Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
38 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thought (2401.06836v3)

Published 12 Jan 2024 in cs.CL and cs.AI

Abstract: 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.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. Exploring sequence-to-sequence learning in aspect term extraction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3538–3547, 2019.
  2. Conditional augmentation for aspect term extraction via masked sequence-to-sequence generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7056–7066, 2020.
  3. Emocaps: Emotion capsule based model for conversational emotion recognition. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1610–1618, 2022.
  4. Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation. In EMNLP-IJCNLP 2019-2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference, 2020.
  5. Databases, features and classifiers for speech emotion recognition: a review. International Journal of Speech Technology, 21:93–120, 2018.
  6. Survey on speech emotion recognition: Features, classification schemes, and databases. Pattern recognition, 44(3):572–587, 2011.
  7. Facial expression recognition. Handbook of face recognition, pages 487–519, 2011.
  8. Facial expression recognition based on local binary patterns: A comprehensive study. Image and vision Computing, 27(6):803–816, 2009.
  9. A wide evaluation of chatgpt on affective computing tasks. arXiv preprint arXiv:2308.13911, 2023.
  10. Dialoguellm: Context and emotion knowledge-tuned llama models for emotion recognition in conversations. arXiv preprint arXiv:2310.11374, 2023.
  11. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023.
  12. Qwen technical report. arXiv preprint arXiv:2309.16609, 2023.
  13. Human-centered neural reasoning for subjective content processing: Hate speech, emotions, and humor. Information Fusion, 94:43–65, 2023.
  14. On the evaluations of chatgpt and emotion-enhanced prompting for mental health analysis. arXiv preprint arXiv:2304.03347, 2023.
  15. Affect-driven dialog generation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3734–3743, 2019.
  16. Automatic dialogue generation with expressed emotions. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 49–54, 2018.
  17. Affect-lm: A neural language model for customizable affective text generation. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 634–642, 2017.
  18. Generating responses with a specific emotion in dialog. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3685–3695, 2019.
  19. Emotional intelligence of large language models. Journal of Pacific Rim Psychology, 17:18344909231213958, 2023.
  20. Character-llm: A trainable agent for role-playing. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13153–13187, 2023.
  21. Rolellm: Benchmarking, eliciting, and enhancing role-playing abilities of large language models. arXiv preprint arXiv:2310.00746, 2023.
  22. Who is chatgpt? benchmarking llms’ psychological portrayal using psychobench. arXiv preprint arXiv:2310.01386, 2023.
  23. Exploring large language models’ cognitive moral development through defining issues test. arXiv preprint arXiv:2309.13356, 2023.
  24. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837, 2022.
  25. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171, 2022.
  26. Daniel Goleman. Emotional intelligence. Bloomsbury Publishing, 2020.
  27. Glm: General language model pretraining with autoregressive blank infilling. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 320–335, 2022.
  28. Iemocap: Interactive emotional dyadic motion capture database. Language resources and evaluation, 42:335–359, 2008.
  29. Helena Chmura Kraemer. Extension of the kappa coefficient. Biometrics, pages 207–216, 1980.
  30. Promptbench: Towards evaluating the robustness of large language models on adversarial prompts. arXiv preprint arXiv:2306.04528, 2023.
  31. A survey on evaluation of large language models. arXiv preprint arXiv:2307.03109, 2023.
  32. End-to-end annotator bias approximation on crowdsourced single-label sentiment analysis. In Proceedings of the 4th International Conference on Natural Language and Speech Processing (ICNLSP 2021), pages 1–10, 2021.
  33. Dailydialog: A manually labelled multi-turn dialogue dataset. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 986–995, 2017.
  34. Towards empathetic open-domain conversation models: A new benchmark and dataset. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 2019.
  35. Towards emotional support dialog systems. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 3469–3483, 2021.
  36. Pens: A dataset and generic framework for personalized news headline generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 82–92, 2021.
  37. Senticap: Generating image descriptions with sentiments. In Proceedings of the AAAI conference on artificial intelligence, volume 30, 2016.
  38. Microsoft coco: Common objects in context. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pages 740–755. Springer, 2014.
  39. Sharegpt4v: Improving large multi-modal models with better captions. arXiv preprint arXiv:2311.12793, 2023.
  40. Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966, 2023.
  41. Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744, 2023.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Zaijing Li (12 papers)
  2. Gongwei Chen (16 papers)
  3. Rui Shao (31 papers)
  4. Dongmei Jiang (31 papers)
  5. Liqiang Nie (191 papers)
  6. Yuquan Xie (11 papers)
Citations (7)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets