Error-based prompt rewriting and self-correction do not significantly improve GPT-4o product attribute extraction on OA-Mine or AE-110K, and both raise token costs.
In: Proceedings of the 47th ACM SIGIR International Conference on Research and Development in Information Retrieval
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Self-Refinement Strategies for LLM-based Product Attribute Value Extraction
Error-based prompt rewriting and self-correction do not significantly improve GPT-4o product attribute extraction on OA-Mine or AE-110K, and both raise token costs.