Search papers, labs, and topics across Lattice.
This paper introduces MASTE, a multi-agent pipeline designed for zero-shot Aspect Sentiment Triplet Extraction (ASTE), which addresses the limitations of large language models in effectively extracting (aspect, opinion, sentiment) triples from review sentences. By decomposing the ASTE task into four sequential stages, MASTE allows specialized agents to focus on distinct subtasks while conditioning on prior outputs, resulting in improved performance without the need for labeled training data. Experimental results demonstrate that MASTE significantly outperforms existing zero-shot and chain-of-thought LLM approaches, approaching the performance of fully supervised methods across multiple benchmarks.
MASTE achieves zero-shot Aspect Sentiment Triplet Extraction with a multi-agent approach that outperforms traditional LLM methods, even without labeled data.
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.
