As large language models (LLMs) reach human-like fluency, reliably distinguishing AI-generated text from human authorship becomes increasingly difficult. While watermarks already exist for LLMs, they often lack flexibility and struggle with attacks such as paraphrasing. To address these issues, we propose a multi-feature method for generating watermarks that combines multiple distinct watermark features into an ensemble watermark. Concretely, we combine acrostica and sensorimotor norms with the established red-green watermark to achieve a 98% detection rate. After a paraphrasing attack, the performance remains high with 95% detection rate. In comparison, the red-green feature alone as a baseline achieves a detection rate of 49% after paraphrasing. The evaluation of all feature combinations reveals that the ensemble of all three consistently has the highest detection rate across several LLMs and watermark strength settings. Due to the flexibility of combining features in the ensemble, various requirements and trade-offs can be addressed. Additionally, the same detection function can be used without adaptations for all ensemble configurations. This method is particularly of interest to facilitate accountability and prevent societal harm.

This paper presents our approach and findings for participating in the FinCausal 2025 competition, which addresses causal question answering derived from financial documents, specifically English and Spanish annual reports. We investigate the effectiveness of generative models, such as Llama, in contrast to common extractive methods like BERT-based token classification. While prompt optimization and few-shot learning offer some improvements, they were insufficient for consistently outperforming extractive methods in FinCausal, suffering from hallucinations. In contrast, fine-tuning generative models was shown to be essential for minimizing hallucinations and achieving superior performance. Using our fine-tuned multilingual model for both tasks, we outperform our extractive and monolingual approaches, achieving top results for Spanish and second-best for English in the competition. Our findings indicate that fine-tuned large language models are well-suited for causal Q&A from complex financial narratives, offering robust multilingual capabilities and effectively mitigating hallucinations.

Identifying software entities and their semantic relations in scientific texts is key for reproducibility and machine-readable knowledge graphs, yet models struggle with domain variability and sparse supervision. We address this by evaluating joint Named Entity Recognition (NER) and Relation Extraction (RE) models on the SOMD 2025 shared task, emphasizing generalization to out-of-domain scholarly texts. We propose a unified training objective that jointly optimizes both tasks using a shared loss function and demonstrates that joint loss formulations can improve out-of-domain robustness compared to disjoint training. Our results reveal significant performance gaps between in- and out-of-domain settings, prompting critical reflections on modeling strategies for software knowledge extraction. Notably, our approach ranked 1st in Phase 2 (out-of-distribution) and 2nd in Phase 1 (in-distribution) in the SOMD 2025 shared task, showing strong generalization and robust performance across domains.