MASSIVE Multilingual Abstract Meaning Representation: A Dataset and Baselines for Hallucination Detection

TL;DR

This paper introduces MASSIVE-AMR, the largest multilingual AMR dataset with over 84,000 annotations across 50+ languages, and evaluates large language models for multilingual AMR parsing and hallucination detection.

Contribution

The paper presents MASSIVE-AMR, a large and diverse multilingual AMR dataset, and provides baseline experiments on multilingual parsing and hallucination detection tasks.

Findings

Large language models show promise in multilingual AMR parsing.

Hallucination detection benefits from structured AMR representations.

The dataset enables diverse linguistic and semantic research.

Abstract

Abstract Meaning Representation (AMR) is a semantic formalism that captures the core meaning of an utterance. There has been substantial work developing AMR corpora in English and more recently across languages, though the limited size of existing datasets and the cost of collecting more annotations are prohibitive. With both engineering and scientific questions in mind, we introduce MASSIVE-AMR, a dataset with more than 84,000 text-to-graph annotations, currently the largest and most diverse of its kind: AMR graphs for 1,685 information-seeking utterances mapped to 50+ typologically diverse languages. We describe how we built our resource and its unique features before reporting on experiments using large language models for multilingual AMR and SPARQL parsing as well as applying AMRs for hallucination detection in the context of knowledge base question answering, with results shedding light on persistent issues using LLMs for structured parsing.