Tag
该论文介绍了团队参加 KnowledgeGraphEval 2026 子任务2（阿拉伯语关系抽取）的系统：结合基于编码器的方法与微调 Yehia、Qwen3.5 的 LLM 系统，最佳集成系统在子任务2中以 94.06 的 micro-F1 获得第一名，凸显了约束预测与多种建模方法互补的重要性。
The Itgan team describes a unified Whisper+LoRA recipe adapted for the three NADI 2026 Arabic ASR subtasks, showing that per-dialect specialists, base-model choice, and training-free weight averaging each dominate for different subtasks rather than any single novel component.
StanceEval 2026 is the second edition of the stance detection shared task on Arabic social media, focusing on cross-target and cross-domain generalization, with top systems reaching F_avg2 scores of 0.8994 and 0.9400 and substantially outperforming baselines.
A DocInsights 2026 shared-task system paper describing EviCalc, a PDF document QA pipeline that pairs evidence passage selection with LLM-generated arithmetic expressions evaluated in local code, reporting 8.61% joint accuracy on DocSem's test set along with descriptive failure analysis, including OCR and block-grouping errors that merged relevant passages.
HalluScoring 2026 presents the first shared task on LLM hallucination detection and factual verification for Arabic question answering, with 13 teams competing across four subtasks covering binary hallucination detection and answer selection on the HalluScore and HalluTruthQA datasets.
TTLab presents a fine-tuned surface tagger for Arabic machine-translation error-span detection and classification, using MARBERTv2 to achieve 3rd place in the AlexandriaX-2026 shared task.
ArGuard is a shared task focused on detecting harmful content in Arabic memes and LLM prompts, highlighting challenges in fine-grained classification and releasing datasets for further research.
AraGenre 2026 is a shared task for hierarchical, definition-guided Arabic genre classification aimed at improving annotated data in low-resource languages, with results showing strong broad-genre recognition but gaps in fine-grained classification.
This paper presents a resource-efficient RAG pipeline for Ukrainian multi-domain document understanding in the UNLP 2026 Shared Task, balancing reasoning depth with hardware constraints to achieve a 10th place ranking.
A system paper on hallucination detection in Vision-Language Models has been accepted at EMNLP 2026 for the SHROOM shared task, hosted at the UncertaiNLP workshop, focusing on marking and labeling hallucinated character spans in VLM outputs.
The paper presents a data selection method for terminology-aware translation that trains only on hard examples where the model's output contradicts the glossary, achieving improved term accuracy, and describes the BSC system submission to the WMT26 Terminology Shared Task.
This paper evaluates retrieval-based in-context learning approaches for detecting criminally relevant hate speech in German social media posts, finding that few-shot prompting outperforms zero-shot but retrieval methods offer marginal gains, with models better suited for triage than autonomous moderation.
This paper presents a SciBERT-based approach for automatic classification of telescope bibliographies, achieving top performance in the WASP-2025 shared task with efficient handling of context-length constraints.
The paper describes a submission to the WMT 2026 MIST shared task, using the Tiny Aya Global model with task-specialized QLoRA adapters for multilingual summarization and question answering.
This paper presents REAP, a two-stage pipeline for closed-book knowledge base construction from LLMs that combines relation-specific elicitation strategies with deterministic JSON parsing, achieving a macro-F1 of 0.62 on the AKBC Shared Task 2026 test set using Mistral-Small-24B-Instruct-2501.
This paper presents EVIL-Detect, a multi-signal ensemble framework with conflict-aware fusion for detecting LLM-generated, refined, and human-written Chinese text in the NLPCC 2026 Shared Task 6, achieving first place with a macro-F1 of 0.8888.
This paper describes Team uOttawa's system for the EvaLatin 2026 shared task on Named Entity Recognition for Classical Latin, using prompt engineering of commercial LLMs (Gemini 2.5 Pro and Claude Sonnet 4-5) to achieve first place in both coarse- and fine-grained NER subtasks.
This paper presents a three-stage neural-symbolic pipeline for gaming toxicity detection, combining transformer ensembles with rule-based mediation, achieving top accuracy in the EEUCA 2026 shared task.
This paper describes LLM-INSTRUCT, the winning system for the UZH Shared Task at ArgMining 2026 on paragraph-level argument mining. The system uses constraint-aware retrieval and selective debate to improve accuracy and schema compliance.
The article announces the first ChineseBabyLM Challenge at NLPCC 2026, which asks researchers to train language models from scratch on 100 million Chinese tokens and evaluate them on NLU, cognitive alignment, and Hanzi knowledge, promoting data-efficient and cognitively plausible modeling for Chinese.