Parametric Knowledge and Retrieval Behavior in RAG Fine-Tuning for Electronic Design Automation

Retrieval-Augmented Generation (RAG) fine-tuning has shown substantial improvements over vanilla RAG, yet most studies target document question answering and often rely on standard NLP metrics that can obscure factual differences. We evaluate RAG fine-tuning for long-form text generation in electronic design automation, adapting a 7B model under five context augmentation strategies with varying retrieval conditions. We introduce TriFEX, a human-validated, triple-based evaluation pipeline that attributes generated claims to their origin-user query, context and reference-and propose Parametric Knowledge Precision (PKP), which isolates internalized knowledge by filtering out claims leaked in the prompt. We show that ROUGE and BERTScore fail to detect factual differences that our triple-based evaluation reveals. Additionally, we demonstrate that an existing metric for knowledge internalization is retrieva-sensitive, with about 75% of its cross-condition variance driven by changes in the rate at which internal knowledge is expressed (PR), rather than by changes in its actual correctness (PKP). The fine-tuned 7B variants outperform a 72B baseline on most metrics, further showing generalization across conditions and on a related benchmark. These results underscore the limitations of available metrics in RAG evaluation and show that smaller models could be reasonably well adapted to specialized tasks for cost-efficient, on-premises deployment.

Small-text: Active Learning for Text Classification in Python

We present small-text, a simple modular active learning library, which offers pool-based active learning for text classification in Python. It comes with various pre-implemented state-of-the-art query strategies, including some which can leverage the GPU. Clearly defined interfaces allow to combine a multitude of such query strategies with different classifiers, thereby facilitating a quick mix and match, and enabling a rapid development of both active learning experiments and applications. To make various classifiers accessible in a consistent way, it integrates several well-known machine learning libraries, namely, scikit-learn, PyTorch, and huggingface transformers -- for which the latter integrations are available as optionally installable extensions. The library is available under the MIT License at https://github.com/webis-de/small-text.

Mining Legacy Issues in Open Pit Mining Sites: Innovation & Support of Renaturalization and Land Utilization

Open pit mines left many regions worldwide inhospitable or uninhabitable. To put these regions back into use, entire stretches of land must be renaturalized. For the sustainable subsequent use or transfer to a new primary use, many contaminated sites and soil information have to be permanently managed. In most cases, this information is available in the form of expert reports in unstructured data collections or file folders, which in the best case are digitized. Due to size and complexity of the data, it is difficult for a single person to have an overview of this data in order to be able to make reliable statements. This is one of the most important obstacles to the rapid transfer of these areas to after-use. An information-based approach to this issue supports fulfilling several Sustainable Development Goals regarding environment issues, health and climate action. We use a stack of Optical Character Recognition, Text Classification, Active Learning and Geographic Information System Visualization to effectively mine and visualize this information. Subsequently, we link the extracted information to geographic coordinates and visualize them using a Geographic Information System. Active Learning plays a vital role because our dataset provides no training data. In total, we process nine categories and actively learn their representation in our dataset. We evaluate the OCR, Active Learning and Text Classification separately to report the performance of the system. Active Learning and text classification results are twofold: Whereas our categories about restrictions work sufficient ($>$.85 F1), the seven topic-oriented categories were complicated for human coders and hence the results achieved mediocre evaluation scores ($<$.70 F1).