Další formáty:
BibTeX
LaTeX
RIS
@inproceedings{2300360, author = {Štefánik, Michal and Kadlčík, Marek}, address = {Toronto, Canada}, booktitle = {Proceedings of the 1st Workshop on Natural Language Reasoning and Structured Explanations (NLRSE)}, keywords = {in-context learning; few-shot learning; generalization}, howpublished = {elektronická verze "online"}, language = {eng}, location = {Toronto, Canada}, isbn = {978-1-959429-94-4}, pages = {107-115}, publisher = {The Association for Computational Linguistics}, title = {Can In-context Learners Learn a Reasoning Concept from Demonstrations?}, year = {2023} }
TY - JOUR ID - 2300360 AU - Štefánik, Michal - Kadlčík, Marek PY - 2023 TI - Can In-context Learners Learn a Reasoning Concept from Demonstrations? PB - The Association for Computational Linguistics CY - Toronto, Canada SN - 9781959429944 KW - in-context learning KW - few-shot learning KW - generalization N2 - Language models exhibit an emergent ability to learn a new task from a small number of input-output demonstrations. However, recent work shows that in-context learners largely rely on their pre-trained knowledge, such as the sentiment of the labels, instead of learning new associations from the input. We argue that the commonly-used few-shot evaluation using a random selection of in-context demonstrations can not disentangle models' reliance on such biases, as most of the randomly-selected demonstrations do not present relations informative for prediction beyond exposing the task's input-output distribution. Therefore, to evaluate models' in-context learning ability independent of models' memory, we introduce a Concept-sharing few-shot learning method choosing the demonstrations that share an underlying concept with the predicted sample. We extract a set of such concepts from available human explanations and measure how much models can benefit from presenting these concepts in few-shot demonstrations. We find that most of the recent in-context learners can not consistently benefit from the demonstrated concepts, irrespective of the model size. However, we note that T0 models are more sensitive to exhibited concepts, benefiting from concept-sharing demonstrations in 7 out of 8 evaluation scenarios. ER -
ŠTEFÁNIK, Michal a Marek KADLČÍK. Can In-context Learners Learn a Reasoning Concept from Demonstrations?. Online. In \textit{Proceedings of the 1st Workshop on Natural Language Reasoning and Structured Explanations (NLRSE)}. Toronto, Canada: The Association for Computational Linguistics, 2023, s.~107-115. ISBN~978-1-959429-94-4.
|