.png){kind=icon}
.png){kind=icon}
Return
KA2L: A knowledge-aware active learning framework for LLMs
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2026.133951.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
<ul class="list">
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="p0001">
KA2L targets unmastered knowledge to guide efficient LLM fine-tuning.
</div></span></li>
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="p0002">
Unsupervised hidden state probing reveals the distribution of LLM knowledge.
</div></span></li>
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="p0003">
Generates training samples effectively from the model’s unknown latent space.
</div></span></li>
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="p0004">
Reduces data and computation costs by 50% while maintaining model performance.
</div></span></li>
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="p0005">
Offers a practical solution for LLM enhancement in low-resource scenarios.
</div></span></li>
</ul>
Keywords:
Large language models
Active learning
LLM hallucination detection
Knowledge boundary
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W