Mitigating Large Language Model Hallucination with Faithful Finetuning
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_ | 1866909225300525056 |
|---|---|
| author | Hu, Minda He, Bowei Wang, Yufei Li, Liangyou Ma, Chen King, Irwin |
| author_facet | Hu, Minda He, Bowei Wang, Yufei Li, Liangyou Ma, Chen King, Irwin |
| contents | Large language models (LLMs) have demonstrated remarkable performance on various natural language processing tasks. However, they are prone to generating fluent yet untruthful responses, known as "hallucinations". Hallucinations can lead to the spread of misinformation and cause harm in critical applications. Mitigating hallucinations is challenging as they arise from factors such as noisy data, model overconfidence, lack of knowledge, and the generation process itself. Recent efforts have attempted to address this issue through representation editing and decoding algorithms, reducing hallucinations without major structural changes or retraining. However, these approaches either implicitly edit LLMs' behavior in latent space or suppress the tendency to output unfaithful results during decoding instead of explicitly modeling on hallucination. In this work, we introduce Faithful Finetuning (F2), a novel method that explicitly models the process of faithful question answering through carefully designed loss functions during fine-tuning. We conduct extensive experiments on popular datasets and demonstrate that F2 achieves significant improvements over vanilla models and baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_11267 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mitigating Large Language Model Hallucination with Faithful Finetuning Hu, Minda He, Bowei Wang, Yufei Li, Liangyou Ma, Chen King, Irwin Computation and Language Large language models (LLMs) have demonstrated remarkable performance on various natural language processing tasks. However, they are prone to generating fluent yet untruthful responses, known as "hallucinations". Hallucinations can lead to the spread of misinformation and cause harm in critical applications. Mitigating hallucinations is challenging as they arise from factors such as noisy data, model overconfidence, lack of knowledge, and the generation process itself. Recent efforts have attempted to address this issue through representation editing and decoding algorithms, reducing hallucinations without major structural changes or retraining. However, these approaches either implicitly edit LLMs' behavior in latent space or suppress the tendency to output unfaithful results during decoding instead of explicitly modeling on hallucination. In this work, we introduce Faithful Finetuning (F2), a novel method that explicitly models the process of faithful question answering through carefully designed loss functions during fine-tuning. We conduct extensive experiments on popular datasets and demonstrate that F2 achieves significant improvements over vanilla models and baselines. |
| title | Mitigating Large Language Model Hallucination with Faithful Finetuning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.11267 |