.png){kind=icon}
.png){kind=icon}
Return
From implicit parameters to explicit knowledge graphs: A structured knowledge recall framework for bidirectional generalization in LLMs
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2026.133844.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">
Introduce a KG-based evaluation revealing LLMs’ insufficient knowledge understanding.
</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">
Mitigate the ”Reversal Curse” and enhance the bidirectional generalization of LLMs.
</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">
Reveal that self-recalled knowledge surpasses external injection for reasoning tasks.
</div></span></li>
</ul>
Keywords:
Large language models
Knowledge graph
Fine-tuning
Knowledge management
Bidirectional generalization
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W
Organization
View more organizations