have you read the book "Automated Essay Scoring" by Beata Beigman Klebanov and Nitin Madnani? The review of this book by Anaïs Tack could give you a glimpse of this great book: doi.org/10.1162/coli... #NLProc #NLP @haikumana.bsky.social

031

Computational Linguistics Journal @complingjournal.bsky.social · 26/04/2026

What is cultural awareness in LLMs & what has been done in the literature for creating cross-cultural datasets, strategies for cultural inclusion & methodologies that have been used for benchmarking cultural awareness? This survey answers all these questions: doi.org/10.1162/COLI... #NLProc

042

Computational Linguistics Journal @complingjournal.bsky.social · 26/04/2026

Is there a relationship between bias and fundamental properties of LLMs? While LLMs are powerful, they contain harmful biases that can emerge unpredictably in their behavior. Read more on this in this thought-provoking position paper: doi.org/10.1162/coli... #NLProc #NLP

0175

Computational Linguistics Journal @complingjournal.bsky.social · 24/04/2026

Hierarchical topic models (HTM) depend heavily on data representation and topic evaluation. Viegas et al. demonstrate that HTMs, by nature, demand novel ways of evaluating the quality of topics. Interested? Read it at: doi.org/10.1162/coli... #NLPRoc

030

Computational Linguistics Journal @complingjournal.bsky.social · 24/04/2026

An unsupervised approach to chunking removes the need for manual annotations. This drives the paper proposing a Hierarchical Recurrent Neural Network (HRNN) designed to model word-to-chunk and chunk-to-sentence compositions. Want to know more? Read it here: doi.org/10.1162/coli... #NLProc

030

Computational Linguistics Journal @complingjournal.bsky.social · 24/04/2026

Do subword tokens influence how LLMs represent the meanings of words and characters? Do LLMs “know” about the composition of Chinese characters? Do they recognize and utilize correspondences between radicals and initial tokens? Answers to these questions at doi.org/10.1162/coli... #NLProc

030

Computational Linguistics Journal @complingjournal.bsky.social · 24/04/2026

Argument structure analysis helps to understand human argumentation. Bao et al. present a unified generative framework for this: UniASA. It can uniformly address multiple argument structure analysis tasks in a seq2seq manner. Read about it here: doi.org/10.1162/coli... #NLProc @aixinsg.bsky.social

041

Computational Linguistics Journal @complingjournal.bsky.social · 23/04/2026

The primary goal of an adversarial attack is to change a model’s prediction. Can we automatically detect adversarial sentences? Tonni et al introduce a novel dataset of Likert-scale human evaluations on the suspiciousness of adversarial sentences. More at: doi.org/10.1162/coli... #NLProc #NLP

010