ECR-Chain: Advancing Generative Language Models to Better Emotion-Cause Reasoners through Reasoning Chains (2405.10860v2)
Abstract: Understanding the process of emotion generation is crucial for analyzing the causes behind emotions. Causal Emotion Entailment (CEE), an emotion-understanding task, aims to identify the causal utterances in a conversation that stimulate the emotions expressed in a target utterance. However, current works in CEE mainly focus on modeling semantic and emotional interactions in conversations, neglecting the exploration of the emotion-generation process. This hinders the models from deeply understanding emotions, restricting their ability to produce explainable predictions. In this work, inspired by the emotion generation process of "stimulus-appraisal-emotion" in the cognitive appraisal theory, we introduce a step-by-step reasoning method, Emotion-Cause Reasoning Chain (ECR-Chain), to infer the stimulus from the target emotional expressions in conversations. Specifically, we first introduce the ECR-Chain to ChatGPT via few-shot prompting, which significantly improves its performance on the CEE task. We further propose an automated construction process to utilize ChatGPT in building an ECR-Chain set, which can enhance the reasoning abilities of smaller models through supervised training and assist the Vicuna-7B model in achieving state-of-the-art CEE performance. Moreover, our methods can enable these generative LLMs to effectively perform emotion-cause reasoning in an explainable manner. Our code, data and more details are at https://github.com/hzp3517/ECR-Chain.
- Magda B Arnold. Emotion and personality. vol. i. psychological aspects. 1960.
- Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020.
- Active prompting with chain-of-thought for large language models. arXiv preprint arXiv:2302.12246, 2023.
- Phoebe C Ellsworth. Some implications of cognitive appraisal theories of emotion. 1991.
- Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 154–164, 2019.
- Large language models are reasoning teachers. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki, editors, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14852–14882, Toronto, Canada, July 2023. Association for Computational Linguistics.
- Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes. In Anna Rogers, Jordan Boyd-Graber, and Naoaki Okazaki, editors, Findings of the Association for Computational Linguistics: ACL 2023, pages 8003–8017, Toronto, Canada, July 2023. Association for Computational Linguistics.
- Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685, 2021.
- (comet-) atomic 2020: on symbolic and neural commonsense knowledge graphs. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 6384–6392, 2021.
- 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.
- Neutral utterances are also causes: Enhancing conversational causal emotion entailment with social commonsense knowledge. In Lud De Raedt, editor, Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pages 4209–4215. International Joint Conferences on Artificial Intelligence Organization, 7 2022. Main Track.
- Explanations from large language models make small reasoners better. arXiv preprint arXiv:2210.06726, 2022.
- On the advance of making language models better reasoners. arXiv preprint arXiv:2206.02336, 2022.
- Dissecting chain-of-thought: Compositionality through in-context filtering and learning. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
- Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692, 2019.
- Dialogueein: emotion interaction network for dialogue affective analysis. In Proceedings of the 29th International Conference on Computational Linguistics, pages 684–693, 2022.
- Dialoguernn: An attentive rnn for emotion detection in conversations. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 6818–6825, 2019.
- Few-shot self-rationalization with natural language prompts. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 410–424, 2022.
- Recognizing emotion cause in conversations. Cognitive Computation, 13:1317–1332, 2021.
- Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023.
- Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations, 2022.
- Large language models are not fair evaluators. arXiv preprint arXiv:2305.17926, 2023.
- Emotion-aware chat machine: Automatic emotional response generation for human-like emotional interaction. In Proceedings of the 28th ACM international conference on information and knowledge management, pages 1401–1410, 2019.
- Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837, 2022.
- Star: Bootstrapping reasoning with reasoning. Advances in Neural Information Processing Systems, 35:15476–15488, 2022.
- Tsam: A two-stream attention model for causal emotion entailment. In Proceedings of the 29th International Conference on Computational Linguistics, pages 6762–6772, 2022.
- Automatic chain of thought prompting in large language models. In The Eleventh International Conference on Learning Representations, 2022.
- Multimodal chain-of-thought reasoning in language models. arXiv preprint arXiv:2302.00923, 2023.
- Knowledge-bridged causal interaction network for causal emotion entailment. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 14020–14028, 2023.
- Is chatgpt equipped with emotional dialogue capabilities? arXiv preprint arXiv:2304.09582, 2023.
- Care: commonsense-aware emotional response generation with latent concepts. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 14577–14585, 2021.
- Zhaopei Huang (3 papers)
- Jinming Zhao (26 papers)
- Qin Jin (94 papers)