Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMs

• URL: http://arxiv.org/abs/2601.03940v1
• Date: Wed, 07 Jan 2026 13:58:29 GMT
• Title: Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMs
• Authors: Paweł Liskowski, Krzysztof Jankowski,
• Abstract summary: Arctic-ABSA is a collection of powerful models for real-life aspect-based sentiment analysis (ABSA)<n>Our models are tailored to commercial needs, trained on a large corpus of public data alongside carefully generated synthetic data, resulting in a dataset 20 times larger than SemEval14.<n>A single multilingual model maintains 87-91% accuracy across six languages without degrading English performance.
• Score: 1.4732811715354455
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce Arctic-ABSA, a collection of powerful models for real-life aspect-based sentiment analysis (ABSA). Our models are tailored to commercial needs, trained on a large corpus of public data alongside carefully generated synthetic data, resulting in a dataset 20 times larger than SemEval14. We extend typical ABSA models by expanding the number of sentiment classes from the standard three (positive, negative, neutral) to five, adding mixed and unknown classes, while also jointly predicting overall text sentiment and supporting multiple languages. We experiment with reasoning injection by fine-tuning on Chain-of-Thought (CoT) examples and introduce a novel reasoning pretraining technique for encoder-only models that significantly improves downstream fine-tuning and generalization. Our 395M-parameter encoder and 8B-parameter decoder achieve up to 10 percentage points higher accuracy than GPT-4o and Claude 3.5 Sonnet, while setting new state-of-the-art results on the SemEval14 benchmark. A single multilingual model maintains 87-91% accuracy across six languages without degrading English performance. We release ABSA-mix, a large-scale benchmark aggregating 17 public ABSA datasets across 92 domains.

Related papers

• CONE: Embeddings for Complex Numerical Data Preserving Unit and Variable Semantics [1.1087735229999816]
  We propose CONE, a hybrid transformer encoder pre-trained model that encodes numbers, ranges, and gaussians into an embedding vector space preserving distance.<n>We conduct extensive experimental evaluation on large-scale datasets across diverse domains.
  arXiv  Detail & Related papers  (2026-03-05T02:26:36Z)
• GerAV: Towards New Heights in German Authorship Verification using Fine-Tuned LLMs on a New Benchmark [20.533795195003286]
  Authorship verification (AV) is the task of determining whether two texts were written by the same author.<n>GerAV is a comprehensive benchmark for German AV comprising over 600k labeled text pairs.
  arXiv  Detail & Related papers  (2026-01-20T08:08:18Z)
• Multi-Domain ABSA Conversation Dataset Generation via LLMs for Real-World Evaluation and Model Comparison [0.0]
  This paper presents an approach for generating synthetic ABSA data using Large Language Models (LLMs)<n>We detail the generation process aimed at producing data with consistent topic and sentiment distributions across multiple domains using GPT-4o.<n>Our results demonstrate the effectiveness of the synthetic data, revealing distinct performance trade-offs among the models.
  arXiv  Detail & Related papers  (2025-05-30T15:24:17Z)
• Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning [77.120955854093]
  We show that data diversity can be a strong predictor of generalization in language models.<n>We introduce G-Vendi, a metric that quantifies diversity via the entropy of model-induced gradients.<n>We present Prismatic Synthesis, a framework for generating diverse synthetic data.
  arXiv  Detail & Related papers  (2025-05-26T16:05:10Z)
• S*: Test Time Scaling for Code Generation [55.11863577956177]
  We propose S*, the first hybrid test-time scaling framework for code generation.<n>S* substantially improves the coverage and selection accuracy of generated code.
  arXiv  Detail & Related papers  (2025-02-20T09:18:53Z)
• Iterative Data Generation with Large Language Models for Aspect-based Sentiment Analysis [39.57537769578304]
  We propose a systematic Iterative Data Generation framework, namely IDG, to boost the performance of ABSA. The core of IDG is to make full use of the powerful abilities (i.e., instruction-following, in-context learning and self-reflection) of LLMs to iteratively generate more fluent and diverse pseudo-label data. IDG brings consistent and significant performance gains among five baseline ABSA models.
  arXiv  Detail & Related papers  (2024-06-29T07:00:37Z)
• Advancing LLM Reasoning Generalists with Preference Trees [119.57169648859707]
  We introduce Eurus, a suite of large language models (LLMs) optimized for reasoning. Eurus models achieve state-of-the-art results among open-source models on a diverse set of benchmarks.
  arXiv  Detail & Related papers  (2024-04-02T16:25:30Z)
• ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot Filler [1.9015367254988451]
  This study evaluates instruction-tuned models (Instruct-LLMs) on popular benchmark datasets for intent classification (IC) and slot filling (SF) We introduce ILLUMINER, an approach framing IC and SF as language generation tasks for Instruct-LLMs, with a more efficient SF-prompting method compared to prior work. A comprehensive comparison with multiple baselines shows that our approach, using the FLAN-T5 11B model, outperforms the state-of-the-art joint IC+SF method and in-context learning with GPT3.5 (175B).
  arXiv  Detail & Related papers  (2024-03-26T09:41:21Z)
• CodingTeachLLM: Empowering LLM's Coding Ability via AST Prior Knowledge [0.0]
  We introduce CodingTeachLLM, a large language model (LLM) designed for coding teaching.<n>Our model realizes the structural disassembly and incremental guided output of educational knowledge.<n>Our model also achieves state-of-the-art in code abilities compared to open-source models.
  arXiv  Detail & Related papers  (2024-03-13T05:38:39Z)
• Large language models for aspect-based sentiment analysis [0.0]
  We assess the performance of GPT-4 and GPT-3.5 in zero shot, few shot and fine-tuned settings. Fine-tuned GPT-3.5 achieves a state-of-the-art F1 score of 83.8 on the joint aspect term extraction and polarity classification task.
  arXiv  Detail & Related papers  (2023-10-27T10:03:21Z)
• Text Classification via Large Language Models [63.1874290788797]
  We introduce Clue And Reasoning Prompting (CARP) to address complex linguistic phenomena involved in text classification. Remarkably, CARP yields new SOTA performances on 4 out of 5 widely-used text-classification benchmarks. More importantly, we find that CARP delivers impressive abilities on low-resource and domain-adaptation setups.
  arXiv  Detail & Related papers  (2023-05-15T06:24:45Z)
• Holistic Evaluation of Language Models [183.94891340168175]
  Language models (LMs) are becoming the foundation for almost all major language technologies, but their capabilities, limitations, and risks are not well understood. We present Holistic Evaluation of Language Models (HELM) to improve the transparency of language models.
  arXiv  Detail & Related papers  (2022-11-16T18:51:34Z)
• Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations [58.442103936918805]
  We show that Attention Mask Consistency produces superior visual grounding results than previous methods. AMC is effective, easy to implement, and is general as it can be adopted by any vision-language model.
  arXiv  Detail & Related papers  (2022-06-30T17:55:12Z)

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.