mlsanityData to 7 Oct 2026

Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thought

arXiv 2401.06836 ↗First posted 12 Jan 2024cs.CL cs.AIcited by 34

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

Abstract (arXiv)

Large Language Models (LLMs) have shown remarkable performance in various emotion recognition tasks, thereby piquing the research community's curiosity for exploring their potential in emotional intelligence. However, several issues in the field of emotional generation tasks remain unresolved, including human preference alignment and emotional generation assessment. In this paper, we propose the Emotional Chain-of-Thought (ECoT), a plug-and-play prompting method that enhances the performance of LLMs on various emotional generation tasks by aligning with human emotional intelligence guidelines. To assess the reliability of ECoT, we propose an automated model-based evaluation method called Emotional Generation Score (EGS). EGS incorporates Goleman's Emotional Intelligence Theory as a consensus of human experts, providing a new perspective on the evaluation of emotional generation tasks. Extensive experimental results demonstrate the effectiveness of ECoT and EGS. Further, we discuss the promise of LLMs in the field of emotional intelligence and present key insights into the LLMs with the ECoT in emotional generation tasks.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning. Builds on 20 of its 33 references that are in the map. First posted on arXiv 12 Jan 2024.

Builds on

20 of 33 references.

References · 20

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  3. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  4. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  5. 2021GLM: General Language Model Pretraining with Autoregressive Blank Infillingcited by 1,026
  6. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  7. 2023Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspectivecited by 293
  8. 2017Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memorycited by 167
  9. 2022MISC: A MIxed Strategy-Aware Model Integrating COMET for Emotional Support Conversationcited by 84
  10. 2021BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Datacited by 75
  11. 2017Affect-LM: A Neural Language Model for Customizable Affective Text Generationcited by 50
  12. 2019Affect-Driven Dialog Generationcited by 50
8 more
  1. 2015SentiCap: Generating Image Descriptions with Sentimentscited by 48
  2. 2023DialogueLLM: Context and Emotion Knowledge-Tuned Large Language Models for Emotion Recognition in Conversationscited by 29
  3. 2018"Factual" or "Emotional": Stylized Image Captioning with Adaptive Learning and Attentioncited by 26
  4. 2018An Affect-Rich Neural Conversational Model with Biased Attention and Weighted Cross-Entropy Losscited by 21
  5. 2023UniSA: Unified Generative Framework for Sentiment Analysiscited by 17
  6. 2023Large language models for aspect-based sentiment analysiscited by 17
  7. 2023Customising General Large Language Models for Specialised Emotion Recognition Taskscited by 7
  8. 2021End-to-End Annotator Bias Approximation on Crowdsourced Single-Label Sentiment Analysiscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 18; 2026: 6.

34 papers.

Sort:

By area:

  1. 2024Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Taskscited by 83
  2. 2024Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examplescited by 29
  3. 2024Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspectivecited by 24
  4. 2024Evaluating Large Language Models with Psychometricscited by 22
  5. 2025Evaluating Vision-Language Models for Emotion Recognitioncited by 19
  6. 2025HiconAgent: History Context-aware Policy Optimization for GUI Agentscited by 13
  7. 2025Triangulating LLM Progress through Benchmarks, Games, and Cognitive Testscited by 11
  8. 2025Affective Image Editing: Shaping Emotional Factors via Text Descriptionscited by 11
  9. 2024HCQA @ Ego4D EgoSchema Challenge 2024cited by 9
  10. 2025Large Language Models for Subjective Language Understanding: A Surveycited by 9
  11. 2024A Review of Human Emotion Synthesis Based on Generative Technologycited by 7
  12. 2025Towards Deeper Emotional Reflection: Crafting Affective Image Filters with Generative Priorscited by 6
22 more
  1. 2025From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Modelscited by 5
  2. 2024Dynamic Generation of Personalities with Large Language Modelscited by 4
  3. 2025VIBE: Can a VLM Read the Room?cited by 4
  4. 2024EmPO: Emotion Grounding for Empathetic Response Generation through Preference Optimizationcited by 3
  5. 2025Is Human-Like Text Liked by Humans? Multilingual Human Detection and Preference Against AIcited by 3
  6. 2025EmoFSM: A Finite State Machine for Emotional Support Conversationcited by 3
  7. 2025An evaluation of LLMs for generating movie reviews: GPT-4o, Gemini-2.0 and DeepSeek-V3cited by 2
  8. 2025Evaluating Human-LLM Representation Alignment: A Case Study on Affective Sentence Generation for Augmentative and Alternative Communicationcited by 1
  9. 2025Chain-of-Conceptual-Thought Elicits Daily Conversation in Large Language Modelscited by 1
  10. 2024PALLM: Evaluating and Enhancing PALLiative Care Conversations with Large Language Modelscited by 0
  11. 2024Socio-Emotional Response Generation: A Human Evaluation Protocol for LLM-Based Conversational Systemscited by 0
  12. 2025Plan-and-Refine: Diverse and Comprehensive Retrieval-Augmented Generationcited by 0
  13. 2025EiCAP: Beyond Fluency, Probing and Improving Emotional Intelligence in LLMs via Psychologically Grounded Multi-Turn Dialoguecited by 0
  14. 2025Dual Information Speech Language Models for Emotional Conversationscited by 0
  15. 2025HEART: Emotionally-Driven Test-Time Scaling of Language Modelscited by 0
  16. 2025Analyzing Image Beyond Visual Aspect: Image Emotion Classification via Multiple-Affective Captioningcited by 0
  17. 2026An Ubuntu-Guided Large Language Model Framework for Cognitive Behavioral Mental Health Dialoguecited by 0
  18. 2026PRISMA: Preference-Reinforced Self-Training Approach for Interpretable Emotionally Intelligent Negotiation Dialoguescited by 0
  19. 2026From Descriptive to Prescriptive: Uncover the Social Value Alignment of LLM-based Agentscited by 0
  20. 2026Self-EmoQ: Plutchik-Guided Value-based Planning to Drive Streaming Emotional TTScited by 0
  21. 2026MeetingToM: Evaluating Multimodal LLMs on Theory-of-Mind Reasoning in Multi-Party Meetingscited by 0
  22. 2026ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026From Emotion Classification to Emotional Reasoning: Enhancing Emotional Intelligence in Large Language Models
  2. 2025Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications
  3. 2025LongEmotion: Measuring Emotional Intelligence of Large Language Models in Long-Context Interaction
  4. 2025Large Language Models are Highly Aligned with Human Ratings of Emotional Stimuli
  5. 2026Emotional intelligence in large language models is fragmented across perception, cognition, and interaction
  6. 2025MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models
  7. 2023Why Can Large Language Models Generate Correct Chain-of-Thoughts?
  8. 2024CogBench: a large language model walks into a psychology lab