{"ID":6267019,"CreatedAt":"2026-07-10T01:11:38.759438437Z","UpdatedAt":"2026-07-12T03:12:04.745660124Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.08080","arxiv_id":"2607.08080","title":"MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction","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.","short_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 mod...","url_abs":"https://arxiv.org/abs/2607.08080","url_pdf":"https://arxiv.org/pdf/2607.08080v1","authors":"[\"Ao Hong\",\"Lehang Wang\",\"Zhirun Yue\",\"Mingxin Wang\",\"Zihan Wang\",\"Houde Liu\"]","published":"2026-07-09T03:20:54Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":614070,"CreatedAt":"2026-07-10T01:11:38.759438437Z","UpdatedAt":"2026-07-10T01:11:38.759438437Z","DeletedAt":null,"paper_id":6267019,"paper_url":"https://arxiv.org/abs/2607.08080","paper_title":"MASTE: A Multi-Agent Pipeline for Zero-Shot Aspect Sentiment Triplet Extraction","repo_url":"https://github.com/Hankerlove/MASTE","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}