Advances in Multimodal Large Language Models (MLLMs) have driven substantial progress in multimodal embeddings. Recent methods exploit generative capabilities by augmenting embedded inputs with self-generated reasoning to produce more informative embeddings. However, conventional retrieval supervision for training embe...
Tian-Yu Yang, Yi-Jun Tian, Lars Benedikt Kaesberg et al.· 0 citations
This work studies the benign case: agents follow one protocol, none intends to deceive, but some read a misleading passage, testing three open-weight models on commonsense reasoning, knowledge QA, and moral judgment, and concludes that robustness should be judged against exposure-matched baselines.
Jonas Becker, Jan Philip Wahle, T. Ruas et al.· arXiv.org· 2 citations
AutoRecLab is presented, a Python-based autonomous RecSys lab that automates RecSys experimentation from natural-language prompts that achieves 8 out of 9 successful runs at an average cost of approximately $1 per run using GPT-5.4-mini.
Moritz Baumgart, Philipp Meister, J. Krell et al.· Proceedings of the 20th ACM...· 0 citations
An episode-level protocol that scores whether, when, and what a delegate contributes around the participant's actual idea units is introduced, to evaluate online delegation.
Muneeb Khan, F. Kirstein, T. Ruas et al.· 0 citations
This work presents the open-source benchmark framework ParliamentBench based on the game Secret Hitler to evaluate LLMs in scenarios that require deception, persuasion, and reasoning under information asymmetry, and introduces three novel metrics that isolate social deduction, reasoning, and deceptive consistency.
Niklas Bauer, Lars Benedikt Kaesberg, Akiko Aizawa et al.· arXiv.org· 0 citations
It is found that visual presentation is a central factor that determines whether VLM benchmarks measure grounded perception, downstream reasoning, or a mixture of both, and gains are closely tied to reductions in grounding-related errors, while rule reasoning remains comparatively challenging.
Lars Benedikt Kaesberg, Tianyu Yang, F. Wunderlich et al.· 1 citation
The findings suggest that activation steering may provide a practical, low- cost mechanism for extending English-derived safety signals to other languages, and introduce a multilingual translation-and-evaluation pipeline to facilitate future work on cross-lingual safety interventions.
Emma V. Stein, Dominik Meier, T. Ruas et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
