Hallucination-aware Optimization for Large Language Model-empowered Communications
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910733603700736 |
|---|---|
| author | Liu, Yinqiu Liu, Guangyuan Zhang, Ruichen Niyato, Dusit Xiong, Zehui Kim, Dong In Huang, Kaibin Du, Hongyang |
| author_facet | Liu, Yinqiu Liu, Guangyuan Zhang, Ruichen Niyato, Dusit Xiong, Zehui Kim, Dong In Huang, Kaibin Du, Hongyang |
| contents | Large Language Models (LLMs) have significantly advanced communications fields, such as Telecom Q\&A, mathematical modeling, and coding. However, LLMs encounter an inherent issue known as hallucination, i.e., generating fact-conflicting or irrelevant content. This problem critically undermines the applicability of LLMs in communication systems yet has not been systematically explored. Hence, this paper provides a comprehensive review of LLM applications in communications, with a particular emphasis on hallucination mitigation. Specifically, we analyze hallucination causes and summarize hallucination mitigation strategies from both model- and system-based perspectives. Afterward, we review representative LLM-empowered communication schemes, detailing potential hallucination scenarios and comparing the mitigation strategies they adopted. Finally, we present a case study of a Telecom-oriented LLM that utilizes a novel hybrid approach to enhance the hallucination-aware service experience. On the model side, we publish a Telecom hallucination dataset and apply direct preference optimization to fine-tune LLMs, resulting in a 20.6\% correct rate improvement. Moreover, we construct a mobile-edge mixture-of-experts architecture for optimal LLM expert activation. Our research aims to propel the field of LLM-empowered communications forward by detecting and minimizing hallucination impacts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_06007 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hallucination-aware Optimization for Large Language Model-empowered Communications Liu, Yinqiu Liu, Guangyuan Zhang, Ruichen Niyato, Dusit Xiong, Zehui Kim, Dong In Huang, Kaibin Du, Hongyang Networking and Internet Architecture Large Language Models (LLMs) have significantly advanced communications fields, such as Telecom Q\&A, mathematical modeling, and coding. However, LLMs encounter an inherent issue known as hallucination, i.e., generating fact-conflicting or irrelevant content. This problem critically undermines the applicability of LLMs in communication systems yet has not been systematically explored. Hence, this paper provides a comprehensive review of LLM applications in communications, with a particular emphasis on hallucination mitigation. Specifically, we analyze hallucination causes and summarize hallucination mitigation strategies from both model- and system-based perspectives. Afterward, we review representative LLM-empowered communication schemes, detailing potential hallucination scenarios and comparing the mitigation strategies they adopted. Finally, we present a case study of a Telecom-oriented LLM that utilizes a novel hybrid approach to enhance the hallucination-aware service experience. On the model side, we publish a Telecom hallucination dataset and apply direct preference optimization to fine-tune LLMs, resulting in a 20.6\% correct rate improvement. Moreover, we construct a mobile-edge mixture-of-experts architecture for optimal LLM expert activation. Our research aims to propel the field of LLM-empowered communications forward by detecting and minimizing hallucination impacts. |
| title | Hallucination-aware Optimization for Large Language Model-empowered Communications |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2412.06007 |