Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework
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_ | 1866910472946581504 |
|---|---|
| author | Sun, Xiaoxi Li, Jinpeng Zhong, Yan Zhao, Dongyan Yan, Rui |
| author_facet | Sun, Xiaoxi Li, Jinpeng Zhong, Yan Zhao, Dongyan Yan, Rui |
| contents | The advent of large language models (LLMs) has facilitated the development of natural language text generation. It also poses unprecedented challenges, with content hallucination emerging as a significant concern. Existing solutions often involve expensive and complex interventions during the training process. Moreover, some approaches emphasize problem disassembly while neglecting the crucial validation process, leading to performance degradation or limited applications. To overcome these limitations, we propose a Markov Chain-based multi-agent debate verification framework to enhance hallucination detection accuracy in concise claims. Our method integrates the fact-checking process, including claim detection, evidence retrieval, and multi-agent verification. In the verification stage, we deploy multiple agents through flexible Markov Chain-based debates to validate individual claims, ensuring meticulous verification outcomes. Experimental results across three generative tasks demonstrate that our approach achieves significant improvements over baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_03075 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework Sun, Xiaoxi Li, Jinpeng Zhong, Yan Zhao, Dongyan Yan, Rui Computation and Language The advent of large language models (LLMs) has facilitated the development of natural language text generation. It also poses unprecedented challenges, with content hallucination emerging as a significant concern. Existing solutions often involve expensive and complex interventions during the training process. Moreover, some approaches emphasize problem disassembly while neglecting the crucial validation process, leading to performance degradation or limited applications. To overcome these limitations, we propose a Markov Chain-based multi-agent debate verification framework to enhance hallucination detection accuracy in concise claims. Our method integrates the fact-checking process, including claim detection, evidence retrieval, and multi-agent verification. In the verification stage, we deploy multiple agents through flexible Markov Chain-based debates to validate individual claims, ensuring meticulous verification outcomes. Experimental results across three generative tasks demonstrate that our approach achieves significant improvements over baselines. |
| title | Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.03075 |