General

New publication at SoftwareX

We are pleased to inform you about the acceptance of the following SoftwareX paper:

Patrick Schrottenbacher, Daniel Baumartz, Giuseppe Abrami, Alexander Mehler and Sebastian Gombert. 2026. MMAnnotator: Enhancing the annotation of web documents in the field of educational sciences with a RAG chatbot. SoftwareX, 36:103188.
BibTeX
@article{Schrottenbacher:et:al:2026:c,
  title     = {MMAnnotator: Enhancing the annotation of web documents in the
               field of educational sciences with a RAG chatbot},
  journal   = {SoftwareX},
  volume    = {36},
  pages     = {103188},
  year      = {2026},
  issn      = {2352-7110},
  doi       = {https://doi.org/10.1016/j.softx.2026.103188},
  url       = {https://www.sciencedirect.com/science/article/pii/S2352711026006783},
  author    = {Patrick Schrottenbacher and Daniel Baumartz and Giuseppe Abrami
               and Alexander Mehler and Sebastian Gombert},
  keywords  = {Multimodal annotation, Linguistic annotation, LLM-assisted annotation, Retrieval-augmented generation, Educational science, core_c08, FACES},
  abstract  = {Generative AI has led to changes in linguistic annotation. Tasks
               that previously required human annotation can now be automated.
               As LLMs become more capable, the problems they can address become
               more complex. LLM-based chatbots present new opportunities: Annotators
               can ask the bot questions and request explanations within the
               UI. This is highly relevant for multimodal annotation, given that
               only a few platforms support the annotation of different modalities.
               We introduce MMAnnotator, a MultiMedia annotation system aiming
               to fill this gap. It allows for linguistic and multimodal annotation
               with the help of a chatbot. We demonstrate MMAnnotator in the
               field of educational sciences and provide a user study for evaluation.}
}

New publications at ArabicNLP 2026 Shared Tasks

We are pleased to inform you about the acceptance of papers at ArabicNLP 2026 Shared Tasks

Bhuvanesh Verma, Ali Abusaleh and Alexander Mehler. October, 2026. TTLab at StanceEval-2026: A Cloze-Style Prompting Approach for Arabic-Language Stance Detection (CLASP-Ar). Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks, 511–518.
BibTeX
@inproceedings{Verma:et:al:2026:CLASP,
  title     = {{TTL}ab at {S}tance{E}val-2026: A Cloze-Style Prompting Approach
               for {A}rabic-Language Stance Detection ({CLASP}-Ar)},
  author    = {Verma, Bhuvanesh and Abusaleh, Ali and Mehler, Alexander},
  editor    = {Abdul-Mageed, Muhammad and Elsayed, Tamer and Bouamor, Houda and El-Beltagy, Samhaa
               and Al-Khalifa, Hend and Abdelali, Ahmed and Elmadany, AbdelRahim
               and El Mekki, Abdellah and Darwish, Kareem and Alkhereyf, Sakhar and Luqman, Hamzah
               and Khalifa, Salam and Magdy, Samar and Alyafeai, Zaid and Hamed, Injy
               and Zaghouani, Wajdi and Zitouni, Imed},
  booktitle = {Proceedings of The Fourth {A}rabic Natural Language Processing
               Conference: Shared Tasks},
  month     = {oct},
  year      = {2026},
  address   = {Budapest, Hungary},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2026.arabicnlp-sharedtasks.66/},
  pages     = {511--518},
  isbn      = {979-8-89176-497-2},
  abstract  = {Arabic-language stance detection remains challenging, and previous
               shared-task systems have largely relied on multitask learning
               and ensembles. While these systems achieve state-of-the-art performance,
               their applicability and transferability are limited by the additional
               complexity introduced by multitask learning. To reduce this complexity,
               we introduce $\\texttt{CLASP-Ar}$, which reformulates the task
               as cloze-style masked language modeling. In this approach, the
               target, predicted sentiment, and text are combined into a single
               prompt whose $\\texttt{[MASK]}$ prediction is restricted to a
               verbalizer-constrained label vocabulary. When evaluated on the
               StanceEval-2026: Arabic Stance Detection Shared Task, our proposed
               approach achieves an $F_{\\text{avg2}}$ score of 71.36{\\%} on
               Track 1 and 74.14{\\%} on Track 2 test sets.}
}

Ali Abusaleh, Bhuvanesh Verma and Alexander Mehler. October, 2026. TTLab at AlexandriaX-2026: A Fine-Tuned Surface Tagger for Arabic Machine-Translation Error-Span Detection and Classification. Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks, 786–792.
BibTeX
@inproceedings{Abusaleh:et:al:2026:mt,
  title     = {{TTL}ab at {A}lexandria{X}-2026: A Fine-Tuned Surface Tagger for
               {A}rabic Machine-Translation Error-Span Detection and Classification},
  author    = {Abusaleh, Ali and Verma, Bhuvanesh and Mehler, Alexander},
  editor    = {Abdul-Mageed, Muhammad and Elsayed, Tamer and Bouamor, Houda and El-Beltagy, Samhaa
               and Al-Khalifa, Hend and Abdelali, Ahmed and Elmadany, AbdelRahim
               and El Mekki, Abdellah and Darwish, Kareem and Alkhereyf, Sakhar and Luqman, Hamzah
               and Khalifa, Salam and Magdy, Samar and Alyafeai, Zaid and Hamed, Injy
               and Zaghouani, Wajdi and Zitouni, Imed},
  booktitle = {Proceedings of The Fourth {A}rabic Natural Language Processing
               Conference: Shared Tasks},
  month     = {oct},
  year      = {2026},
  address   = {Budapest, Hungary},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2026.arabicnlp-sharedtasks.98/},
  pages     = {786--792},
  isbn      = {979-8-89176-497-2},
  abstract  = {We present TTLab{'}s submission to the AlexandriaX-2026 Subtask
               3 on Arabic MT error span detection and classification. Our system
               frames the task as token-level classification over surface forms,
               preserving character offsets to ensure exact alignment with the
               evaluation metric. To handle severe label imbalance, we employ
               a focal loss with class weighting and dialect-specific decoding
               thresholds. Among six Arabic pre-trained encoders, MARBERTv2 achieves
               the best overall performance of 40.8 and 40.91 on the development
               and test set, respectively, ranking 3rd out of all participating
               teams. While our system localizes error spans effectively, classification
               of rare error types remains challenging, highlighting the need
               for data augmentation for tail categories.}
}

Bhuvanesh Verma, Ali Abusaleh and Alexander Mehler. October, 2026. TTLab at Daleel 2026: STAR-Ar, Sequence Tagging for Argument Recognition in Arabic. Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks, 1304–1309.
BibTeX
@inproceedings{verma-etal-2026-ttlab-daleel,
  title     = {{TTL}ab at Daleel 2026: {STAR}-Ar, Sequence Tagging for Argument
               Recognition in {A}rabic},
  author    = {Verma, Bhuvanesh and Abusaleh, Ali and Mehler, Alexander},
  editor    = {Abdul-Mageed, Muhammad and Elsayed, Tamer and Bouamor, Houda and El-Beltagy, Samhaa
               and Al-Khalifa, Hend and Abdelali, Ahmed and Elmadany, AbdelRahim
               and El Mekki, Abdellah and Darwish, Kareem and Alkhereyf, Sakhar and Luqman, Hamzah
               and Khalifa, Salam and Magdy, Samar and Alyafeai, Zaid and Hamed, Injy
               and Zaghouani, Wajdi and Zitouni, Imed},
  booktitle = {Proceedings of The Fourth {A}rabic Natural Language Processing
               Conference: Shared Tasks},
  month     = {oct},
  year      = {2026},
  address   = {Budapest, Hungary},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2026.arabicnlp-sharedtasks.163/},
  pages     = {1304--1309},
  isbn      = {979-8-89176-497-2},
  abstract  = {Argument Mining (AM) is a critical NLP task that remains significantly
               under-resourced in Arabic. This paper presents STAR-Ar, a BERT-BiLSTM-CRF
               architecture for argument discourse detection and classification,
               as our system for Daleel 2026, the inaugural Arabic argument mining
               shared task. The task requires the identification and classification
               of argumentative discourse units (ADUs) in debate and editorial
               texts. We jointly model these two objectives as a token-level
               sequence labeling task using a BERT-BiLSTM-CRF architecture that
               combines contextual transformer embeddings with structural transition
               constraints to support accurate span detection. STAR-Ar achieves
               an F1-score of 72.69 on validation and 73.7 on test data. Our
               domain-specific analysis shows that models trained exclusively
               on editorials underperform those trained on debates, a disparity
               we primarily attribute to the smaller size of the editorial dataset.}
}

New Publication at AACL-IJCNLP 2026

We are pleased to announce the acceptance of the paper “From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting Tasks” in the proceedings of the 5th Asia-Pacific Chapter of the Association for Computational Linguistics & the 15th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2026)

Ayan Datta, Mounika Marreddy, Alexander Mehler, Zhixue Zhao and Radhika Mamidi. 2026. From Early Encoding to Late Suppression: Interpreting LLMs on Character Counting Tasks. Proceedings of the 5th Asia-Pacific Chapter of the Association for Computational Linguistics & the 15th International Joint Conference on Natural Language Processing (AACL-IJCNLP 2026). accepted.
BibTeX
@inproceedings{Datta:Marreddy:Mehler:2026,
  title     = {From Early Encoding to Late Suppression: Interpreting {LLM}s on
               Character Counting Tasks},
  author    = {Datta, Ayan and Marreddy, Mounika and Mehler, Alexander and Zhao, Zhixue
               and Mamidi, Radhika},
  booktitle = {Proceedings of the 5th Asia-Pacific Chapter of the Association
               for Computational Linguistics {&} the 15th International Joint
               Conference on Natural Language Processing (AACL-IJCNLP 2026)},
  year      = {2026},
  note      = {accepted}
}

New Publication at NALOMA 2026

We are pleased to inform you that the following paper has been accepted at the 6th NALOMA (NAtural Language Meets LOgic and MAchine Learning) workshop, co-located with ESSLLI from August 3–7 in Prague.

Leon Lukas Hammerla and Alexander Mehler. August, 2026. Negation in Reasoning Traces: Interpretable Signals of Correctness and Provenance. Proceedings of the 6th Workshop on Natural Language Meets Logic and Machine Learning (NALOMA), 19–39.
BibTeX
@inproceedings{Hammerla:Mehler:2026:b,
  title     = {Negation in Reasoning Traces: Interpretable Signals of Correctness
               and Provenance},
  author    = {Hammerla, Leon Lukas and Mehler, Alexander},
  editor    = {Yanaka, Hitomi and Abzianidze, Lasha},
  booktitle = {Proceedings of the 6th Workshop on Natural Language Meets Logic
               and Machine Learning ({NALOMA})},
  month     = {aug},
  year      = {2026},
  address   = {Prague, Czechia},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2026.naloma-1.4/},
  pages     = {19--39},
  isbn      = {979-8-89176-389-0},
  abstract  = {Chain-of-thought (CoT) reasoning is widely used in large language
               models (LLMs), but the resulting reasoning traces remain underexplored.We
               study these traces through the lens of discourse-level negation.Specifically,
               we distinguish between corrective negation, which rejects a prior
               reasoning step, and refining negation, which narrows or qualifies
               it, and introduce metrics to quantify their use in human- and
               LLM-authored reasoning traces.Across multiple benchmarks, we find
               that negation occurs much more frequently in intermediate reasoning
               traces than in final response texts.We then test whether negation-based
               features provide predictive and descriptive signal for correctness,
               model identity, and human-vs.-LLM authorship.For correctness prediction,
               negation-based features consistently outperform simple structural
               baselines and in several settings add complementary signal to
               embedding-based representations, although embeddings remain stronger
               overall.In a controlled comparison on correct human and LLM traces
               from the same dataset, our strongest results arise in human-vs.-LLM
               classification, where negation features outperform both structural
               and embedding baselines.Overall, these findings position discourse-level
               negation as an interpretable feature for reasoning-trace analysis,
               with especially strong utility for provenance-related classification
               and modest but consistent value for correctness prediction.}
}