paper-with-me

홈 › Papers

A Novel Approach to Eliminating Hallucinations in Large Language Model-Assisted Causal Discovery

2024-11-16 · Grace Sng, YanMing Zhang, Klaus Mueller

The increasing use of large language models (LLMs) in causal discovery as a substitute for human domain experts highlights the need for optimal model selection. This paper presents the first hallucination survey of popular LLMs for causal discovery. We show that hallucinations exist when using LLMs in causal discovery so the choice of LLM is important. We propose using Retrieval Augmented Generation (RAG) to reduce hallucinations when quality data is available. Additionally, we introduce a novel method employing multiple LLMs with an arbiter in a debate to audit edges in causal graphs, achieving a comparable reduction in hallucinations to RAG.

📄 PDF Abstract BibTeX arXiv:2411.12759

Code (0)

등록된 구현이 없습니다.

Tasks

Causal DiscoveryHallucinationLanguage ModelingLanguage ModellingLarge Language ModelModel SelectionRAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
WordPiece 설명 없음
Weight Decay 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Exploring Causal Effect of Social Bias on Faithfulness Hallucinations in Large Language Models

2025-08-11 · Zhenliang Zhang, Junzhe Zhang, Xinyu Hu, HuiXuan Zhang 외 arxiv

Large language models (LLMs) have achieved remarkable success in various tasks, yet they remain vulnerable to faithfulness hallucinations, where the output does not align with the input. In this study, we investigate whe…

Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models

2025-05-26 · Xinmiao Hu, Chun Wang, Ruihe An, ChenYu Shao 외

Multimodal Large Language Models (MLLMs) have demonstrated strong performance in visual understanding tasks, yet they often suffer from object hallucinations--generating descriptions of objects that are inconsistent with…

DisentanglementHallucinationLanguage ModelingLanguage Modelling+1

CausalGuard: A Smart System for Detecting and Preventing False Information in Large Language Models

2025-10-30 · Piyushkumar Patel arxiv

While large language models have transformed how we interact with AI systems, they have a critical weakness: they confidently state false information that sounds entirely plausible. This "hallucination" problem has becom…

Medical Diagnosis

COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs

2025-08-06 · Peizheng Guo, Jingyao Wang, Wenwen Qiang, Jiahuan Zhou 외 arxiv

Despite Multimodal Large Language Models (MLLMs) having shown impressive capabilities, they may suffer from hallucinations. Empirically, we find that MLLMs attend disproportionately to task-irrelevant background regions …

Mitigating Hallucinations in Large Language Models via Causal Reasoning

2025-08-17 · Yuangang Li, Yiqing Shen, Yi Nian, Jiechao Gao 외 arxiv

Large language models (LLMs) exhibit logically inconsistent hallucinations that appear coherent yet violate reasoning principles, with recent research suggesting an inverse relationship between causal reasoning capabilit…