# DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition

arXiv: https://arxiv.org/abs/2605.17900 · HTML: https://mlsanity.com/paper/2605.17900/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 18 May 2026.

## Builds on (most cited first, 13 of 13)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [Hello, It's GPT-2 -- How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1907.05774/) (2019)
- [Few-shot Natural Language Generation for Task-Oriented Dialog](https://mlsanity.com/paper/2002.12328/) (2020)
- [Language Model is All You Need: Natural Language Understanding as Question Answering](https://mlsanity.com/paper/2011.03023/) (2020)
- [ERNIE-GeoL: A Geography-and-Language Pre-trained Model and its Applications in Baidu Maps](https://mlsanity.com/paper/2203.09127/) (2022)
- [Multi-User Chat Assistant (MUCA): a Framework Using LLMs to Facilitate Group Conversations](https://mlsanity.com/paper/2401.04883/) (2024)
- [DLocRL: A Deep Learning Pipeline for Fine-Grained Location Recognition and Linking in Tweets](https://mlsanity.com/paper/1901.07005/) (2019)
- [DuMapper: Towards Automatic Verification of Large-Scale POIs with Street Views at Baidu Maps](https://mlsanity.com/paper/2411.18073/) (2024)
- [GEDIT: Geographic-Enhanced and Dependency-Guided Tagging for Joint POI and Accessibility Extraction at Baidu Maps](https://mlsanity.com/paper/2108.09104/) (2021)
- [HGAMN: Heterogeneous Graph Attention Matching Network for Multilingual POI Retrieval at Baidu Maps](https://mlsanity.com/paper/2409.03504/) (2024)

## Built on by (most cited first, 1 of 1)

- [Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection](https://mlsanity.com/paper/2610.18881/) (2026)

## Abstract (arXiv)

Accurate Point of Interest (POI) attribute acquisition is essential for location-based services, yet traditional modular Interactive Voice Response (IVR) systems suffer from error accumulation and high maintenance overhead. We present DuIVRS-2, a large language model (LLM)-based end-to-end framework designed for large-scale POI attribute acquisition at Baidu Maps. To address the long-tail distribution of real-world interactions, our methodology first employs a finite state machine (FSM)-guided data augmentation strategy to synthesize a balanced and diverse training dataset. We then streamline dialogue management via a selective generation scheme combined with a Chain-of-Thought (CoT) mechanism, which ensures output stability and effectively eliminates hallucinations in industrial settings. To facilitate continuous policy refinement with minimal manual effort, we design a cooperative iterative learning framework that leverages a dual-evaluator voting system. Deployed in production for two months, DuIVRS-2 processed 0.4 million calls daily and achieved a 83.9% Task Success Rate (TSR), outperforming its predecessor by 4 percentage points while maintaining a low reaction time of 130ms. This work provides a production-proven reference for developing robust, cost-effective LLM agents for large-scale industrial dialogue applications.