mlsanityData to 14 Oct 2026

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

arXiv 2601.03940 ↗First posted 7 Jan 2026cs.CL cs.AIcited by 0

On the map: LLM reasoning → Audio-language model reasoning

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning. Builds on 33 of its 54 references that are in the map. First posted on arXiv 7 Jan 2026.

Builds on

33 of 54 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024RVISA: Reasoning and Verification for Implicit Sentiment Analysis2 Jul

Other references · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2024The Llama 3 Herd of Modelscited by 14,715
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  6. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  7. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  8. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  9. 2024Qwen2.5 Technical Reportcited by 4,942
  10. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  11. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  12. 2017Decoupled Weight Decay Regularizationcited by 1,831
20 more
  1. 2024A Survey on LLM-as-a-Judgecited by 1,423
  2. 2024OpenAI o1 System Cardcited by 1,244
  3. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
  4. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 797
  5. 2024Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inferencecited by 554
  6. 2024From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgecited by 494
  7. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 417
  8. 2023Efficient Guided Generation for Large Language Modelscited by 200
  9. 2023Implicit Chain of Thought Reasoning via Knowledge Distillationcited by 176
  10. 2023Reasoning Implicit Sentiment with Chain-of-Thought Promptingcited by 80
  11. 2024Arctic-Embed 2.0: Multilingual Retrieval Without Compromisecited by 58
  12. 2023MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretrainingcited by 34
  13. 2025EuroBERT: Scaling Multilingual Encoders for European Languagescited by 31
  14. 2023InstructABSA: Instruction Learning for Aspect Based Sentiment Analysiscited by 23
  15. 2023SEntFiN 1.0: Entity-Aware Sentiment Analysis for Financial Newscited by 18
  16. 2023Large language models for aspect-based sentiment analysiscited by 17
  17. 2025NeoBERT: A Next-Generation BERTcited by 16
  18. 2022Boosting Distributed Training Performance of the Unpadded BERT Modelcited by 15
  19. 2021LSA: Modeling Aspect Sentiment Coherency via Local Sentiment Aggregationcited by 8
  20. 2023Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentationscited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training
  2. 2025Multi-Domain ABSA Conversation Dataset Generation via LLMs for Real-World Evaluation and Model Comparison
  3. 2021Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis
  4. 2024DS2-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis
  5. 2025From Annotation to Adaptation: Metrics, Synthetic Data, and Aspect Extraction for Aspect-Based Sentiment Analysis with Large Language Models
  6. 2025Balanced Training Data Augmentation for Aspect-Based Sentiment Analysis
  7. 2024Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis with Large Language Models
  8. 2025AF-MAT: Aspect-aware Flip-and-Fuse xLSTM for Aspect-based Sentiment Analysis