Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Qian, Junlang"'
Large language models (LLMs) have demonstrated impressive capabilities in various tasks using the in-context learning (ICL) paradigm. However, their effectiveness is often compromised by inherent bias, leading to prompt brittleness, i.e., sensitivity
Externí odkaz:
http://arxiv.org/abs/2405.20612
Prompts play a crucial role in guiding the responses of Large Language Models (LLMs). However, the intricate role of individual tokens in prompts, known as input saliency, in shaping the responses remains largely underexplored. Existing saliency meth
Externí odkaz:
http://arxiv.org/abs/2405.11891
In this study, we investigate in-context learning (ICL) in document-level event argument extraction (EAE) to alleviate the dependency on large-scale labeled data for this task. We introduce the Heuristic-Driven Link-of-Analogy (HD-LoA) prompting to a
Externí odkaz:
http://arxiv.org/abs/2311.06555