Other formats:
BibTeX
LaTeX
RIS
@inproceedings{2425558,
author = {Štefánik, Michal and Kadlčík, Marek and Sojka, Petr},
address = {Bangkok, Thailand},
booktitle = {Findings of the Association for Computational Linguistics ACL 2024},
editor = {Lun-Wei Ku, Andre Martins, Vivek Srikumar},
keywords = {data efficiency; LLM; concept-aware training; in-context learning},
howpublished = {elektronická verze "online"},
language = {eng},
location = {Bangkok, Thailand},
isbn = {979-8-89176-099-8},
pages = {12335-12352},
publisher = {Association for Computational Linguistics},
title = {Concept-aware Data Construction Improves In-context Learning of Language Models},
url = {https://aclanthology.org/2024.findings-acl.733/},
year = {2024}
}
TY - JOUR
ID - 2425558
AU - Štefánik, Michal - Kadlčík, Marek - Sojka, Petr
PY - 2024
TI - Concept-aware Data Construction Improves In-context Learning of Language Models
PB - Association for Computational Linguistics
CY - Bangkok, Thailand
SN - 9798891760998
KW - data efficiency
KW - LLM
KW - concept-aware training
KW - in-context learning
UR - https://aclanthology.org/2024.findings-acl.733/
N2 - Many recent language models (LMs) are capable of in-context learning (ICL), manifested in the LMs’ ability to perform a new task solely from natural-language instruction. Previous work curating in-context learners assumes that ICL emerges from a vast over-parametrization or the scale of multi-task training. However, recent theoretical work attributes the ICL ability to concept-dependent training data and creates functional in-context learners even in small-scale, synthetic settings.In this work, we practically explore this newly identified axis of ICL quality. We propose Concept-aware Training (CoAT), a framework for constructing training scenarios that make it beneficial for the LM to learn to utilize the analogical reasoning concepts from demonstrations. We find that by using CoAT, pre-trained transformers can learn to better utilise new latent concepts from demonstrations and that such ability makes ICL more robust to the functional deficiencies of the previous models. Finally, we show that concept-aware in-context learners are much more effective in in-context learning a majority of unseen tasks compared to traditional instruction tuning, and fare comparably also to previous in-context learners trained in large-scale multitask learning requiring magnitudes of more training data.
ER -
ŠTEFÁNIK, Michal, Marek KADLČÍK and Petr SOJKA. Concept-aware Data Construction Improves In-context Learning of Language Models. Online. In Lun-Wei Ku, Andre Martins, Vivek Srikumar. \textit{Findings of the Association for Computational Linguistics ACL 2024}. Bangkok, Thailand: Association for Computational Linguistics, 2024, p.~12335-12352. ISBN~979-8-89176-099-8.
|
