paper-with-me

홈 › Papers

Enhancing LLM Factual Accuracy with RAG to Counter Hallucinations: A Case Study on Domain-Specific Queries in Private Knowledge-Bases

2024-03-15 · Jiarui Li, Ye Yuan, Zehua Zhang

We proposed an end-to-end system design towards utilizing Retrieval Augmented Generation (RAG) to improve the factual accuracy of Large Language Models (LLMs) for domain-specific and time-sensitive queries related to private knowledge-bases. Our system integrates RAG pipeline with upstream datasets processing and downstream performance evaluation. Addressing the challenge of LLM hallucinations, we finetune models with a curated dataset which originates from CMU's extensive resources and annotated with the teacher model. Our experiments demonstrate the system's effectiveness in generating more accurate answers to domain-specific and time-sensitive inquiries. The results also revealed the limitations of fine-tuning LLMs with small-scale and skewed datasets. This research highlights the potential of RAG systems in augmenting LLMs with external datasets for improved performance in knowledge-intensive tasks. Our code and models are available on Github.

📄 PDF Abstract BibTeX arXiv:2403.10446

Code (1)

anlp-team/LTI_Neural_Navigator 공식 구현 pytorch

Tasks

RAGRetrievalRetrieval-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
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
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.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
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…

Similar Papers 제목 키워드 기반

Fighting Hallucinations with Counterfactuals: Diffusion-Guided Perturbations for LVLM Hallucination Suppression

2026-03-11 · Hamidreza Dastmalchi, Aijun An, Ali Cheraghian, Hamed Barzamini arxiv

While large vision-language models (LVLMs) achieve strong performance on multimodal tasks, they frequently generate hallucinations -- unfaithful outputs misaligned with the visual input. To address this issue, we introdu…

HalluSegBench: Counterfactual Visual Reasoning for Segmentation Hallucination Evaluation

2025-06-26 · Xinzhuo Li, Adheesh Juvekar, Xingyou Liu, Muntasir Wahed 외

Recent progress in vision-language segmentation has significantly advanced grounded visual understanding. However, these models often exhibit hallucinations by producing segmentation masks for objects not grounded in the…

counterfactualCounterfactual ReasoningHallucinationHallucination Evaluation+4

Counterfactual Probing for Hallucination Detection and Mitigation in Large Language Models

2025-08-03 · Yijun Feng arxiv

Large Language Models have demonstrated remarkable capabilities across diverse tasks, yet they frequently generate hallucinations outputs that are fluent but factually incorrect or unsupported. We propose Counterfactual …

HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data

2023-11-22 · CVPR 2024 1 · Qifan Yu, Juncheng Li, Longhui Wei, Liang Pang 외

Multi-modal Large Language Models (MLLMs) tuned on machine-generated instruction-following data have demonstrated remarkable performance in various multi-modal understanding and generation tasks. However, the hallucinati…

AttributecounterfactualHallucinationHallucination Evaluation+1

Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation

2025-12-30 · Zhe Huang, Hao Wen, Aiming Hao, Bingze Song 외 arxiv

Multimodal Large Language Models (MLLMs) have made remarkable progress in video understanding. However, they suffer from a critical vulnerability: an over-reliance on language priors, which can lead to visual ungrounded …

Video Generation