Zobrazeno 1 - 10
of 528
pro vyhledávání: '"Korhonen, Anna"'
Autor:
Fytas, Panagiotis, Breger, Anna, Selby, Ian, Baker, Simon, Shahipasand, Shahab, Korhonen, Anna
Developing imaging models capable of detecting pathologies from chest X-rays can be cost and time-prohibitive for large datasets as it requires supervision to attain state-of-the-art performance. Instead, labels extracted from radiology reports may s
Externí odkaz:
http://arxiv.org/abs/2408.04121
Multiple choice question answering tasks evaluate the reasoning, comprehension, and mathematical abilities of Large Language Models (LLMs). While existing benchmarks employ automatic translation for multilingual evaluation, this approach is error-pro
Externí odkaz:
http://arxiv.org/abs/2407.12402
Human label variation (HLV) is a valuable source of information that arises when multiple human annotators provide different labels for valid reasons. In Natural Language Inference (NLI) earlier approaches to capturing HLV involve either collecting a
Externí odkaz:
http://arxiv.org/abs/2406.17600
Large language models (LLMs) have shown promising abilities as cost-effective and reference-free evaluators for assessing language generation quality. In particular, pairwise LLM evaluators, which compare two generated texts and determine the preferr
Externí odkaz:
http://arxiv.org/abs/2406.11370
The surge of interest in culturally aware and adapted Natural Language Processing (NLP) has inspired much recent research. However, the lack of common understanding of the concept of "culture" has made it difficult to evaluate progress in this emergi
Externí odkaz:
http://arxiv.org/abs/2406.03930
Top-view perspective denotes a typical way in which humans read and reason over different types of maps, and it is vital for localization and navigation of humans as well as of `non-human' agents, such as the ones backed by large Vision-Language Mode
Externí odkaz:
http://arxiv.org/abs/2406.02537
Large language models (LLMs) often exhibit undesirable behaviours, such as generating untruthful or biased content. Editing their internal representations has been shown to be effective in mitigating such behaviours on top of the existing alignment m
Externí odkaz:
http://arxiv.org/abs/2405.09719
Autor:
Li, Yaoyiran, Zhai, Xiang, Alzantot, Moustafa, Yu, Keyi, Vulić, Ivan, Korhonen, Anna, Hammad, Mohamed
Traditional recommender systems such as matrix factorization methods rely on learning a shared dense embedding space to represent both items and user preferences. Sequence models such as RNN, GRUs, and, recently, Transformers have also excelled in th
Externí odkaz:
http://arxiv.org/abs/2405.02429
Autor:
Liu, Yinhong, Zhou, Han, Guo, Zhijiang, Shareghi, Ehsan, Vulić, Ivan, Korhonen, Anna, Collier, Nigel
Large Language Models (LLMs) have demonstrated promising capabilities as automatic evaluators in assessing the quality of generated natural language. However, LLMs still exhibit biases in evaluation and often struggle to generate coherent evaluations
Externí odkaz:
http://arxiv.org/abs/2403.16950
Supervised fine-tuning (SFT), supervised instruction tuning (SIT) and in-context learning (ICL) are three alternative, de facto standard approaches to few-shot learning. ICL has gained popularity recently with the advent of LLMs due to its simplicity
Externí odkaz:
http://arxiv.org/abs/2403.01929