Research

Paper

AI LLM March 17, 2026

RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recovery

Authors

Abhishek Kumar, Aashraya Sachdeva

Abstract

Entity recognition in Automatic Speech Recognition (ASR) is challenging for rare and domain-specific terms. In domains such as finance, medicine, and air traffic control, these errors are costly. If the entities are entirely absent from the ASR output, post-ASR correction becomes difficult. To address this, we introduce RECOVER, an agentic correction framework that serves as a tool-using agent. It leverages multiple hypotheses as evidence from ASR, retrieves relevant entities, and applies Large Language Model (LLM) correction under constraints. The hypotheses are used using different strategies, namely, 1-Best, Entity-Aware Select, Recognizer Output Voting Error Reduction (ROVER) Ensemble, and LLM-Select. Evaluated across five diverse datasets, it achieves 8-46% relative reductions in entity-phrase word error rate (E-WER) and increases recall by up to 22 percentage points. The LLM-Select achieves the best overall performance in entity correction while maintaining overall WER.

Metadata

arXiv ID: 2603.16411
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-17
Fetched: 2026-03-18 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.16411v1</id>\n    <title>RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recovery</title>\n    <updated>2026-03-17T11:48:12Z</updated>\n    <link href='https://arxiv.org/abs/2603.16411v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.16411v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Entity recognition in Automatic Speech Recognition (ASR) is challenging for rare and domain-specific terms. In domains such as finance, medicine, and air traffic control, these errors are costly. If the entities are entirely absent from the ASR output, post-ASR correction becomes difficult. To address this, we introduce RECOVER, an agentic correction framework that serves as a tool-using agent. It leverages multiple hypotheses as evidence from ASR, retrieves relevant entities, and applies Large Language Model (LLM) correction under constraints. The hypotheses are used using different strategies, namely, 1-Best, Entity-Aware Select, Recognizer Output Voting Error Reduction (ROVER) Ensemble, and LLM-Select. Evaluated across five diverse datasets, it achieves 8-46% relative reductions in entity-phrase word error rate (E-WER) and increases recall by up to 22 percentage points. The LLM-Select achieves the best overall performance in entity correction while maintaining overall WER.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='eess.AS'/>\n    <published>2026-03-17T11:48:12Z</published>\n    <arxiv:comment>Under review. Submitted to Interspeech 2026</arxiv:comment>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Abhishek Kumar</name>\n    </author>\n    <author>\n      <name>Aashraya Sachdeva</name>\n    </author>\n  </entry>"
}