Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Fan, Caoyun"'
In-Context Learning (ICL) is an important paradigm for adapting Large Language Models (LLMs) to downstream tasks through a few demonstrations. Despite the great success of ICL, the limitation of the demonstration number may lead to demonstration bias
Externí odkaz:
http://arxiv.org/abs/2312.07476
Game theory, as an analytical tool, is frequently utilized to analyze human behavior in social science research. With the high alignment between the behavior of Large Language Models (LLMs) and humans, a promising research direction is to employ LLMs
Externí odkaz:
http://arxiv.org/abs/2312.05488
Chain-of-Thought (CoT) is a technique that guides Large Language Models (LLMs) to decompose complex tasks into multi-step reasoning through intermediate steps in natural language form. Briefly, CoT enables LLMs to think step by step. However, althoug
Externí odkaz:
http://arxiv.org/abs/2310.11721
Multi-Label Text Classification (MLTC) aims to assign the most relevant labels to each given text. Existing methods demonstrate that label dependency can help to improve the model's performance. However, the introduction of label dependency may cause
Externí odkaz:
http://arxiv.org/abs/2310.07588
Counterfactually-Augmented Data (CAD) -- minimal editing of sentences to flip the corresponding labels -- has the potential to improve the Out-Of-Distribution (OOD) generalization capability of language models, as CAD induces language models to explo
Externí odkaz:
http://arxiv.org/abs/2310.06666
When modeling related tasks in computer vision, Multi-Task Learning (MTL) can outperform Single-Task Learning (STL) due to its ability to capture intrinsic relatedness among tasks. However, MTL may encounter the insufficient training problem, i.e., s
Externí odkaz:
http://arxiv.org/abs/2302.09352
Counterfactually-Augmented Data (CAD) has the potential to improve language models' Out-Of-Distribution (OOD) generalization capability, as CAD induces language models to exploit causal features and exclude spurious correlations. However, the empiric
Externí odkaz:
http://arxiv.org/abs/2302.09345
Recent work for image captioning mainly followed an extract-then-generate paradigm, pre-extracting a sequence of object-based features and then formulating image captioning as a single sequence-to-sequence task. Although promising, we observed two pr
Externí odkaz:
http://arxiv.org/abs/2105.08573
Publikováno v:
In Expert Systems With Applications 15 March 2024 238 Part C