StorySparkQA: Expert-Annotated QA Pairs with Real-World Knowledge for Children's Story-Based Learning
Interactive story reading is common in early childhood education, where teachers expect to
teach both language skills and real-world knowledge beyond the story. While many story …
teach both language skills and real-world knowledge beyond the story. While many story …
Enhancing Text Classification through LLM-Driven Active Learning and Human Annotation
H Rouzegar, M Makrehchi - arXiv preprint arXiv:2406.12114, 2024 - arxiv.org
In the context of text classification, the financial burden of annotation exercises for creating
training data is a critical issue. Active learning techniques, particularly those rooted in …
training data is a critical issue. Active learning techniques, particularly those rooted in …
More Samples or More Prompts? Exploring Effective Few-Shot In-Context Learning for LLMs with In-Context Sampling
While most existing works on LLM prompting techniques focus only on how to select a better
set of data samples inside one single prompt input (In-Context Learning or ICL), why can not …
set of data samples inside one single prompt input (In-Context Learning or ICL), why can not …
Vital Insight: Assisting Experts' Sensemaking Process of Multi-modal Personal Tracking Data Using Visualization and LLM
Researchers have long recognized the socio-technical gaps in personal tracking research,
where machines can never fully model the complexity of human behavior, making it only …
where machines can never fully model the complexity of human behavior, making it only …
Automated Collection of Evaluation Dataset for Semantic Search in Low-Resource Domain Language
Domain-specific languages that use a lot of specific terminology often fall into the category of
low-resource languages. Collecting test datasets in a narrow domain is time-consuming and …
low-resource languages. Collecting test datasets in a narrow domain is time-consuming and …
Automatic Bottom-Up Taxonomy Construction: A Software Application Domain Study
C Sas, A Capiluppi - arXiv preprint arXiv:2409.15881, 2024 - arxiv.org
Previous research in software application domain classification has faced challenges due to
the lack of a proper taxonomy that explicitly models relations between classes. As a result …
the lack of a proper taxonomy that explicitly models relations between classes. As a result …
How to Discern Important Urgent News?
O Vasilyev, J Bohannon - arXiv preprint arXiv:2402.10302, 2024 - arxiv.org
We found that a simple property of clusters in a clustered dataset of news correlate strongly
with importance and urgency of news (IUN) as assessed by LLM. We verified our finding …
with importance and urgency of news (IUN) as assessed by LLM. We verified our finding …
GPTA: Generative Prompt Tuning Assistant for Synergistic Downstream Neural Network Enhancement with LLMs
This study introduces GPTA, a Large Language Model assistance training framework, that
enhances the training of downstream task models via prefix prompt. By minimizing data …
enhances the training of downstream task models via prefix prompt. By minimizing data …
Intent Identification Using Few-Shot and Active Learning with User Feedback
SG Yuvaraj, B Benatallah, HR Motahari-Nezhad… - … Conference on Web …, 2024 - Springer
Collaboration tools contain many intents in workplace conversation, and identifying these
intents is important to increase workplace productivity. However, labelling these intents for a …
intents is important to increase workplace productivity. However, labelling these intents for a …