MALTO at SemEval-2024 Task 6: Leveraging Synthetic Data for LLM Hallucination Detection
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_ | 1866912771510108160 |
|---|---|
| author | Borra, Federico Savelli, Claudio Rosso, Giacomo Koudounas, Alkis Giobergia, Flavio |
| author_facet | Borra, Federico Savelli, Claudio Rosso, Giacomo Koudounas, Alkis Giobergia, Flavio |
| contents | In Natural Language Generation (NLG), contemporary Large Language Models (LLMs) face several challenges, such as generating fluent yet inaccurate outputs and reliance on fluency-centric metrics. This often leads to neural networks exhibiting "hallucinations". The SHROOM challenge focuses on automatically identifying these hallucinations in the generated text. To tackle these issues, we introduce two key components, a data augmentation pipeline incorporating LLM-assisted pseudo-labelling and sentence rephrasing, and a voting ensemble from three models pre-trained on Natural Language Inference (NLI) tasks and fine-tuned on diverse datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_00964 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MALTO at SemEval-2024 Task 6: Leveraging Synthetic Data for LLM Hallucination Detection Borra, Federico Savelli, Claudio Rosso, Giacomo Koudounas, Alkis Giobergia, Flavio Computation and Language Machine Learning In Natural Language Generation (NLG), contemporary Large Language Models (LLMs) face several challenges, such as generating fluent yet inaccurate outputs and reliance on fluency-centric metrics. This often leads to neural networks exhibiting "hallucinations". The SHROOM challenge focuses on automatically identifying these hallucinations in the generated text. To tackle these issues, we introduce two key components, a data augmentation pipeline incorporating LLM-assisted pseudo-labelling and sentence rephrasing, and a voting ensemble from three models pre-trained on Natural Language Inference (NLI) tasks and fine-tuned on diverse datasets. |
| title | MALTO at SemEval-2024 Task 6: Leveraging Synthetic Data for LLM Hallucination Detection |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2403.00964 |