3 citations · 5 across the 12 of their papers we have counts for
4 papers · 1 filter
Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches
Teddy Ferdinan, Bartłomiej Koptyra, Mikołaj 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 --…
What properties of reasoning supervision are associated with improved downstream model quality?
Mikołaj Langner, Dzmitry Pihulski, Jan Eliasz +5
Validating training data for reasoning models typically requires expensive trial-and-error fine-tuning cycles. In this work, we investigate whether the utility of a reasoning datas…
AggTruth: Contextual Hallucination Detection using Aggregated Attention Scores in LLMs
Piotr Matys, Jan Eliasz, Konrad Kiełczyński +4
In real-world applications, Large Language Models (LLMs) often hallucinate, even in Retrieval-Augmented Generation (RAG) settings, which poses a significant challenge to their depl…
Modeling Uncertainty in Personalized Emotion Prediction with Normalizing Flows
Piotr Miłkowski, Konrad Karanowski, Patryk Wielopolski +3
Designing predictive models for subjective problems in natural language processing (NLP) remains challenging. This is mainly due to its non-deterministic nature and different perce…