REVIEW 6 cited by
A Review on Language Models as Knowledge Bases
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recently, there has been a surge of interest in the NLP community on the use of pretrained Language Models (LMs) as Knowledge Bases (KBs). Researchers have shown that LMs trained on a sufficiently large (web) corpus will encode a significant amount of knowledge implicitly in its parameters. The resulting LM can be probed for different kinds of knowledge and thus acting as a KB. This has a major advantage over traditional KBs in that this method requires no human supervision. In this paper, we present a set of aspects that we deem a LM should have to fully act as a KB, and review the recent literature with respect to those aspects.
Forward citations
Cited by 6 Pith papers
-
Epistemic Familiarity is Associated With Belief Stability in Large Language Models
Language models retract previously true answers far more often after seeing unfamiliar synthetic statements than after seeing familiar fictional statements, in both internal probes and prompted behavior.
-
Multi-Ontology Integration with Dual-Axis Propagation for Medical Concept Representation
LINKO integrates multiple medical ontologies with dual-axis graph propagation and LLM-based initialization, improving diagnosis prediction on MIMIC-III and MIMIC-IV.
-
Extracting Probabilistic Knowledge from Large Language Models for Bayesian Network Parameterization
LLM-elicited conditional probabilities can serve as expert-style priors for Bayesian network parameterization, and blending them with data beats both uniform priors and data-only estimation in low-data regimes.
-
The Role of Visualization in LLM-Assisted Knowledge Graph Systems: Effects on User Trust, Exploration, and Workflows
Visualizations designed to increase transparency in an LLM-based knowledge graph query tool actually led users, including experts, to overtrust incorrect outputs.
-
A Graph Perspective to Probe Structural Patterns of Knowledge in Large Language Models
LLM knowledge, measured by self-reported true/false checks on knowledge-graph triplets, shows homophily and degree correlations that a graph neural network exploits to select more effective fine-tuning data.
-
Benchmarking and Rethinking Knowledge Editing for Large Language Models
Under autoregressive and sequential editing, parameter-based knowledge editing methods perform poorly, while the retrieval-based SCR baseline consistently outperforms them across datasets and models.
Discussion (0). Continue with ORCID to comment.