paper-with-me

홈 › Papers

CPR: Mitigating Large Language Model Hallucinations with Curative Prompt Refinement

2025-10-14 · Jung-Woo Shim, Yeong-Joon Ju, Ji-Hoon Park, Seong-Whan Lee arxiv

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.

📄 PDF Abstract BibTeX arXiv:2510.12029

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Mitigating Prompt-Induced Hallucinations in Large Language Models via Structured Reasoning

2026-01-06 · Jinbo Hao, Kai Yang, Qingzhen Su, Yang Chen 외 arxiv

To address hallucination issues in large language models (LLMs), this paper proposes a method for mitigating prompt-induced hallucinations. Building on a knowledge distillation chain-style model, we introduce a code modu…

Knowledge Distillation

Beyond Fine-Tuning: Effective Strategies for Mitigating Hallucinations in Large Language Models for Data Analytics

2024-10-26 · Mikhail Rumiantsau, Aliaksei Vertsel, Ilya Hrytsuk, Isaiah Ballah

Large Language Models (LLMs) have become increasingly important in natural language processing, enabling advanced data analytics through natural language queries. However, these models often generate "hallucinations"-ina…

Decision MakingNatural Language QueriesStructured Output Generation

Multi-stage Prompt Refinement for Mitigating Hallucinations in Large Language Models

2025-10-14 · Jung-Woo Shim, Yeong-Joon Ju, Ji-Hoon Park, Seong-Whan Lee arxiv

Recent advancements in large language models (LLMs) have shown strong performance in natural language understanding and generation tasks. However, LLMs continue to encounter challenges with hallucinations, where models g…

Natural Language Understanding

Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention

2025-01-01 · CVPR 2025 1 · Wenbin An, Feng Tian, Sicong Leng, Jiahao Nie 외

Despite great success across various multimodal tasks, Large Vision-Language Models (LVLMs) often encounter object hallucinations with generated textual responses being inconsistent with the actual objects in images.…

HallucinationResponse GenerationVisual Grounding

Investigating the Role of Prompting and External Tools in Hallucination Rates of Large Language Models

2024-10-25 · Liam Barkley, Brink van der Merwe

Large Language Models (LLMs) are powerful computational models trained on extensive corpora of human-readable text, enabling them to perform general-purpose language understanding and generation. LLMs have garnered signi…

HallucinationPrompt EngineeringText Generation