Exploring Zero-Shot ACSA with Unified Meaning Representation in Chain-of-Thought Prompting

• URL: http://arxiv.org/abs/2512.19651v1
• Date: Mon, 22 Dec 2025 18:23:37 GMT
• Title: Exploring Zero-Shot ACSA with Unified Meaning Representation in Chain-of-Thought Prompting
• Authors: Filippos Ventirozos, Peter Appleby, Matthew Shardlow,
• Abstract summary: Aspect-Category Sentiment Analysis (ACSA) provides granular insights by identifying specific themes within reviews and their associated sentiment.<n>We argue that leveraging large language models (LLMs) in a zero-shot setting is a practical alternative where resources for data annotation are limited.<n>We propose a novel Chain-of-Thought (CoT) prompting technique that utilise an intermediate Unified Meaning Representation (UMR) to structure the reasoning process for the ACSA task.
• Score: 4.14197005718384
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Aspect-Category Sentiment Analysis (ACSA) provides granular insights by identifying specific themes within reviews and their associated sentiment. While supervised learning approaches dominate this field, the scarcity and high cost of annotated data for new domains present significant barriers. We argue that leveraging large language models (LLMs) in a zero-shot setting is a practical alternative where resources for data annotation are limited. In this work, we propose a novel Chain-of-Thought (CoT) prompting technique that utilises an intermediate Unified Meaning Representation (UMR) to structure the reasoning process for the ACSA task. We evaluate this UMR-based approach against a standard CoT baseline across three models (Qwen3-4B, Qwen3-8B, and Gemini-2.5-Pro) and four diverse datasets. Our findings suggest that UMR effectiveness may be model-dependent. Whilst preliminary results indicate comparable performance for mid-sized models such as Qwen3-8B, these observations warrant further investigation, particularly regarding the potential applicability to smaller model architectures. Further research is required to establish the generalisability of these findings across different model scales.

Related papers

• Data-Efficient Adaptation and a Novel Evaluation Method for Aspect-based Sentiment Analysis [2.3949433621799283]
  ABSA research needs are unmet in high-demand yet low-resource areas such as education and healthcare.<n>Traditional evaluation methods based on exact matches are overly rigid for ABSA tasks.<n>We propose a novel evaluation method, Flexible Text Similarity Matching and Optimal Bipartite Pairing.<n>We present the first ABSA study of small decoder-only generative language models.
  arXiv  Detail & Related papers  (2025-11-04T22:11:10Z)
• Demystifying Network Foundation Models [14.775836458250799]
  This work presents a systematic investigation into the latent knowledge encoded within Network Foundation Models (NFMs)<n>We evaluate four state-of-the-art NFMs, revealing that they all exhibit significant anisotropy, inconsistent feature sensitivity patterns.<n>Our work identifies numerous limitations across all models and demonstrates that addressing them can significantly improve model performance.
  arXiv  Detail & Related papers  (2025-09-27T03:53:46Z)
• The CoT Encyclopedia: Analyzing, Predicting, and Controlling how a Reasoning Model will Think [81.38614558541772]
  We introduce the CoT Encyclopedia, a framework for analyzing and steering model reasoning.<n>Our method automatically extracts diverse reasoning criteria from model-generated CoTs.<n>We show that this framework produces more interpretable and comprehensive analyses than existing methods.
  arXiv  Detail & Related papers  (2025-05-15T11:31:02Z)
• Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection [52.490375806093745]
  The objective of few-shot object detection (FSOD) is to detect novel objects with few training samples.<n>We introduce the side information to alleviate the negative influences derived from the feature space and sample viewpoints.<n>Our model outperforms the previous state-of-the-art methods, significantly improving the ability of FSOD in most shots/splits.
  arXiv  Detail & Related papers  (2025-04-09T17:24:05Z)
• Understanding the Cross-Domain Capabilities of Video-Based Few-Shot Action Recognition Models [3.072340427031969]
  Few-shot action recognition (FSAR) aims to learn a model capable of identifying novel actions in videos using only a few examples. In assuming the base dataset seen during meta-training and novel dataset used for evaluation can come from different domains, cross-domain few-shot learning alleviates data collection and annotation costs. We systematically evaluate existing state-of-the-art single-domain, transfer-based, and cross-domain FSAR methods on new cross-domain tasks.
  arXiv  Detail & Related papers  (2024-06-03T07:48:18Z)
• Self-supervised co-salient object detection via feature correspondence at multiple scales [27.664016341526988]
  This paper introduces a novel two-stage self-supervised approach for detecting co-occurring salient objects (CoSOD) in image groups without requiring segmentation annotations. We train a self-supervised network that detects co-salient regions by computing local patch-level feature correspondences across images. In experiments on three CoSOD benchmark datasets, our model outperforms the corresponding state-of-the-art models by a huge margin.
  arXiv  Detail & Related papers  (2024-03-17T06:21:21Z)
• Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition [57.08108545219043]
  Recognizing novel sub-categories with scarce samples is an essential and challenging research topic in computer vision. Existing literature addresses this challenge by employing local-based representation approaches. This article proposes a novel model, Robust Saliency-aware Distillation (RSaD), for few-shot fine-grained visual recognition.
  arXiv  Detail & Related papers  (2023-05-12T00:13:17Z)
• CrossRE: A Cross-Domain Dataset for Relation Extraction [21.513743126525622]
  CrossRE is a new, freely-available cross-domain benchmark for Relation Extraction (RE) We provide an empirical evaluation with a state-of-the-art model for relation classification. As the meta-data enables us to shed new light on the state-of-the-art model, we provide a comprehensive analysis on the impact of difficult cases.
  arXiv  Detail & Related papers  (2022-10-17T18:33:14Z)
• Exploring Neural Models for Query-Focused Summarization [74.41256438059256]
  We conduct a systematic exploration of neural approaches to query-focused summarization (QFS) We present two model extensions that achieve state-of-the-art performance on the QMSum dataset by a margin of up to 3.38 ROUGE-1, 3.72 ROUGE-2, and 3.28 ROUGE-L.
  arXiv  Detail & Related papers  (2021-12-14T18:33:29Z)
• SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction [51.27558374091491]
  We propose to explicitly teach the model to capture relevant contexts and entity types by supervising and augmenting intermediate steps (SAIS) for relation extraction. Based on a broad spectrum of carefully designed tasks, our proposed SAIS method not only extracts relations of better quality due to more effective supervision, but also retrieves the corresponding supporting evidence more accurately.
  arXiv  Detail & Related papers  (2021-09-24T17:37:35Z)
• Few-Shot Named Entity Recognition: A Comprehensive Study [92.40991050806544]
  We investigate three schemes to improve the model generalization ability for few-shot settings. We perform empirical comparisons on 10 public NER datasets with various proportions of labeled data. We create new state-of-the-art results on both few-shot and training-free settings.
  arXiv  Detail & Related papers  (2020-12-29T23:43:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.