Prompt relevance is a critical yet underexplored dimension in Arabic Automated Essay Scoring (AES). We present the first systematic study of binary prompt-essay relevance classification, supporting both AES scoring and dataset annotation. To address data scarcity, we built a synthetic dataset of on-topic and off-topic pairs and evaluated multiple models, including threshold-based classifiers, SVMs, causal LLMs, and a fine-tuned masked SBERT model. For real-data evaluation, we combined QAES with ZAEBUC, creating off-topic pairs via mismatched prompts. We also tested prompt expansion strategies using AraVec, CAMeL, and GPT-4o. Our fine-tuned SBERT achieved 98% F1 on synthetic data and strong results on QAES+ZAEBUC, outperforming SVMs and threshold-based baselines and offering a resource-efficient alternative to LLMs. This work establishes the first benchmark for Arabic prompt relevance and provides practical strategies for low-resource AES.

Automated Essay Scoring (AES) plays a crucial role in assessing language learners’ writingquality, reducing grading workload, and providing real-time feedback. The lack of annotatedessay datasets inhibits the development of Arabic AES systems. This paper leverages LargeLanguage Models (LLMs) and Transformermodels to generate synthetic Arabic essays forAES. We prompt an LLM to generate essaysacross the Common European Framework ofReference (CEFR) proficiency levels and introduce and compare two approaches to errorinjection. We create a dataset of 3,040 annotated essays with errors injected using our twomethods. Additionally, we develop a BERTbased Arabic AES system calibrated to CEFRlevels. Our experimental results demonstratethe effectiveness of our synthetic dataset in improving Arabic AES performance. We makeour code and data publicly available

Recent work has investigated whether extant neural language models (LMs) have an inbuilt inductive bias towards the acquisition of attested typologically-frequent grammatical patterns as opposed to infrequent, unattested, or impossible patterns using artificial languages (White and Cotterell, 2021; Kuribayashi et al., 2024). The use of artificial languages facilitates isolation of specific grammatical properties from other factors such as lexical or real-world knowledge, but also risks oversimplification of the problem.In this paper, we examine the use of Generalized Categorial Grammars (GCGs) (Wood, 2014) as a general framework to create artificial languages with a wider range of attested word order patterns, including those where the subject intervenes between verb and object (VSO, OSV) and unbounded dependencies in object relative clauses. In our experiments, we exemplify our approach by extending White and Cotterell (2021) and report some significant differences from existing results.

Providing constructive feedback to paper authors is a core component of peer review. With reviewers increasingly having less time to perform reviews, automated support systems are required to ensure high reviewing quality, thus making the feedback in reviews useful for authors. To this end, we identify four key aspects of review comments (individual points in weakness sections of reviews) that drive the utility for authors: Actionability, Grounding & Specificity, Verifiability, and Helpfulness. To enable evaluation and development of models assessing review comments, we introduce the RevUtil dataset. We collect 1,430 human-labeled review comments and scale our data with 10k synthetically labeled comments for training purposes. The synthetic data additionally contains rationales, i.e., explanations for the aspect score of a review comment. Employing the RevUtil dataset, we benchmark fine-tuned models for assessing review comments on these aspects and generating rationales. Our experiments demonstrate that these fine-tuned models achieve agreement levels with humans comparable to, and in some cases exceeding, those of powerful closed models like GPT-4o. Our analysis further reveals that machine-generated reviews generally underperform human reviews on our four aspects.

Whether language models (LMs) have inductive biases that favor typologically frequent grammatical properties over rare, implausible ones has been investigated, typically using artificial languages (ALs) (White and Cotterell, 2021; Kuribayashi et al., 2024). In this paper, we extend these works from two perspectives. First, we extend their context-free AL formalization by adopting Generalized Categorial Grammar (GCG) (Wood, 2014), which allows ALs to cover attested but previously overlooked constructions, such as unbounded dependency and mildly context-sensitive structures. Second, our evaluation focuses more on the generalization ability of LMs to process unseen longer test sentences. Thus, our ALs better capture features of natural languages and our experimental paradigm leads to clearer conclusions — typologically plausible word orders tend to be easier for LMs to productively generalize.

Although Arabic is spoken by over 400 million people, advanced Arabic writing assistance tools remain limited. To address this gap, we present ARWI, a new writing assistant that helps learners improve essay writing in Modern Standard Arabic. ARWI is the first publicly available Arabic writing assistant to include a prompt database for different proficiency levels, an Arabic text editor, state-of-the-art grammatical error detection and correction, and automated essay scoring aligned with the Common European Framework of Reference standards for language attainment (https://arwi.mbzuai.ac.ae/). Moreover, ARWI can be used to gather a growing auto-annotated corpus, facilitating further research on Arabic grammar correction and essay scoring, as well as profiling patterns of errors made by native speakers and non-native learners. A preliminary user study shows that ARWI provides actionable feedback, helping learners identify grammatical gaps, assess language proficiency, and guide improvement.

We present PeerQA, a real-world, scientific, document-level Question Answering (QA) dataset. PeerQA questions have been sourced from peer reviews, which contain questions that reviewers raised while thoroughly examining the scientific article. Answers have been annotated by the original authors of each paper. The dataset contains 579 QA pairs from 208 academic articles, with a majority from ML and NLP, as well as a subset of other scientific communities like Geoscience and Public Health.PeerQA supports three critical tasks for developing practical QA systems: Evidence retrieval, unanswerable question classification, and answer generation. We provide a detailed analysis of the collected dataset and conduct experiments establishing baseline systems for all three tasks. Our experiments and analyses reveal the need for decontextualization in document-level retrieval, where we find that even simple decontextualization approaches consistently improve retrieval performance across architectures. On answer generation, PeerQA serves as a challenging benchmark for long-context modeling, as the papers have an average size of 12k tokens.

Regulatory compliance questions often require aggregating evidence from multiple, interrelated sections of long, complex documents. To support question-answering (QA) in this setting, we introduce ObliQA-MP, a dataset for multi-passage regulatory QA, extending the earlier ObliQA benchmark (CITATION), and improve evidence quality with an LLM–based validation step that filters out ~20% of passages missed by prior natural language inference (NLI) based filtering. Our benchmarks show a notable performance drop from single- to multi-passage retrieval, underscoring the challenges of semantic overlap and structural complexity in regulatory texts. To address this, we propose a feature-based learning-to-rank (LTR) framework that integrates lexical, semantic, and graph-derived information, achieving consistent gains over dense and hybrid baselines. We further add a lightweight score-based filter to trim noisy tails and an obligation-centric prompting technique. On ObliQA-MP, LTR improves retrieval (Recall@10/MAP@10/nDCG@10) over dense, hybrid, and fusion baselines. Our generation approach, based on domain-specific filtering plus prompting, achieves strong scores using the RePAS metric (CITATION) on ObliQA-MP, producing faithful, citation-grounded answers. Together, ObliQA-MP and our validation and RAG systems offer a stronger benchmark and a practical recipe for grounded, citation-controlled QA in regulatory domains.

This paper provides an overview of the Shared Task RIRAG-2025, which focused on advancing the field of Regulatory Information Retrieval and Answer Generation (RIRAG). The task was designed to evaluate methods for answering regulatory questions using the ObliQA dataset. This paper summarizes the shared task, participants’ methods, and the results achieved by various teams.

The world’s languages exhibit certain so-called typological or implicational universals; for example, Subject-Object-Verb (SOV) languages typically use postpositions. Explaining the source of such biases is a key goal of linguistics.We study word-order universals through a computational simulation with language models (LMs).Our experiments show that typologically-typical word orders tend to have lower perplexity estimated by LMs with cognitively plausible biases: syntactic biases, specific parsing strategies, and memory limitations. This suggests that the interplay of cognitive biases and predictability (perplexity) can explain many aspects of word-order universals.It also showcases the advantage of cognitively-motivated LMs, typically employed in cognitive modeling, in the simulation of language universals.

Grammatical Error Correction (GEC) is the task of automatically detecting and correcting errors in text. The task not only includes the correction of grammatical errors, such as missing prepositions and mismatched subject–verb agreement, but also orthographic and semantic errors, such as misspellings and word choice errors, respectively. The field has seen significant progress in the last decade, motivated in part by a series of five shared tasks, which drove the development of rule-based methods, statistical classifiers, statistical machine translation, and finally neural machine translation systems, which represent the current dominant state of the art. In this survey paper, we condense the field into a single article and first outline some of the linguistic challenges of the task, introduce the most popular datasets that are available to researchers (for both English and other languages), and summarize the various methods and techniques that have been developed with a particular focus on artificial error generation. We next describe the many different approaches to evaluation as well as concerns surrounding metric reliability, especially in relation to subjective human judgments, before concluding with an overview of recent progress and suggestions for future work and remaining challenges. We hope that this survey will serve as a comprehensive resource for researchers who are new to the field or who want to be kept apprised of recent developments.

In this work, we systematically investigate how well current models of coherence can capture aspects of text implicated in discourse organisation. We devise two datasets of various linguistic alterations that undermine coherence and test model sensitivity to changes in syntax and semantics. We furthermore probe discourse embedding space and examine the knowledge that is encoded in representations of coherence. We hope this study shall provide further insight into how to frame the task and improve models of coherence assessment further. Finally, we make our datasets publicly available as a resource for researchers to use to test discourse coherence models.

Automating the assessment of learner summary provides a useful tool for assessing learner reading comprehension. We present a summarization task for evaluating non-native reading comprehension and propose three novel approaches to automatically assess the learner summaries. We evaluate our models on two datasets we created and show that our models outperform traditional approaches that rely on exact word match on this task. Our best model produces quality assessments close to professional examiners.

This paper reports on the BEA-2019 Shared Task on Grammatical Error Correction (GEC). As with the CoNLL-2014 shared task, participants are required to correct all types of errors in test data. One of the main contributions of the BEA-2019 shared task is the introduction of a new dataset, the Write&Improve+LOCNESS corpus, which represents a wider range of native and learner English levels and abilities. Another contribution is the introduction of tracks, which control the amount of annotated data available to participants. Systems are evaluated in terms of ERRANT F_0.5, which allows us to report a much wider range of performance statistics. The competition was hosted on Codalab and remains open for further submissions on the blind test set.

We demonstrate that current state-of-the-art approaches to Automated Essay Scoring (AES) are not well-suited to capturing adversarially crafted input of grammatical but incoherent sequences of sentences. We develop a neural model of local coherence that can effectively learn connectedness features between sentences, and propose a framework for integrating and jointly training the local coherence model with a state-of-the-art AES model. We evaluate our approach against a number of baselines and experimentally demonstrate its effectiveness on both the AES task and the task of flagging adversarial input, further contributing to the development of an approach that strengthens the validity of neural essay scoring models.

Since the end of the CoNLL-2014 shared task on grammatical error correction (GEC), research into language model (LM) based approaches to GEC has largely stagnated. In this paper, we re-examine LMs in GEC and show that it is entirely possible to build a simple system that not only requires minimal annotated data (∼1000 sentences), but is also fairly competitive with several state-of-the-art systems. This approach should be of particular interest for languages where very little annotated training data exists, although we also hope to use it as a baseline to motivate future research.

Some language exams have multiple writing tasks. When a learner writes multiple texts in a language exam, it is not surprising that the quality of these texts tends to be similar, and the existing automated text scoring (ATS) systems do not explicitly model this similarity. In this paper, we suggest that it could be useful to include the other texts written by this learner in the same exam as extra references in an ATS system. We propose various approaches of fusing information from multiple tasks and pass this authorship knowledge into our ATS model on six different datasets. We show that this can positively affect the model performance at a global level.

Until now, error type performance for Grammatical Error Correction (GEC) systems could only be measured in terms of recall because system output is not annotated. To overcome this problem, we introduce ERRANT, a grammatical ERRor ANnotation Toolkit designed to automatically extract edits from parallel original and corrected sentences and classify them according to a new, dataset-agnostic, rule-based framework. This not only facilitates error type evaluation at different levels of granularity, but can also be used to reduce annotator workload and standardise existing GEC datasets. Human experts rated the automatic edits as “Good” or “Acceptable” in at least 95% of cases, so we applied ERRANT to the system output of the CoNLL-2014 shared task to carry out a detailed error type analysis for the first time.

We propose a novel word embedding pre-training approach that exploits writing errors in learners’ scripts. We compare our method to previous models that tune the embeddings based on script scores and the discrimination between correct and corrupt word contexts in addition to the generic commonly-used embeddings pre-trained on large corpora. The comparison is achieved by using the aforementioned models to bootstrap a neural network that learns to predict a holistic score for scripts. Furthermore, we investigate augmenting our model with error corrections and monitor the impact on performance. Our results show that our error-oriented approach outperforms other comparable ones which is further demonstrated when training on more data. Additionally, extending the model with corrections provides further performance gains when data sparsity is an issue.

Shortage of available training data is holding back progress in the area of automated error detection. This paper investigates two alternative methods for artificially generating writing errors, in order to create additional resources. We propose treating error generation as a machine translation task, where grammatically correct text is translated to contain errors. In addition, we explore a system for extracting textual patterns from an annotated corpus, which can then be used to insert errors into grammatically correct sentences. Our experiments show that the inclusion of artificially generated errors significantly improves error detection accuracy on both FCE and CoNLL 2014 datasets.

We propose a new method of automatically extracting learner errors from parallel English as a Second Language (ESL) sentences in an effort to regularise annotation formats and reduce inconsistencies. Specifically, given an original and corrected sentence, our method first uses a linguistically enhanced alignment algorithm to determine the most likely mappings between tokens, and secondly employs a rule-based function to decide which alignments should be merged. Our method beats all previous approaches on the tested datasets, achieving state-of-the-art results for automatic error extraction.

We have integrated the RASP system with the UIMA framework (RASP4UIMA) and used this to parse the XML-encoded version of the British National Corpus (BNC). All original annotation is preserved, and parsing information, mainly in the form of grammatical relations, is added in an XML format. A few specific adaptations of the system to give better results with the BNC are discussed briefly. The RASP4UIMA system is publicly available and can be used to parse other corpora or document collections, and the final parsed version of the BNC will be deposited with the Oxford Text Archive.

We introduce a large computational subcategorizationlexicon which includes subcategorization frame (SCF) and frequencyinformation for 6,397 English verbs. This extensive lexicon was acquiredautomatically from five corpora and the Web using the current version of the comprehensive subcategorization acquisition system of Briscoe and Carroll (1997). The lexicon is provided freely for research use, along with a script which can be used to filter and build sub-lexicons suited for different natural languageprocessing (NLP) purposes. Documentation is also provided whichexplains each sub-lexicon option and evaluates its accuracy.

We describe an approach to robust domain-independent syntactic parsing of unrestricted naturally-occurring (English) input. The technique involves parsing sequences of part-of-speech and punctuation labels using a unification-based grammar coupled with a probabilistic LR parser. We describe the coverage of several corpora using this grammar and report the results of a parsing experiment using probabilities derived from bracketed training data. We report the first substantial experiments to assess the contribution of punctuation to deriving an accurate syntactic analysis, by parsing identical texts both with and without naturally-occurring punctuation marks.