REVIEW 2 cited by
Neuro-Symbolic AI: Explainability, Challenges, and Future Trends
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
Explainability is an essential reason limiting the application of neural networks in many vital fields. Although neuro-symbolic AI hopes to enhance the overall explainability by leveraging the transparency of symbolic learning, the results are less evident than imagined. This article proposes a classification for explainability by considering both model design and behavior of 191 studies from 2013, focusing on neuro-symbolic AI, hoping to inspire scholars who want to understand the explainability of neuro-symbolic AI. Precisely, we classify them into five categories by considering whether the form of bridging the representation differences is readable as their design factor, if there are representation differences between neural networks and symbolic logic learning, and whether a model decision or prediction process is understandable as their behavior factor: implicit intermediate representations and implicit prediction, partially explicit intermediate representations and partially explicit prediction, explicit intermediate representations or explicit prediction, explicit intermediate representation and explicit prediction, unified representation and explicit prediction. We also analyzed the research trends and three significant challenges: unified representations, explainability and transparency, and sufficient cooperation from neural networks and symbolic learning. Finally, we put forward suggestions for future research in three aspects: unified representations, enhancing model explainability, ethical considerations, and social impact.
Forward citations
Cited by 2 Pith papers
-
AI Mother Tongue: Self-Emergent Communication in MARL via Endogenous Symbol Systems
Agents with a shared discrete-symbol codebook reportedly converge on cooperative communication in a Prisoner's Dilemma variant, but the paper provides no reproducible data to support the claim.
-
CoreThink: A Symbolic Reasoning Layer to reason over Long Horizon Tasks with LLMs
The paper claims a symbolic orchestration layer, CoreThink, achieves state-of-the-art results on seven coding and reasoning benchmarks with no training, but provides no verifiable implementation or method details.
Discussion (0). Continue with ORCID to comment.