Research map / Large language models / Agents, code and math
QART: A System for Real-Time Holistic Quality Assurance for Contact Center Dialogues
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add conversational meta-attributes to content attributes for emotion CRF (ablation) | CRF emotion categorization · customer emotion | accuracy (%): 44.7 -> 62.4 | Helped |
| add meta-attributes to content attributes (ablation) | CRF sentiment categorization · customer sentiment | accuracy (%): 66.1 -> 69.5 | Helped |
| add meta-attributes to content attributes (ablation) | CRF · agent emotion/sentiment | accuracy (%): 79.3 -> 79.8 (emotion); 82.1 -> 82.0 (sentiment) | No clear effect |
| use content attributes instead of bag-of-words only (ablation) | CRF · customer emotion | accuracy (%): 40.5 -> 44.7 | Helped |
| use sequence labeling CRF instead of independent-turn SVM for conversation structure | structure detection with rules · conversation structure | overall accuracy (%): 80.3 -> 83.9 | Helped |
| unsupervised K-means instead of supervised CRF | structure detection · conversation structure | overall accuracy (%): 83.9 -> 82.8 | No clear effect |
| use QART assistance instead of 10% sampling manual QA | quality analyst · contact center QA | precision/recall/time: time 1150 s -> 2.2 s (compliance); emotion precision 0.90 -> 0.61 | Mixed |
Closest papers by meaning
- Mix-Ecom: Towards Mixed-Type E-Commerce Dialogues with Complex Domain Rules (ICLR 2026 · similarity 0.80)
- QA-Calibration of Language Model Confidence Scores (ICLR 2025 · similarity 0.80)
- A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering (NeurIPS 2026 · similarity 0.79)
- SubjECTive-QA: Measuring Subjectivity in Earnings Call Transcripts' QA Through Six-Dimensional Feature Analysis (NeurIPS 2024 · similarity 0.79)
- From Conversation to Query Execution: Benchmarking User and Tool Interactions for EHR Database Agents (ICLR 2026 · similarity 0.79)
- TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning (NeurIPS 2026 · similarity 0.79)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.