336 citations
12 papers
UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough
Ryszard Tuora, Mateusz Galiński, Michał Godziszewski +4
One of the key problems in Retrieval-augmented generation (RAG) systems is that chunk-based retrieval pipelines represent the source chunks as atomic objects, mixing the informatio…
A Benchmark for Audio Reasoning Capabilities of Multimodal Large Language Models
Iwona Christop, Mateusz Czyżnikiewicz, Paweł Skórzewski +4
The present benchmarks for testing the audio modality of multimodal large language models concentrate on testing various audio tasks such as speaker diarization or gender identific…
Tag and correct: high precision post-editing approach to correction of speech recognition errors
Tomasz Ziętkiewicz
This paper presents a new approach to the problem of correcting speech recognition errors by means of post-editing. It consists of using a neural sequence tagger that learns how to…
Can We Use Probing to Better Understand Fine-tuning and Knowledge Distillation of the BERT NLU?
Jakub Hościłowicz, Marcin Sowański, Piotr Czubowski +1
In this article, we use probing to investigate phenomena that occur during fine-tuning and knowledge distillation of a BERT-based natural language understanding (NLU) model. Our ul…
Spectrum Correction: Acoustic Scene Classification with Mismatched Recording Devices
Michał Kośmider
Machine learning algorithms, when trained on audio recordings from a limited set of devices, may not generalize well to samples recorded using other devices with different frequenc…
Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts
Tomasz Stanisławek, Filip Graliński, Anna Wróblewska +5
The relevance of the Key Information Extraction (KIE) task is increasingly important in natural language processing problems. But there are still only a few well-defined problems t…