5 papers
Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches
Teddy Ferdinan, BartÅomiej Koptyra, MikoÅaj Langner +42
While Reasoning Language Models (RLMs) are rapidly emerging as powerful tools for scientific research, their impact is primarily concentrated in "hard science" fields. The slow --…
PRAIB: Peer Review AI Benchmark of Behaviour of LLM-Assisted Reviewing
Krzysztof Żurawicki, Julia Farganus, Arkadiusz GaweŠ+2
The growing number of submitted papers has motivated the exploration of Large Language Models (LLMs) as a means to support and augment the peer review process, particularly in term…
Geometry of Knowledge Allows Extending Diversity Boundaries of Large Language Models
Mateusz BystroÅski, Doheon Han, Nitesh V. Chawla +1
Starting from the hypothesis that knowledge in semantic space is organized along structured manifolds, we argue that this geometric structure renders the space explorable. By trave…
LatentPrompt: Optimizing Promts in Latent Space
Mateusz BystroÅski, Grzegorz Piotrowski, Nitesh V. Chawla +1
Recent advances have shown that optimizing prompts for Large Language Models (LLMs) can significantly improve task performance, yet many optimization techniques rely on heuristics…
SMOTExT: SMOTE meets Large Language Models
Mateusz BystroÅski, MikoÅaj HoÅysz, Grzegorz Piotrowski +2
Data scarcity and class imbalance are persistent challenges in training robust NLP models, especially in specialized domains or low-resource settings. We propose a novel technique,…