Papers by Tommaso Bonetti
Comparing Human and Large Language Model Interpretation of Implicit Information (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are a popular approach for generating text indistinguishable from human-generated language. |
| Approach: | They propose an LLM-based pipeline that builds a structured knowledge graph from a context sentence by extracting relational triplets, validating implicit inferences, and analyzing temporal relations. |
| Outcome: | The proposed pipeline builds a structured knowledge graph from a context sentence by extracting relational triplets, validating implicit inferences, and analyzing temporal relations. |