MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction

Researchers propose MASTE, a multi-agent pipeline that decomposes aspect sentiment triplet extraction into four sequential stages handled by specialized agents, achieving zero-shot performance that narrows the gap to supervised methods without using labeled data.

arXiv:2607.08080v1 Announce Type: new Abstract: Aspect Sentiment Triplet Extraction ASTE requires jointly identifying aspect, opinion, sentiment triples from a given review sentence. While large language models LLMs achieve strong zero-shot performance on many NLP benchmarks, their effectiveness on ASTE remains limited, as single-pass generation forces the model to determine span boundaries, opinion grouping, and sentiment polarity in a single decoding step. Common remedies, such as few-shot in-context learning and chain-of-thought prompting, offer only marginal improvements and rely heavily on either in-domain demonstrations sampled from labeled training data or carefully engineered reasoning prompts, neither of which is broadly available in zero-shot deployment. Inspired by the classical agent paradigm, we propose MASTE, a multi-agent pipeline for zero-shot Aspect Sentiment Triplet Extraction. MASTE decomposes ASTE into four sequential stages, where specialized agents handle different compositional subtasks with explicit conditioning on prior outputs. This design enables entirely training-free zero-shot ASTE and generalizes across different backbones and datasets. Extensive experiments on four ASTE benchmarks show that MASTE substantially outperforms zero-shot and chain-of-thought LLM baselines under the same backbone, narrowing the gap to fully supervised methods without using any labeled triplets. Code is available at https://github.com/Hankerlove/MASTE.