LLM-based Discriminative Reasoning for Knowledge Graph Question Answering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915184675651584 |
|---|---|
| author | Xu, Mufan Chen, Kehai Bai, Xuefeng Yang, Muyun Zhao, Tiejun Zhang, Min |
| author_facet | Xu, Mufan Chen, Kehai Bai, Xuefeng Yang, Muyun Zhao, Tiejun Zhang, Min |
| contents | Large language models (LLMs) based on generative pre-trained Transformer have achieved remarkable performance on knowledge graph question-answering (KGQA) tasks. However, LLMs often produce ungrounded subgraph planning or reasoning results in KGQA due to the hallucinatory behavior brought by the generative paradigm. To tackle this issue, we propose READS to reformulate the KGQA process into discriminative subtasks, which simplifies the search space for each subtasks. Based on the subtasks, we design a new corresponding discriminative inference strategy to conduct the reasoning for KGQA, thereby alleviating hallucination and ungrounded reasoning issues in LLMs. Experimental results show that the proposed approach outperforms multiple strong comparison methods, along with achieving state-of-the-art performance on widely used benchmarks WebQSP and CWQ. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_12643 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLM-based Discriminative Reasoning for Knowledge Graph Question Answering Xu, Mufan Chen, Kehai Bai, Xuefeng Yang, Muyun Zhao, Tiejun Zhang, Min Computation and Language Large language models (LLMs) based on generative pre-trained Transformer have achieved remarkable performance on knowledge graph question-answering (KGQA) tasks. However, LLMs often produce ungrounded subgraph planning or reasoning results in KGQA due to the hallucinatory behavior brought by the generative paradigm. To tackle this issue, we propose READS to reformulate the KGQA process into discriminative subtasks, which simplifies the search space for each subtasks. Based on the subtasks, we design a new corresponding discriminative inference strategy to conduct the reasoning for KGQA, thereby alleviating hallucination and ungrounded reasoning issues in LLMs. Experimental results show that the proposed approach outperforms multiple strong comparison methods, along with achieving state-of-the-art performance on widely used benchmarks WebQSP and CWQ. |
| title | LLM-based Discriminative Reasoning for Knowledge Graph Question Answering |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2412.12643 |