Researchers have developed a new methodology for analyzing multilingual customer feedback, particularly for public sector organizations like tax administrations. This approach combines large language models (LLMs) with statistical techniques and human oversight to identify emerging service quality issues and potential inequities. The system uses fine-tuned, quantized LLMs and a human-in-the-loop framework to ensure accuracy, efficiency, and context-awareness, reducing LLM fabrication and improving reliability. Evaluations showed the methodology aligns better with expert judgments than baseline models, supporting evidence-based decision-making and enhancing public trust. AI
IMPACT Enhances public sector decision-making by improving the analysis of multilingual customer feedback for fairness and service quality.
RANK_REASON The item is a research paper published on arXiv detailing a new methodology for analyzing service feedback using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX
- Connected Papers
- DagsHub
- Gotit.pub
- Hugging Face
- Influence Flower
- Litmaps
- ScienceCast
- scite Smart Citations
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
