paper-with-me

홈 › Papers

Quantifying reliance on external information over parametric knowledge during Retrieval Augmented Generation (RAG) using mechanistic analysis

2024-10-01 · Reshmi Ghosh, Rahul Seetharaman, Hitesh Wadhwa, Somyaa Aggarwal, Samyadeep Basu, Soundararajan Srinivasan, Wenlong Zhao, Shreyas Chaudhari, Ehsan Aghazadeh

Retrieval Augmented Generation (RAG) is a widely used approach for leveraging external context in several natural language applications such as question answering and information retrieval. Yet, the exact nature in which a Language Model (LM) leverages this non-parametric memory or retrieved context isn't clearly understood. This paper mechanistically examines the RAG pipeline to highlight that LMs demonstrate a "shortcut'' effect and have a strong bias towards utilizing the retrieved context to answer questions, while relying minimally on model priors. We propose (a) Causal Mediation Analysis; for proving that parametric memory is minimally utilized when answering a question and (b) Attention Contributions and Knockouts for showing the last token residual stream do not get enriched from the subject token in the question, but gets enriched from tokens of RAG-context. We find this pronounced "shortcut'' behaviour to be true across both LLMs (e.g.,LlaMa) and SLMs (e.g., Phi)

📄 PDF Abstract BibTeX arXiv:2410.00857

Code (0)

등록된 구현이 없습니다.

Tasks

Information RetrievalLanguage ModelingLanguage ModellingQuestion AnsweringRAGRetrievalRetrieval-augmented Generation

Methods 이 논문이 사용한 방법론

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…
WordPiece 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.
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
BERT BERT, or Bidirectional Encoder Representations from Transformers, improves upon standard Transformers by removing the…

Similar Papers 제목 키워드 기반

Evaluating the External and Parametric Knowledge Fusion of Large Language Models

2024-05-29 · Hao Zhang, Yuyang Zhang, Xiaoguang Li, Wenxuan Shi 외

Integrating external knowledge into large language models (LLMs) presents a promising solution to overcome the limitations imposed by their antiquated and static parametric memory. Prior studies, however, have tended to …

Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models

2025-03-20 · Baolong Bi, Shenghua Liu, Yiwei Wang, Yilong Xu 외

Retrieval-Augmented Generation (RAG) mitigates hallucinations in Large Language Models (LLMs) by integrating external knowledge. However, conflicts between parametric knowledge and retrieved context pose challenges, part…

counterfactualRAGRetrieval-augmented Generation

SEReDeEP: Hallucination Detection in Retrieval-Augmented Models via Semantic Entropy and Context-Parameter Fusion

2025-05-12 · Lei Wang

Retrieval-Augmented Generation (RAG) models frequently encounter hallucination phenomena when integrating external information with internal parametric knowledge. Empirical studies demonstrate that the disequilibrium bet…

HallucinationRAGRetrieval-augmented Generation

Quantifying Prior Dominance in RAG Systems

2026-04-29 · Barak Or arxiv

Retrieval-Augmented Generation (RAG) grounds Large Language Models in external knowledge, yet current evaluations rely on discrete heuristics that suffer from ''epistemic blindness'' - failing to distinguish genuine cont…

Information Extraction

Agentic AI Enhances Physician Trust in Clinical Decision Making

2026-06-16 · Zhiling Yan, Zhe Fang, David J King, Ann Pongsakul 외 arxiv

Medical AI has shifted from reasoning to agentic AI, a new paradigm that autonomously invokes external tools during reasoning, rendering intermediate reasoning steps and tool outputs transparent to users. Although proven…

Decision Making