A Logically Consistent Chain-of-Thought Approach for Stance Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918095202811904 |
|---|---|
| author | Zhang, Bowen Ding, Daijun Jing, Liwen Huang, Hu |
| author_facet | Zhang, Bowen Ding, Daijun Jing, Liwen Huang, Hu |
| contents | Zero-shot stance detection (ZSSD) aims to detect stances toward unseen targets. Incorporating background knowledge to enhance transferability between seen and unseen targets constitutes the primary approach of ZSSD. However, these methods often struggle with a knowledge-task disconnect and lack logical consistency in their predictions. To address these issues, we introduce a novel approach named Logically Consistent Chain-of-Thought (LC-CoT) for ZSSD, which improves stance detection by ensuring relevant and logically sound knowledge extraction. LC-CoT employs a three-step process. Initially, it assesses whether supplementary external knowledge is necessary. Subsequently, it uses API calls to retrieve this knowledge, which can be processed by a separate LLM. Finally, a manual exemplar guides the LLM to infer stance categories, using an if-then logical structure to maintain relevance and logical coherence. This structured approach to eliciting background knowledge enhances the model's capability, outperforming traditional supervised methods without relying on labeled data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_16054 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A Logically Consistent Chain-of-Thought Approach for Stance Detection Zhang, Bowen Ding, Daijun Jing, Liwen Huang, Hu Computation and Language Zero-shot stance detection (ZSSD) aims to detect stances toward unseen targets. Incorporating background knowledge to enhance transferability between seen and unseen targets constitutes the primary approach of ZSSD. However, these methods often struggle with a knowledge-task disconnect and lack logical consistency in their predictions. To address these issues, we introduce a novel approach named Logically Consistent Chain-of-Thought (LC-CoT) for ZSSD, which improves stance detection by ensuring relevant and logically sound knowledge extraction. LC-CoT employs a three-step process. Initially, it assesses whether supplementary external knowledge is necessary. Subsequently, it uses API calls to retrieve this knowledge, which can be processed by a separate LLM. Finally, a manual exemplar guides the LLM to infer stance categories, using an if-then logical structure to maintain relevance and logical coherence. This structured approach to eliciting background knowledge enhances the model's capability, outperforming traditional supervised methods without relying on labeled data. |
| title | A Logically Consistent Chain-of-Thought Approach for Stance Detection |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2312.16054 |