ECCoT: A Framework for Enhancing Effective Cognition via Chain of Thought in Large Language Model
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908419437363200 |
|---|---|
| author | Duan, Zhenke Pan, Jiqun Tu, Jiani Wang, Xiaoyi Wang, Yanqing |
| author_facet | Duan, Zhenke Pan, Jiqun Tu, Jiani Wang, Xiaoyi Wang, Yanqing |
| contents | In the era of large-scale artificial intelligence, Large Language Models (LLMs) have made significant strides in natural language processing. However, they often lack transparency and generate unreliable outputs, raising concerns about their interpretability. To address this, the Chain of Thought (CoT) prompting method structures reasoning into step-by-step deductions. Yet, not all reasoning chains are valid, and errors can lead to unreliable conclusions. We propose ECCoT, an End-to-End Cognitive Chain of Thought Validation Framework, to evaluate and refine reasoning chains in LLMs. ECCoT integrates the Markov Random Field-Embedded Topic Model (MRF-ETM) for topic-aware CoT generation and Causal Sentence-BERT (CSBert) for causal reasoning alignment. By filtering ineffective chains using structured ordering statistics, ECCoT improves interpretability, reduces biases, and enhances the trustworthiness of LLM-based decision-making. Key contributions include the introduction of ECCoT, MRF-ETM for topic-driven CoT generation, and CSBert for causal reasoning enhancement. Code is released at: https://github.com/erwinmsmith/ECCoT.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_19599 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ECCoT: A Framework for Enhancing Effective Cognition via Chain of Thought in Large Language Model Duan, Zhenke Pan, Jiqun Tu, Jiani Wang, Xiaoyi Wang, Yanqing Computation and Language Artificial Intelligence In the era of large-scale artificial intelligence, Large Language Models (LLMs) have made significant strides in natural language processing. However, they often lack transparency and generate unreliable outputs, raising concerns about their interpretability. To address this, the Chain of Thought (CoT) prompting method structures reasoning into step-by-step deductions. Yet, not all reasoning chains are valid, and errors can lead to unreliable conclusions. We propose ECCoT, an End-to-End Cognitive Chain of Thought Validation Framework, to evaluate and refine reasoning chains in LLMs. ECCoT integrates the Markov Random Field-Embedded Topic Model (MRF-ETM) for topic-aware CoT generation and Causal Sentence-BERT (CSBert) for causal reasoning alignment. By filtering ineffective chains using structured ordering statistics, ECCoT improves interpretability, reduces biases, and enhances the trustworthiness of LLM-based decision-making. Key contributions include the introduction of ECCoT, MRF-ETM for topic-driven CoT generation, and CSBert for causal reasoning enhancement. Code is released at: https://github.com/erwinmsmith/ECCoT.git. |
| title | ECCoT: A Framework for Enhancing Effective Cognition via Chain of Thought in Large Language Model |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2506.19599 |