Large language models (LLMs) are prone to hallucinating or misinterpreting facts, which impairs their usability in retrieval-augmented generation or data-to-text systems. We analyse how faithfulness of LLMs to provided context depends on how plausible they perceive the context to be (context-memory conflict). To better identify error patterns, we make use of the increased difficulty of non-English and low-resource language text generation and input data based on local knowledge, only partially captured in models' parametric knowledge. We let the models generate text in English, Czech, Slovak and Upper Sorbian from factual (FA), counterfactual (CFA) and fictional (FI) RDF triples containing local Czech and Slovak data. Contrary to our expectations, we observe only a weak context-memory conflict on the human-annotated sample. For Kimi K3 as an LLM judge, which agrees well with human annotations on the sample, counterfactual inputs receive only slightly lower faithfulness scores than factual ones (-0.05 on a 1-5 scale). We also find that a suboptimal choice of LLM judge would lead to overestimating the strength of the context-memory conflict.

Large language models (LLMs) are increasingly used for text analysis tasks, such as named entity recognition or error detection. Unlike encoder-based models, however, generative architectures lack an explicit mechanism to refer to specific parts of their input. This leads to a variety of ad-hoc prompting strategies for span labeling, often with inconsistent results. In this paper, we categorize these strategies into three families: tagging the input text, indexing numerical positions of spans, and matching span content. To address the limitations of content matching, we introduce LogitMatch, a new constrained decoding method that forces the model's output to align with valid input spans. We evaluate all methods across four diverse tasks. We find that while tagging remains a robust baseline, LogitMatch improves upon competitive matching-based methods by eliminating span matching issues and outperforms other strategies in some setups.

While having a significant potential for parallel processing in theory, diffusion-based non-autoregressive text generation remains inefficient due to the need for multiple denoising steps. Performance degrades sharply if a low number of steps is used, such as in flow matching. To enable accurate one-step generation, we propose a novel shortcut flow-matching model that learns to directly predict multi-step denoising outcomes in a single step. Experiments conducted on three datasets demonstrate consistent improvements over classic flow-matching, with BLEU scores more than doubling on two datasets. We also tested five different ways of extending shortcut models with commonly used techniques.

Large language models (LLMs) are becoming central to natural language processing education, yet materials showing their mechanics are sparse. We present AnimatedLLM, an interactive web application that provides step-by-step visualizations of a Transformer language model. AnimatedLLM runs entirely in the browser, using pre-computed traces of open LLMs applied on manually curated inputs. The application is available at https://animatedllm.github.io, both as a teaching aid and for self-educational purposes.

Large Language Models (LLMs) achieve strong performance on many reasoning benchmarks, yet these evaluations typically focus on isolated tasks that differ from real-world usage in task-oriented dialogue (TOD). In this setting, LLMs must perform reasoning inherently while generating text and adhering to instructions on role, format, and style. This mismatch raises concerns about whether benchmark performance accurately reflects models’ reasoning robustness in TOD setting.We investigate how framing reasoning tasks within TOD affects LLM performance by introducing a new dynamic benchmark covering eight travel-related tasks that require arithmetic, spatial, temporal, and commonsense reasoning. Each problem is presented in both isolated and dialogue-based variants, enabling controlled comparison while mitigating data contamination. Experiments on nine LLMs reveal a substantial and consistent performance gap between isolated and dialogue settings. Through ablations and qualitative analysis, we show that this gap is largely driven by the multi-turn nature of dialogue, with additional effects from role conditioning and tool-use requirements. Our results highlight the need to evaluate LLM reasoning in realistic interactive scenarios.

Building monolingual language models (LMs) for low-resource languages typically relies on adapting pretrained language models (PLMs) by finetuning the whole model on the target language. This approach is widely favored over training from scratch, as it enables effective knowledge transfer. Additionally, prior work has shown that using a language-specific tokenizer can enhance the adaptability. In this work, we hypothesize that full model tuning is often unnecessary and propose a more modular approach. Specifically, we replace the tokens, freeze the corresponding embeddings, and tune the rest of the model. We use Scottish Gaelic, Irish, and Quechua for our experiments, with Quechua being a very low-resource language (8.5k training instances). Evaluation on natural language understanding (NLU) tasks – mask filling, NER, and POS – shows that our proposed approach improves performance when adapting models to low-resource languages. Additionally, we provide a comprehensive analysis of the effectiveness of training strategies, the choice of pretrained embeddings, and models.

This paper describes our system submitted to SemEval-2026 Task 11: Disentangling Content and Formal Reasoning in Large Language Models. We present an efficient modular neuro-symbolic approach, combining a symbolic prover with small reasoning LLMs (4B parameters). The system consists of an LLM-based parser that translates natural language syllogisms to a first-order logic (FOL) representation, an automated theorem prover, and two optional modules: machine translation for multilingual inputs and a symbolic retrieval component for the identification of relevant premises. The system achieves competitive accuracy and relatively low content effect on most subtasks. Our ablations show that this approach outperforms LLM-based zero-shot baselines in this parameter size range, but also reveal limited multilingual capabilities of small LLMs. Finally, we include a discussion of the task's main ranking metric and analyze its limitations.

Citation excerpts can be used to increase the reliability of generated outputs and their faithfulness to cited sources, which is especially important in high-stakes domains such as human and veterinary medicine. However, this does not guarantee that generated claims are faithful to the provided excerpts. We present VetScore, a multi-step evaluation method for veterinary long-form question answering, designed to assess how well are generated claims supported by the provided excerpts, weighing this information by each claim's harm potential. VetScore first segments the output and decomposes it into individual claims, then scores each claim with respect to its harm potential and evaluates its faithfulness to source excerpts, and finally calculates the overall risk-adjusted score. We collect an expert-annotated meta-evaluation dataset, evaluate our approach with a range of judge models, and show that it achieves high correlations with veterinary experts even with small judge models, while offering explainability across multiple dimensions.

Large language models (LLMs) are increasingly being used for automated decision-making systems in finance, healthcare, or environmental monitoring. Time series data are ubiquitous in these fields, yet hard to process automatically. Can time series be analyzed by LLM agents? We examine three approaches: providing the agent with raw numerical data, using the LLM as a coding agent, or a combination of both. In the coding agent setup, the model iteratively queries the data using Python code. Using two time series understanding benchmarks, we show that agents with code access can outperform models processing raw data by up to 10%. However, even the best performing agent still answers about 22-34% of the questions incorrectly. To get insights into models' strategies and reasoning gaps, we analyze the model outputs with a strong LLM judge. Our analysis reveals that coding agents can select appropriate statistical tests, but often miss important nuances. Meanwhile, models with access to raw data can reach the right conclusions using back-of-the-envelope calculations.

Span annotation - annotating specific text features at the span level - can be used to evaluate texts where single-score metrics fail to provide actionable feedback. Until recently, span annotation was done by human annotators or fine-tuned models. In this paper, we study whether large language models (LLMs) can serve as an alternative to human annotators. We compare the abilities of LLMs to skilled human annotators on three span annotation tasks: evaluating data-to-text generation, identifying translation errors, and detecting propaganda techniques. We show that overall, LLMs have only moderate inter-annotator agreement (IAA) with human annotators. However, we demonstrate that LLMs make errors at a similar rate as skilled crowdworkers. LLMs also produce annotations at a fraction of the cost per output annotation. We release the dataset of over 40k model and human span annotations for further research.

In this paper, we use large language models to generate personalized stories for language learners, using only the vocabulary they know.The generated texts are specifically written to teach the user new vocabulary by simply reading stories where it appears in context, while at the same time seamlessly reviewing recently learned vocabulary. The generated stories are enjoyable to read and the vocabulary reviewing/learning is optimized by a Spaced Repetition System.The experiments are conducted in three languages: English, Chinese and Polish, evaluating three story generation methods and three strategies for enforcing lexical constraints. The results show that the generated stories are more grammatical, coherent, and provide better examples of word usage than texts generated by the standard constrained beam search approach.

Large Language Models (LLMs) have demonstrated great potential as evaluators of NLG systems, allowing for high-quality, reference-free, and multi-aspect assessments. However, existing LLM-based metrics suffer from two major drawbacks: reliance on proprietary models to generate training data or perform evaluations, and a lack of fine-grained, explanatory feedback. In this paper, we introduce OpeNLGauge, a fully open-source, reference-free NLG evaluation metric that provides accurate explanations based on error spans. OpeNLGauge is available as a two-stage ensemble of larger open-weight LLMs, or as a small fine-tuned evaluation model, with confirmed generalizability to unseen tasks, domains and aspects. Our extensive meta-evaluation shows that OpeNLGauge achieves competitive correlation with human judgments, outperforming state-of-the-art models on certain tasks while maintaining full reproducibility and providing explanations more than twice as accurate.

Table-to-text generation (insight generation from tables) is a challenging task that requires precision in analyzing the data. In addition, the evaluation of existing benchmarks is affected by contamination of Large Language Model (LLM) training data as well as domain imbalance. We introduce FreshTab, an on-the-fly table-to-text benchmark generation from Wikipedia, to combat the LLM data contamination problem and enable domain-sensitive evaluation. While non-English table-to-text datasets are limited, FreshTab collects datasets in different languages on demand (we experiment with German, Russian and French in addition to English). We find that insights generated by LLMs from recent tables collected by our method appear clearly worse by automatic metrics, but this does not translate into LLM and human evaluations. Domain effects are visible in all evaluations, showing that a domain-balanced benchmark is more challenging.

Hallucinations are one of the most pressing challenges for large language models (LLMs). While numerous methods have been proposed to detect and mitigate them automatically, human evaluation continues to serve as the gold standard. However, these human evaluations of hallucinations show substantial variation in definitions, terminology, and evaluation practices. In this paper, we survey 64 studies involving human evaluation of hallucination published between 2019 and 2024, to investigate how hallucinations are currently defined and assessed. Our analysis reveals a lack of consistency in definitions and exposes several concerning methodological shortcomings. Crucial details, such as evaluation guidelines, user interface design, inter-annotator agreement metrics, and annotator demographics, are frequently under-reported or omitted altogether.

Large language models (LLMs) gained immense popularity due to their impressive capabilities in unstructured conversations. Empowering LLMs with advanced prompting strategies such as reasoning and acting (ReAct) (Yao et al., 2022) has shown promise in solving complex tasks traditionally requiring reinforcement learning. In this work, we apply the ReAct strategy to guide LLMs performing task-oriented dialogue (TOD). We evaluate ReAct-based LLMs (ReAct-LLMs) both in simulation and with real users. While ReAct-LLMs severely underperform state-of-the-art approaches on success rate in simulation, this difference becomes less pronounced in human evaluation. Moreover, compared to the baseline, humans report higher subjective satisfaction with ReAct-LLM despite its lower success rate, most likely thanks to its natural and confidently phrased responses.

We introduce a simple approach that uses a large language model (LLM) to automatically implement a fully interpretable rule-based data-to-text system in pure Python. Experimental evaluation on the WebNLG dataset showed that such a constructed system produces text of better quality (according to the BLEU and BLEURT metrics) than the same LLM prompted to directly produce outputs, and produces fewer hallucinations than a BART language model fine-tuned on the same data. Furthermore, at runtime, the approach generates text in a fraction of the processing time required by neural approaches, using only a single CPU

We investigate how large language models (LLMs) can produce personalized dialogue responses, specifically focusing on whether they reflect linguistic styles pertaining to different generations: Baby Boomers, Generation X, Generation Y, and Generation Z. We create P-MultiWoZ, a personalized, generation-specific version of MultiWOZ 2.2, by prompting LLMs, and validate its alignment with the original dataset through automatic and human evaluations. To validate the appropriateness of generational linguistic traits, we introduce GeMoSC, a corpus of generation-annotated movie dialogues. Linguistic analysis and perplexity test suggest that P-MultiWoZ reflects patterns consistent with GeMoSC. Finally, a human evaluation reveals that annotators were able to mostly correctly identify the generation behind P-MultiWoZ dialogues, based only on a single query-reply pair.

Text style transfer (TST) is the task of transforming a text to reflect a particular style while preserving its original content. Evaluating TST outputs is a multidimensional challenge, requiring the assessment of style transfer accuracy, content preservation, and naturalness. Using human evaluation is ideal but costly, as is common in other natural language processing (NLP) tasks, however, automatic metrics for TST have not received as much attention as metrics for, e.g., machine translation or summarization. In this paper, we examine both set of existing and novel metrics from broader NLP tasks for TST evaluation, focusing on two popular subtasks, sentiment transfer and detoxification, in a multilingual context comprising English, Hindi, and Bengali. By conducting meta-evaluation through correlation with human judgments, we demonstrate the effectiveness of these metrics when used individually and in ensembles. Additionally, we investigate the potential of large language models (LLMs) as tools for TST evaluation. Our findings highlight newly applied advanced NLP metrics and LLM-based evaluations provide better insights than existing TST metrics. Our oracle ensemble approaches show even more potential.