Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915800569348096 |
|---|---|
| author | Qin, Yuehan Li, Shawn Nian, Yi Yu, Xinyan Velocity Zhao, Yue Ma, Xuezhe |
| author_facet | Qin, Yuehan Li, Shawn Nian, Yi Yu, Xinyan Velocity Zhao, Yue Ma, Xuezhe |
| contents | Large language models (LLMs) have shown substantial capacity for generating fluent, contextually appropriate responses. However, they can produce hallucinated outputs, especially when a user query includes one or more false premises-claims that contradict established facts. Such premises can mislead LLMs into offering fabricated or misleading details. Existing approaches include pretraining, fine-tuning, and inference-time techniques that often rely on access to logits or address hallucinations after they occur. These methods tend to be computationally expensive, require extensive training data, or lack proactive mechanisms to prevent hallucination before generation, limiting their efficiency in real-time applications. We propose a retrieval-based framework that identifies and addresses false premises before generation. Our method first transforms a user's query into a logical representation, then applies retrieval-augmented generation (RAG) to assess the validity of each premise using factual sources. Finally, we incorporate the verification results into the LLM's prompt to maintain factual consistency in the final output. Experiments show that this approach effectively reduces hallucinations, improves factual accuracy, and does not require access to model logits or large-scale fine-tuning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_06438 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning Qin, Yuehan Li, Shawn Nian, Yi Yu, Xinyan Velocity Zhao, Yue Ma, Xuezhe Computation and Language Artificial Intelligence Large language models (LLMs) have shown substantial capacity for generating fluent, contextually appropriate responses. However, they can produce hallucinated outputs, especially when a user query includes one or more false premises-claims that contradict established facts. Such premises can mislead LLMs into offering fabricated or misleading details. Existing approaches include pretraining, fine-tuning, and inference-time techniques that often rely on access to logits or address hallucinations after they occur. These methods tend to be computationally expensive, require extensive training data, or lack proactive mechanisms to prevent hallucination before generation, limiting their efficiency in real-time applications. We propose a retrieval-based framework that identifies and addresses false premises before generation. Our method first transforms a user's query into a logical representation, then applies retrieval-augmented generation (RAG) to assess the validity of each premise using factual sources. Finally, we incorporate the verification results into the LLM's prompt to maintain factual consistency in the final output. Experiments show that this approach effectively reduces hallucinations, improves factual accuracy, and does not require access to model logits or large-scale fine-tuning. |
| title | Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2504.06438 |