Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910472676048896 |
|---|---|
| author | Hua, Wenyue Zhu, Kaijie Li, Lingyao Fan, Lizhou Lin, Shuhang Jin, Mingyu Xue, Haochen Li, Zelong Wang, JinDong Zhang, Yongfeng |
| author_facet | Hua, Wenyue Zhu, Kaijie Li, Lingyao Fan, Lizhou Lin, Shuhang Jin, Mingyu Xue, Haochen Li, Zelong Wang, JinDong Zhang, Yongfeng |
| contents | This study intends to systematically disentangle pure logic reasoning and text understanding by investigating the contrast across abstract and contextualized logical problems from a comprehensive set of domains. We explore whether LLMs demonstrate genuine reasoning capabilities across various domains when the underlying logical structure remains constant. We focus on two main questions (1) Can abstract logical problems alone accurately benchmark an LLM's reasoning ability in real-world scenarios, disentangled from contextual support in practical settings? (2) Does fine-tuning LLMs on abstract logic problem generalize to contextualized logic problems and vice versa? To investigate these questions, we focus on standard propositional logic, specifically propositional deductive and abductive logic reasoning. In particular, we construct instantiated datasets for deductive and abductive reasoning with 4 levels of difficulty, encompassing 12 distinct categories or domains based on the categorization of Wikipedia. Our experiments aim to provide insights into disentangling context in logical reasoning and the true reasoning capabilities of LLMs and their generalization potential. The code and dataset are available at: https://github.com/agiresearch/ContextHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_02787 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities Hua, Wenyue Zhu, Kaijie Li, Lingyao Fan, Lizhou Lin, Shuhang Jin, Mingyu Xue, Haochen Li, Zelong Wang, JinDong Zhang, Yongfeng Computation and Language Artificial Intelligence Machine Learning This study intends to systematically disentangle pure logic reasoning and text understanding by investigating the contrast across abstract and contextualized logical problems from a comprehensive set of domains. We explore whether LLMs demonstrate genuine reasoning capabilities across various domains when the underlying logical structure remains constant. We focus on two main questions (1) Can abstract logical problems alone accurately benchmark an LLM's reasoning ability in real-world scenarios, disentangled from contextual support in practical settings? (2) Does fine-tuning LLMs on abstract logic problem generalize to contextualized logic problems and vice versa? To investigate these questions, we focus on standard propositional logic, specifically propositional deductive and abductive logic reasoning. In particular, we construct instantiated datasets for deductive and abductive reasoning with 4 levels of difficulty, encompassing 12 distinct categories or domains based on the categorization of Wikipedia. Our experiments aim to provide insights into disentangling context in logical reasoning and the true reasoning capabilities of LLMs and their generalization potential. The code and dataset are available at: https://github.com/agiresearch/ContextHub. |
| title | Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2406.02787 |