An ensemble of BERT, cosine similarity, NLI, and LLM judgment with a meta-classifier detects distorted simplifications, while an LLM post-editor trades simplicity for faithfulness.
Vendeville, et al., Overview of the CLEF 2025 SimpleText Task 2: Identify and Avoid Hallucination, in: G
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
dataset 1polarities
use dataset 1representative citing papers
citing papers explorer
-
Hallucination Detection and Mitigation in Scientific Text Simplification using Ensemble Approaches: DS@GT at CLEF 2025 SimpleText
An ensemble of BERT, cosine similarity, NLI, and LLM judgment with a meta-classifier detects distorted simplifications, while an LLM post-editor trades simplicity for faithfulness.