On a new 50-item thermodynamics benchmark, the best LLM scored 82%, below the authors' 95% tutoring-safety threshold, with diagram-based questions near chance.
Extracting Blockchain Concepts from Text
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Blockchains provide a mechanism through which mutually distrustful remote parties can reach consensus on the state of a ledger of information. With the great acceleration with which this space is developed, the demand for those seeking to learn about blockchain also grows. Being a technical subject, it can be quite intimidating to start learning. For this reason, the main objective of this project was to apply machine learning models to extract information from whitepapers and academic articles focused on the blockchain area to organize this information and aid users to navigate the space.
fields
physics.ed-ph 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
From Canonical to Complex: Benchmarking LLM Capabilities in Undergraduate Thermodynamics
On a new 50-item thermodynamics benchmark, the best LLM scored 82%, below the authors' 95% tutoring-safety threshold, with diagram-based questions near chance.