mlsanityData to 7 Oct 2026

Reasoning Implicit Sentiment with Chain-of-Thought Prompting

arXiv 2305.11255 ↗First posted 18 May 2023cs.CLcited by 79

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

While sentiment analysis systems try to determine the sentiment polarities of given targets based on the key opinion expressions in input texts, in implicit sentiment analysis (ISA) the opinion cues come in an implicit and obscure manner. Thus detecting implicit sentiment requires the common-sense and multi-hop reasoning ability to infer the latent intent of opinion. Inspired by the recent chain-of-thought (CoT) idea, in this work we introduce a Three-hop Reasoning (THOR) CoT framework to mimic the human-like reasoning process for ISA. We design a three-step prompting principle for THOR to step-by-step induce the implicit aspect, opinion, and finally the sentiment polarity. Our THOR+Flan-T5 (11B) pushes the state-of-the-art (SoTA) by over 6% F1 on supervised setup. More strikingly, THOR+GPT3 (175B) boosts the SoTA by over 50% F1 on zero-shot setting. Our code is open at https://github.com/scofield7419/THOR-ISA.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 27 of its 42 references that are in the map. First posted on arXiv 18 May 2023.

Builds on

27 of 42 references.

Closest ancestors · 5

Same direction, newest first

  1. 2022Automatic Chain of Thought Prompting in Large Language Models7 Oct
  2. 2022Complexity-Based Prompting for Multi-Step Reasoning3 Oct
  3. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Models21 May
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2021Generated Knowledge Prompting for Commonsense Reasoningcited by 213
  6. 2019Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysiscited by 123
  7. 2020Relational Graph Attention Network for Aspect-based Sentiment Analysiscited by 104
  8. 2021Aspect Sentiment Quad Prediction as Paraphrase Generationcited by 99
  9. 2020Position-Aware Tagging for Aspect Sentiment Triplet Extractioncited by 90
  10. 2018Aspect Based Sentiment Analysis with Gated Convolutional Networkscited by 65
  11. 2019Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classificationcited by 62
  12. 2018Transformation Networks for Target-Oriented Sentiment Classificationcited by 47
10 more
  1. 2021Prompting Contrastive Explanations for Commonsense Reasoning Taskscited by 45
  2. 2023LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Modelcited by 43
  3. 2021Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Trainingcited by 37
  4. 2021Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extractionwith Rich Syntactic Knowledgecited by 31
  5. 2022DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysiscited by 27
  6. 2021Mastering the Explicit Opinion-role Interaction: Syntax-aided Neural Transition System for Unified Opinion Role Labelingcited by 25
  7. 2020Retrofitting Structure-aware Transformer Language Model for End Taskscited by 24
  8. 2022Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment Analysiscited by 22
  9. 2023On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Trainingcited by 20
  10. 2022Causal Intervention Improves Implicit Sentiment Analysiscited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 14; 2024: 31; 2025: 16; 2026: 18.

79 papers.

Sort:

By area:

  1. 2023Recommender Systems in the Era of Large Language Models (LLMs)cited by 188
  2. 2024Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognitioncited by 151
  3. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  4. 2024Faithful Logical Reasoning via Symbolic Chain-of-Thoughtcited by 99
  5. 2024Designing Heterogeneous LLM Agents for Financial Sentiment Analysiscited by 48
  6. 2024A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Taskscited by 46
  7. 2023Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Modelscited by 37
  8. 2025Benchmarking Reasoning Robustness in Large Language Modelscited by 30
  9. 2024Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspectivecited by 24
  10. 2024RDRec: Rationale Distillation for LLM-based Recommendationcited by 21
  11. 2024Two-stage Generative Question Answering on Temporal Knowledge Graph Using Large Language Modelscited by 18
  12. 2024ToxiCraft: A Novel Framework for Synthetic Generation of Harmful Informationcited by 17
38 more
  1. 2023Prompting and Fine-Tuning Open-Sourced Large Language Models for Stance Classificationcited by 16
  2. 2023Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labelingcited by 15
  3. 2024SportQA: A Benchmark for Sports Understanding in Large Language Modelscited by 15
  4. 2023Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognitioncited by 13
  5. 2024PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysiscited by 13
  6. 2023Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language Modelscited by 11
  7. 2023Sentiment Analysis through LLM Negotiationscited by 11
  8. 2024SemEval-2024 Task 3: Multimodal Emotion Cause Analysis in Conversationscited by 11
  9. 2024Why Misinformation is Created? Detecting them by Integrating Intent Featurescited by 11
  10. 2024Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Informationcited by 10
  11. 2024Which Demographics do LLMs Default to During Annotation?cited by 10
  12. 2024MEMO-Bench: A Multiple Benchmark for Text-to-Image and Multimodal Large Language Models on Human Emotion Analysiscited by 10
  13. 2024Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Modelscited by 9
  14. 2024Deciphering Political Entity Sentiment in News with Large Language Models: Zero-Shot and Few-Shot Strategiescited by 8
  15. 2024RVISA: Reasoning and Verification for Implicit Sentiment Analysiscited by 8
  16. 2026ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thoughtcited by 8
  17. 2023Enhance Multi-domain Sentiment Analysis of Review Texts through Prompting Strategiescited by 7
  18. 2023Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentationscited by 7
  19. 2023Reverse Multi-Choice Dialogue Commonsense Inference with Graph-of-Thoughtcited by 7
  20. 2024EFSA: Towards Event-Level Financial Sentiment Analysiscited by 7
  21. 2024NUS-Emo at SemEval-2024 Task 3: Instruction-Tuning LLM for Multimodal Emotion-Cause Analysis in Conversationscited by 5
  22. 2025Explainable Sentiment Analysis with DeepSeek-R1: Performance, Efficiency, and Few-Shot Learningcited by 5
  23. 2023Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detectioncited by 4
  24. 2024My Words Imply Your Opinion: Reader Agent-based Propagation Enhancement for Personalized Implicit Emotion Analysiscited by 4
  25. 2025Why We Feel: Breaking Boundaries in Emotional Reasoning with Multimodal Large Language Modelscited by 4
  26. 2025Causal Prompting for Implicit Sentiment Analysis with Large Language Modelscited by 4
  27. 2024EDDA: A Encoder-Decoder Data Augmentation Framework for Zero-Shot Stance Detectioncited by 3
  28. 2024Large Language Models in Targeted Sentiment Analysiscited by 3
  29. 2025Towards Multimodal Metaphor Understanding: A Chinese Dataset and Model for Metaphor Mapping Identificationcited by 3
  30. 2025Constraint-Aware Route Recommendation from Natural Language via Hierarchical LLM Agentscited by 3
  31. 2023A Bi-directional Multi-hop Inference Model for Joint Dialog Sentiment Classification and Act Recognitioncited by 2
  32. 2024nicolay-r at SemEval-2024 Task 3: Using Flan-T5 for Reasoning Emotion Cause in Conversations with Chain-of-Thought on Emotion Statescited by 2
  33. 2024Implicit Sentiment Analysis Based on Chain of Thought Promptingcited by 2
  34. 2026Enhancing Self-Correction in Large Language Models through Multi-Perspective Reflectioncited by 2
  35. 2026When to Invoke: Refining LLM Fairness with Toxicity Assessmentcited by 2
  36. 2026Taming Actor-Observer Asymmetry in Agents via Dialectical Alignmentcited by 2
  37. 2023Chain-Of-Thought Prompting Under Streaming Batch: A Case Studycited by 1
  38. 2023DialogRE^C+: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogscited by 1

50 most cited of 79 All 79 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Reassessing the Role of Chain-of-Thought in Sentiment Analysis: Insights and Limitations
  2. 2026Think Wider: Mitigating Latent Rank Collapse in Implicit Chain-of-Thought Reasoning
  3. 2024Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought
  4. 2025How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding
  5. 2025SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens
  6. 2026Post-Hoc Reasoning in Chain of Thought: Decoding and Steering Pre-Committed Answers
  7. 2025Enhancing Granular Sentiment Classification with Chain-of-Thought Prompting in Large Language Models
  8. 2025Emotion-o1: Adaptive Long Reasoning for Emotion Understanding in LLMs