Can we use GPT-4 as a mathematics evaluator in education?: Exploring the efficacy and limitation of LLM-based automatic assessment system for open-ended …

U Lee, Y Kim, S Lee, J Park, J Mun, E Lee… - International Journal of …, 2024 - Springer
This paper explores the potential of Large Language Models (LLMs), specifically GPT-4, to
enhance the precision and effectiveness of Automated Assessment Systems (AAS) for open …

Large Language Models Are No Longer Shallow Parsers

Y Tian, F Xia, Y Song - Proceedings of the 62nd Annual Meeting of …, 2024 - aclanthology.org
The development of large language models (LLMs) brings significant changes to the field of
natural language processing (NLP), enabling remarkable performance in various high-level …

ICE-SEARCH: A Language Model-Driven Feature Selection Approach

T Yang, T Yang, F Lyu, S Liu - arXiv preprint arXiv:2402.18609, 2024 - arxiv.org
This study unveils the In-Context Evolutionary Search (ICE-SEARCH) method, which is
among the first works that melds large language models (LLMs) with evolutionary algorithms …

AutoCAP: Towards Automatic Cross-lingual Alignment Planning for Zero-shot Chain-of-Thought

Y Zhang, Q Chen, M Li, W Che, L Qin - arXiv preprint arXiv:2406.13940, 2024 - arxiv.org
Cross-lingual chain-of-thought can effectively complete reasoning tasks across languages,
which gains increasing attention. Recently, dominant approaches in the literature improve …

Are All Languages Equal? Curriculum Learning over Different Languages

G Pucci¹, L Ranaldi, FM Zanzotto¹ - Proceedings of the 9th Italian …, 2024 - books.google.com
Curriculum Learning (CL) is emerging as a relevant technique to reduce the cost of pre-
training Large Language Models. The idea, tested for the English language, is to train LLMs …

[PDF][PDF] Teasing LLMs Adapted to Italian.

L Ranaldi, G Pucci, ES Ruzzetti, FM Zanzotto, A Freitas - CLiC-it, 2023 - ceur-ws.org
Abstract Instruction-tuned Large Language Models (It-LLMs) are changing NLP thanks to
their easy accessibility. These models seem able to grasp language, solve complex tasks …

[PDF][PDF] The limits of Italian in Reasoning Tasks

L Ranaldi, F Ranaldi, G Pucci, ES Ruzzetti… - 2024 - ceur-ws.org
Earlier works have been showing the efficacy of reasoning methods in eliciting step-wise
reasoning of large language models (LLMs) by operating via in-context demonstrations …

Decompose, Analyze and Rethink: Solving Intricate Problems with Human-like Reasoning Cycle

S Xue, Z Huang, J Liu, X Lin, Y Ning, B Jin, X Li… - The Thirty-eighth Annual … - openreview.net
In this paper, we introduce DeAR (_Decompose-Analyze-Rethink_), a framework that
iteratively builds a reasoning tree to tackle intricate problems within a single large language …