We introduce mmPISA-bench, a compact high-quality multilingual reasoning benchmark derived from the OECD Programme for International Student Assessment (PISA). The benchmark consists of 25 multiple-choice questions that require reasoning in order to be answered correctly. Each question is provided in official human translations to 43 languages and complemented with machine-translated counterparts (i.e., 2,150 data points in total). We evaluate two mainstream proprietary LLMs across languages, reasoning effort levels, and translation types in terms of their ability to answer the questions correctly. Our results show that modern LLMs can reason effectively across all evaluated languages, achieve accuracy comparable to human test-takers, with some performance variations across covered languages. We further find that machine-translated questions do not degrade accuracy relative to official human translations which suggests that high-quality machine translation (synthetic data) might often be adequate for large-scale multilingual reasoning evaluations where official translations are not available. Finally, we analyze token usage and related inference cost and find that LLMs usage in some languages is simultaneously more expensive and less accurate.

Large language models are widely used by everyday users, and can be asked to perform tasks that require specialized expertise, such as interpreting contractual terms and conditions, filing personal taxes, or diagnosing medical symptoms. Although these tools should not be used in place of professional advice, they can be useful starting points for users seeking professional help, improving users’ access and interactions with professionals. In this vein, this paper introduces a legal question reformulation task to assist non-experts in their interactions with lawyers. This has the potential to streamline discussions between lawyers and clients, who may not know the correct legal language to communicate their needs. Using a novel evaluation framework informed by legal expertise, we investigate the quality of model-generated legal question reformulations on in-the-wild data from non-experts seeking legal advice. Our findings indicate that LLMs have significant potential in legal reasoning, but some unexpected safety concerns may emerge. Further, adding linguisticallyaligned in-domain text samples can improve performance for smaller models, even when the samples are not aligned factually with the given question.

Structured span extraction research is siloed by context length, annotation task, and domain, making it difficult to assess how well large language models (LLMs) generalize across realistic extraction settings. We introduce SSA (Structured Span Annotation), a unified evaluation framework bringing together five datasets across four domains: finance, biomedicine, affective analysis, and privacy, under a common JSONL format with character-level offsets. We conduct an exploratory study evaluating seven models (three closed, four open-weight) under three prompting configurations: zero-shot, definition-augmented, and few-shot, formulating extraction as inline XML generation where models reproduce the document with tagged spans. Our results reveal two distinct performance regimes: on tasks requiring complex ontology reasoning, zero-shot performance is near zero (e.g., 0.00% F1 on FiNER-139) but improves substantially with label definitions (e.g., Claude Opus 4.6 rises from 8.8% to 57.5% F1); on pattern-based tasks like PII detection, definitions consistently hurt performance across all models. These findings suggest that prompting strategy must be matched to task structure, and that unified evaluation frameworks spanning varied domains and input lengths are essential for understanding LLM extraction capabilities.

Legal texts routinely use concepts that are difficult to understand. Lawyers elaborate on the meaning of such concepts by, among other things, carefully investigating how they have been used in the past. Finding text snippets that mention a particular concept in a useful way is tedious, time-consuming, and hence expensive. We assembled a data set of 26,959 sentences, coming from legal case decisions, and labeled them in terms of their usefulness for explaining selected legal concepts. Using the dataset we study the effectiveness of transformer models pre-trained on large language corpora to detect which of the sentences are useful. In light of models’ predictions, we analyze various linguistic properties of the explanatory sentences as well as their relationship to the legal concept that needs to be explained. We show that the transformer-based models are capable of learning surprisingly sophisticated features and outperform the prior approaches to the task.

In this paper, we publicly release an annotated corpus of 42 decisions of the European Court of Human Rights (ECHR). The corpus is annotated in terms of three types of clauses useful in argument mining: premise, conclusion, and non-argument parts of the text. Furthermore, relationships among the premises and conclusions are mapped. We present baselines for three tasks that lead from unstructured texts to structured arguments. The tasks are argument clause recognition, clause relation prediction, and premise/conclusion recognition. Despite a straightforward application of the bidirectional encoders from Transformers (BERT), we obtained very promising results F1 0.765 on argument recognition, 0.511 on relation prediction, and 0.859/0.628 on premise/conclusion recognition). The results suggest the usefulness of pre-trained language models based on deep neural network architectures in argument mining. Because of the simplicity of the baselines, there is ample space for improvement in future work based on the released corpus.