Hallucination Detection and Mitigation in Scientific Text Simplification using Ensemble Approaches: DS@GT at CLEF 2025 SimpleText
By: Krishna Chaitanya Marturi, Heba H. Elwazzan
Potential Business Impact:
Checks if simplified science text is true.
In this paper, we describe our methodology for the CLEF 2025 SimpleText Task 2, which focuses on detecting and evaluating creative generation and information distortion in scientific text simplification. Our solution integrates multiple strategies: we construct an ensemble framework that leverages BERT-based classifier, semantic similarity measure, natural language inference model, and large language model (LLM) reasoning. These diverse signals are combined using meta-classifiers to enhance the robustness of spurious and distortion detection. Additionally, for grounded generation, we employ an LLM-based post-editing system that revises simplifications based on the original input texts.
Similar Papers
LLM-Guided Planning and Summary-Based Scientific Text Simplification: DS@GT at CLEF 2025 SimpleText
Computation and Language
Makes science papers easy to understand.
A Theoretically Grounded Hybrid Ensemble for Reliable Detection of LLM-Generated Text
Computation and Language
Finds fake writing in schoolwork better.
DETECT: Determining Ease and Textual Clarity of German Text Simplifications
Computation and Language
Helps computers judge how well text is simplified.