CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914091347476480 |
|---|---|
| author | Shim, Jung-Woo Ju, Yeong-Joon Park, Ji-Hoon Lee, Seong-Whan |
| author_facet | Shim, Jung-Woo Ju, Yeong-Joon Park, Ji-Hoon Lee, Seong-Whan |
| contents | Recent advancements in large language models (LLMs) highlight their fluency in generating responses to diverse prompts. However, these models sometimes generate plausible yet incorrect ``hallucinated" facts, undermining trust. A frequent but often overlooked cause of such errors is the use of poorly structured or vague prompts by users, leading LLMs to base responses on assumed rather than actual intentions. To mitigate hallucinations induced by these ill-formed prompts, we introduce Curative Prompt Refinement (CPR), a plug-and-play framework for curative prompt refinement that 1) cleans ill-formed prompts, and 2) generates additional informative task descriptions to align the intention of the user and the prompt using a fine-tuned small language model. When applied to language models, we discover that CPR significantly increases the quality of generation while also mitigating hallucination. Empirical studies show that prompts with CPR applied achieves over a 90\% win rate over the original prompts without any external knowledge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12029 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement Shim, Jung-Woo Ju, Yeong-Joon Park, Ji-Hoon Lee, Seong-Whan Computation and Language Artificial Intelligence Machine Learning Recent advancements in large language models (LLMs) highlight their fluency in generating responses to diverse prompts. However, these models sometimes generate plausible yet incorrect ``hallucinated" facts, undermining trust. A frequent but often overlooked cause of such errors is the use of poorly structured or vague prompts by users, leading LLMs to base responses on assumed rather than actual intentions. To mitigate hallucinations induced by these ill-formed prompts, we introduce Curative Prompt Refinement (CPR), a plug-and-play framework for curative prompt refinement that 1) cleans ill-formed prompts, and 2) generates additional informative task descriptions to align the intention of the user and the prompt using a fine-tuned small language model. When applied to language models, we discover that CPR significantly increases the quality of generation while also mitigating hallucination. Empirical studies show that prompts with CPR applied achieves over a 90\% win rate over the original prompts without any external knowledge. |
| title | CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2510.12029 |