A training-free backtracking defense that rewrites RAG output at the first sign of privacy leakage improves privacy utility scores by up to 15% over sanitization and prompting baselines on a new healthcare and finance benchmark.
Correction with Backtracking Reduces Hallucination in Summarization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Abstractive summarization aims at generating natural language summaries of a source document that are succinct while preserving the important elements. Despite recent advances, neural text summarization models are known to be susceptible to hallucinating (or more correctly confabulating), that is to produce summaries with details that are not grounded in the source document. In this paper, we introduce a simple yet efficient technique, CoBa, to reduce hallucination in abstractive summarization. The approach is based on two steps: hallucination detection and mitigation. We show that the former can be achieved through measuring simple statistics about conditional word probabilities and distance to context words. Further, we demonstrate that straight-forward backtracking is surprisingly effective at mitigation. We thoroughly evaluate the proposed method with prior art on three benchmark datasets for text summarization. The results show that CoBa is effective and efficient in reducing hallucination, and offers great adaptability and flexibility. Code can be found at https://github.com/zhenzhel/CoBa.
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adaptive Backtracking for Privacy Protection in Large Language Models
A training-free backtracking defense that rewrites RAG output at the first sign of privacy leakage improves privacy utility scores by up to 15% over sanitization and prompting baselines on a new healthcare and finance benchmark.