# FormBharo: Designing and Evaluating a Voice Agent for Conversational Form Filling in Rural India

arXiv: https://arxiv.org/abs/2608.06027 · HTML: https://mlsanity.com/paper/2608.06027/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 35 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 7 of 7)

- [IndicVoices: Towards building an Inclusive Multilingual Speech Dataset for Indian Languages](https://mlsanity.com/paper/2403.01926/) (2024)
- [IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages](https://mlsanity.com/paper/2208.11761/) (2022)
- [EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents](https://mlsanity.com/paper/2605.13841/) (2026)
- [VAANI: Capturing the language landscape for an inclusive digital India](https://mlsanity.com/paper/2603.28714/) (2026)
- [Speech-based Slot Filling using Large Language Models](https://mlsanity.com/paper/2311.07418/) (2023)
- [Recognizing Every Voice: Towards Inclusive ASR for Rural Bhojpuri Women](https://mlsanity.com/paper/2506.09653/) (2025)
- [Precarious Experiences: Citizens' Frustrations, Anxieties and Burdens of an Online Welfare Benefit System](https://mlsanity.com/paper/2405.08515/) (2024)

## Abstract (arXiv)

In India, almost every social benefit starts with a form, yet the people who need these benefits most are often unable to read or write. Reaching them requires a spoken conversation. Today that work falls to frontline health workers who enroll beneficiaries one at a time, a poor use of stretched capacity. We built FormBharo ("fill the form" in Hindi), a voice agent that fills a structured form over a phone call under tight latency and cost budgets by pairing Large Language Models (LLMs) with deterministic, rule-based validation and flow control. It is being piloted with ARMMAN, an NGO running large-scale maternal and child mobile-health programs in India, to enroll low-income, Hindi-speaking mothers in antenatal and postnatal care. To our knowledge, it is the first voice agent piloted to fill an enrollment form for this population. We openly release FormVoiceAgentBench, a benchmark pairing human-recorded Hindi audio with 3,760 multi-turn conversation tests across 960 simulated calls, to evaluate our agent's components (transcription, extraction, reply generation) and end-to-end form completion under real acoustic variations. Form completion drops by up to ~41 points when LLMs receive error-prone real-speech transcripts instead of reference ones. The rule-based controls recover many turn-level extraction errors, helping smaller, cheaper models match or surpass frontier models on form completion. Component performance does not predict end-to-end performance: GPT-5.5 leads turn-level extraction accuracy on reference transcripts (99.8%) but ranks lower on form completion. Since errors both propagate and cancel across the pipeline, the optimal model choice of models emerges only through end-to-end evaluation. Finally, no single model is best across accuracy, cost, and latency at once, so we use a Pareto-based weighted-sum scalarization to select a deployable configuration balancing the three.