Oct 2026· Publications Office of the European Union
Topic Modeling
Abstract
This dataset contains the outputs used to evaluate how well large language models (LLMs) can identify transport-relevant research projects for TRIMIS, the European Commission's Transport Research and Innovation Monitoring and Information System. A random sample of 250 Horizon Europe projects from CORDIS was labelled by domain experts as not relevant, partly relevant or relevant to transport. The same projects were then scored by four open-weight LLMs, each run with 13 different prompts, giving 52 sets of results. Each file lists, per project, the expert label, the model's score, its justification and supporting quotation, and processing cost. The package also includes the prompts, a Python script that recomputes all reported statistics, and the resulting tables and charts. It supports the article "Enhancing Transport Innovation Knowledge Management Workflows Using Artificial Intelligence: A TRIMIS Database Case Study" (European Transport Research Review, 2026).
This paper investigates developing real-world perception for active agents, proposes Gibson Environment for this purpose, and showcases a set of perceptual tasks learned therein.
F. Xia, Amir Zamir, Zhi-Yang He et al.· 2018 IEEE/CVF Conference on...· 1,069 citations· ⚡112
GAOKAO-Bench is introduced, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions that contribute a robust evaluation benchmark for future large language models and offers valuable insights into the advantages and limitations...
Xiaotian Zhang, Chun-yan Li, Yi Zong et al.· arXiv.org· 216 citations· ⚡17
An algorithm is proposed which leverages disentangled semantic factors to generate adversarial perturbation by altering controlled semantic attributes to fool the learner towards various "adversarial" targets.
Haonan Qiu, Chaowei Xiao, Lei Yang et al.· arXiv.org· 208 citations· ⚡17
This work proposes a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, and suggests that the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.
This work investigates the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection and finds that the MTEs are biased, significantly favoring White-associated names in 85% of cases and female-associated names in only 11.1% of cases.
This work shows that orders of magnitude enhancement in performance could be obtained by a combination of hardware improvements and tight quantum-HPC integration and introduces high-performance architectures for quantum-probabilistic computing with custom-designed accelerators to tackle today's industry-scale classical...
Masoud Mohseni, Artur Scherer, K. Johnson et al.· arXiv.org· 121 citations· ⚡9
