Zobrazeno 1 - 10
of 335
pro vyhledávání: '"Kędziorski, A."'
Autor:
Lovering, Charles, Krumdick, Michael, Lai, Viet Dac, Kumar, Nilesh, Reddy, Varshini, Koncel-Kedziorski, Rik, Tanner, Chris
Some information is factual (e.g., "Paris is in France"), whereas other information is probabilistic (e.g., "the coin flip will be a [Heads/Tails]."). We believe that good Language Models (LMs) should understand and reflect this nuance. Our work inve
Externí odkaz:
http://arxiv.org/abs/2410.16007
Autor:
Reddy, Varshini, Koncel-Kedziorski, Rik, Lai, Viet Dac, Krumdick, Michael, Lovering, Charles, Tanner, Chris
For large language models (LLMs) to be effective in the financial domain -- where each decision can have a significant impact -- it is necessary to investigate realistic tasks and data. Financial professionals often interact with documents that are h
Externí odkaz:
http://arxiv.org/abs/2401.06915
Autor:
Koncel-Kedziorski, Rik, Krumdick, Michael, Lai, Viet, Reddy, Varshini, Lovering, Charles, Tanner, Chris
Answering questions within business and finance requires reasoning, precision, and a wide-breadth of technical knowledge. Together, these requirements make this domain difficult for large language models (LLMs). We introduce BizBench, a benchmark for
Externí odkaz:
http://arxiv.org/abs/2311.06602
Evaluation of QA systems is very challenging and expensive, with the most reliable approach being human annotations of correctness of answers for questions. Recent works (AVA, BEM) have shown that transformer LM encoder based similarity metrics trans
Externí odkaz:
http://arxiv.org/abs/2309.12250
Recent studies show that sentence-level extractive QA, i.e., based on Answer Sentence Selection (AS2), is outperformed by Generation-based QA (GenQA) models, which generate answers using the top-k answer sentences ranked by AS2 models (a la retrieval
Externí odkaz:
http://arxiv.org/abs/2305.15344
Autor:
Kędziorski, Piotr1 (AUTHOR) marcin.jagoda@tu.koszalin.pl, Jagoda, Marcin1 (AUTHOR), Tysiąc, Paweł2 (AUTHOR) pawel.tysiac@pg.edu.pl, Katzer, Jacek3 (AUTHOR) jacek.katzer@uwm.edu.pl
Publikováno v:
Materials (1996-1944). Nov2024, Vol. 17 Issue 22, p5445. 26p.
Autor:
Urbańczyk, Tomasz1 (AUTHOR) tomek.urbanczyk@uj.edu.pl, Kędziorski, Andrzej2 (AUTHOR) andrzej.kedziorski@fizyka.umk.pl, Krośnicki, Marek3 (AUTHOR) marek.krosnicki@ug.edu.pl, Koperski, Jarosław1 (AUTHOR) jaroslaw.koperski@uj.edu.pl
Publikováno v:
Molecules. Oct2024, Vol. 29 Issue 19, p4657. 54p.
Autor:
Gabburo, Matteo, Koncel-Kedziorski, Rik, Garg, Siddhant, Soldaini, Luca, Moschitti, Alessandro
Recent studies show that Question Answering (QA) based on Answer Sentence Selection (AS2) can be improved by generating an improved answer from the top-k ranked answer sentences (termed GenQA). This allows for synthesizing the information from multip
Externí odkaz:
http://arxiv.org/abs/2210.12865
Autor:
Flasz, Barbara, Babczyńska, Agnieszka, Tarnawska, Monika, Ajay, Amrendra K., Kędziorski, Andrzej, Napora-Rutkowski, Łukasz, Augustyniak, Maria
Publikováno v:
In Biochemical and Biophysical Research Communications 3 December 2024 736
Autor:
Babczyńska, Agnieszka, Tarnawska, Monika, Czaja, Klaudia, Flasz, Barbara, Ajay, Amrendra K., Napora-Rutkowski, Łukasz, Rozpędek, Katarzyna, Świerczek, Ewa, Kędziorski, Andrzej, Augustyniak, Maria
Publikováno v:
In Chemosphere November 2024 367