Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.17174 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916659971751936 |
|---|---|
| author | Wang, Kangsheng Zhang, Xiao Lyu, Juntao Hu, Tianyu Ma, Huimin |
| author_facet | Wang, Kangsheng Zhang, Xiao Lyu, Juntao Hu, Tianyu Ma, Huimin |
| contents | Chain-based reasoning methods like chain of thought (CoT) play a rising role in solving reasoning tasks for large language models (LLMs). However, the causal hallucinations between a step of reasoning and corresponding state transitions are becoming a significant obstacle to advancing LLMs' reasoning capabilities, especially in long-range reasoning tasks. This paper proposes a non-chain-based reasoning framework for simultaneous consideration of causal significance and consistency, i.e., the Causal Significance and Consistency Enhancer (CSCE). We customize LLM's loss function utilizing treatment effect assessments to enhance its reasoning ability from two aspects: causal significance and consistency. This ensures that the model captures essential causal relationships and maintains robust and consistent performance across various scenarios. Additionally, we transform the reasoning process from the cascading multiple one-step reasoning commonly used in Chain-Based methods, like CoT, to a causal-enhanced method that outputs the entire reasoning process in one go, further improving the model's reasoning efficiency. Extensive experiments show that our method improves both the reasoning success rate and speed. These improvements further demonstrate that non-chain-based methods can also aid LLMs in completing reasoning tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17174 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CSCE: Boosting LLM Reasoning by Simultaneous Enhancing of Causal Significance and Consistency Wang, Kangsheng Zhang, Xiao Lyu, Juntao Hu, Tianyu Ma, Huimin Computation and Language Artificial Intelligence Chain-based reasoning methods like chain of thought (CoT) play a rising role in solving reasoning tasks for large language models (LLMs). However, the causal hallucinations between a step of reasoning and corresponding state transitions are becoming a significant obstacle to advancing LLMs' reasoning capabilities, especially in long-range reasoning tasks. This paper proposes a non-chain-based reasoning framework for simultaneous consideration of causal significance and consistency, i.e., the Causal Significance and Consistency Enhancer (CSCE). We customize LLM's loss function utilizing treatment effect assessments to enhance its reasoning ability from two aspects: causal significance and consistency. This ensures that the model captures essential causal relationships and maintains robust and consistent performance across various scenarios. Additionally, we transform the reasoning process from the cascading multiple one-step reasoning commonly used in Chain-Based methods, like CoT, to a causal-enhanced method that outputs the entire reasoning process in one go, further improving the model's reasoning efficiency. Extensive experiments show that our method improves both the reasoning success rate and speed. These improvements further demonstrate that non-chain-based methods can also aid LLMs in completing reasoning tasks. |
| title | CSCE: Boosting LLM Reasoning by Simultaneous Enhancing of Causal Significance and Consistency |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2409.17174 |