Large Language Models for Czech Aspect-Based Sentiment Analysis

• URL: http://arxiv.org/abs/2508.07860v1
• Date: Mon, 11 Aug 2025 11:24:57 GMT
• Title: Large Language Models for Czech Aspect-Based Sentiment Analysis
• Authors: Jakub Šmíd, Pavel Přibáň, Pavel Král,
• Abstract summary: Small domain-specific models fine-tuned for ABSA outperform general-purpose LLMs in zero-shot and few-shot settings.<n>We analyze how factors such as multilingualism, model size, and recency influence performance and present an error analysis highlighting key challenges.
• Score: 0.8602553195689511
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task that aims to identify sentiment toward specific aspects of an entity. While large language models (LLMs) have shown strong performance in various natural language processing (NLP) tasks, their capabilities for Czech ABSA remain largely unexplored. In this work, we conduct a comprehensive evaluation of 19 LLMs of varying sizes and architectures on Czech ABSA, comparing their performance in zero-shot, few-shot, and fine-tuning scenarios. Our results show that small domain-specific models fine-tuned for ABSA outperform general-purpose LLMs in zero-shot and few-shot settings, while fine-tuned LLMs achieve state-of-the-art results. We analyze how factors such as multilingualism, model size, and recency influence performance and present an error analysis highlighting key challenges, particularly in aspect term prediction. Our findings provide insights into the suitability of LLMs for Czech ABSA and offer guidance for future research in this area.

Related papers

• Extending Czech Aspect-Based Sentiment Analysis with Opinion Terms: Dataset and LLM Benchmarks [1.9779500088459443]
  This paper introduces a novel Czech dataset in the restaurant domain for aspect-based sentiment analysis (ABSA)<n>We conduct extensive experiments using modern Transformer-based models, including large language models (LLMs) in monolingual, cross-lingual, and multilingual settings.<n>A detailed error analysis reveals key challenges, including the detection of subtle opinion terms and nuanced sentiment expressions.
  arXiv  Detail & Related papers  (2026-02-26T08:13:42Z)
• LLaMA-Based Models for Aspect-Based Sentiment Analysis [0.8602553195689511]
  Large language models (LLMs) show promise for various tasks, their performance in compound aspect-based sentiment analysis (ABSA) tasks lags behind fine-tuned models.<n>This paper examines the capabilities of open-source LLMs fine-tuned for ABSA, focusing on LLaMA-based models.<n>We evaluate the performance across four tasks and eight English datasets, finding that the fine-tuned Orca2 model surpasses state-of-the-art results in all tasks.
  arXiv  Detail & Related papers  (2025-08-12T05:30:32Z)
• Ensemble Bayesian Inference: Leveraging Small Language Models to Achieve LLM-level Accuracy in Profile Matching Tasks [0.0]
  This study explores the potential of small language model(SLM) ensembles to achieve accuracy comparable to proprietary large language models (LLMs)<n>We propose Ensemble Bayesian Inference (EBI), a novel approach that applies Bayesian estimation to combine judgments from multiple SLMs.
  arXiv  Detail & Related papers  (2025-04-24T15:55:10Z)
• From Annotation to Adaptation: Metrics, Synthetic Data, and Aspect Extraction for Aspect-Based Sentiment Analysis with Large Language Models [1.5020330976600738]
  This study examines the performance of Large Language Models (LLMs) in Aspect-Based Sentiment Analysis (ABSA)<n>Using a synthetic sports feedback dataset, we evaluate open-weight LLMs' ability to extract aspect-polarity pairs.
  arXiv  Detail & Related papers  (2025-03-26T16:52:40Z)
• Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis with Large Language Models [0.9832963381777073]
  We evaluate large language models (LLMs) under zero-shot conditions to explore their potential to tackle ABSA task.<n>We investigate various prompting strategies, including vanilla zero-shot, chain-of-thought (CoT), self-improvement, self-debate, and self-consistency.<n>Results indicate that while LLMs show promise in handling multilingual ABSA, they generally fall short of fine-tuned, task-specific models.
  arXiv  Detail & Related papers  (2024-12-17T05:48:48Z)
• The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights [108.40766216456413]
  We propose a question alignment framework to bridge the gap between large language models' English and non-English performance. Experiment results show it can boost multilingual performance across diverse reasoning scenarios, model families, and sizes. We analyze representation space, generated response and data scales, and reveal how question translation training strengthens language alignment within LLMs.
  arXiv  Detail & Related papers  (2024-05-02T14:49:50Z)
• Unveiling Linguistic Regions in Large Language Models [49.298360366468934]
  Large Language Models (LLMs) have demonstrated considerable cross-lingual alignment and generalization ability. This paper conducts several investigations on the linguistic competence of LLMs.
  arXiv  Detail & Related papers  (2024-02-22T16:56:13Z)
• BLESS: Benchmarking Large Language Models on Sentence Simplification [55.461555829492866]
  We present BLESS, a performance benchmark of the most recent state-of-the-art large language models (LLMs) on the task of text simplification (TS) We assess a total of 44 models, differing in size, architecture, pre-training methods, and accessibility, on three test sets from different domains (Wikipedia, news, and medical) under a few-shot setting. Our evaluation indicates that the best LLMs, despite not being trained on TS, perform comparably with state-of-the-art TS baselines.
  arXiv  Detail & Related papers  (2023-10-24T12:18:17Z)
• Sentiment Analysis in the Era of Large Language Models: A Reality Check [69.97942065617664]
  This paper investigates the capabilities of large language models (LLMs) in performing various sentiment analysis tasks. We evaluate performance across 13 tasks on 26 datasets and compare the results against small language models (SLMs) trained on domain-specific datasets.
  arXiv  Detail & Related papers  (2023-05-24T10:45:25Z)
• Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models [76.48370548802464]
  This paper focuses on conducting a series of analytical experiments to examine the relations between the multi-head self-attention and the final MRC system performance. We discover that passage-to-question and passage understanding attentions are the most important ones in the question answering process. Through comprehensive visualizations and case studies, we also observe several general findings on the attention maps, which can be helpful to understand how these models solve the questions.
  arXiv  Detail & Related papers  (2021-08-26T04:23:57Z)
• Reducing Confusion in Active Learning for Part-Of-Speech Tagging [100.08742107682264]
  Active learning (AL) uses a data selection algorithm to select useful training samples to minimize annotation cost. We study the problem of selecting instances which maximally reduce the confusion between particular pairs of output tags. Our proposed AL strategy outperforms other AL strategies by a significant margin.
  arXiv  Detail & Related papers  (2020-11-02T06:24:58Z)

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.