paper-with-me

Papers

Dense Passage Retrieval: Is it Retrieving?

2024-02-16 · Benjamin Reichman, Larry Heck

Dense passage retrieval (DPR) is the first step in the retrieval augmented generation (RAG) paradigm for improving the performance of large language models (LLM). DPR fine-tunes pre-trained networks to enhance the alignment of the embeddings between queries and relevant textual data. A deeper understanding of DPR fine-tuning will be required to fundamentally unlock the full potential of this approach. In this work, we explore DPR-trained models mechanistically by using a combination of probing, layer activation analysis, and model editing. Our experiments show that DPR training decentralizes how knowledge is stored in the network, creating multiple access pathways to the same information. We also uncover a limitation in this training style: the internal knowledge of the pre-trained model bounds what the retrieval model can retrieve. These findings suggest a few possible directions for dense retrieval: (1) expose the DPR training process to more knowledge so more can be decentralized, (2) inject facts as decentralized representations, (3) model and incorporate knowledge uncertainty in the retrieval process, and (4) directly map internal model knowledge to a knowledge base.

📄 PDF Abstract BibTeX arXiv:2402.11035

Code (0)

등록된 구현이 없습니다.

Tasks

Model EditingPassage RetrievalRAGRetrievalRetrieval-augmented Generation

Similar Papers 제목 키워드 기반

Phrase Retrieval Learns Passage Retrieval, Too

2021-09-16 · EMNLP 2021 11 · Jinhyuk Lee, Alexander Wettig, Danqi Chen

Dense retrieval methods have shown great promise over sparse retrieval methods in a range of NLP problems. Among them, dense phrase retrieval-the most fine-grained retrieval unit-is appealing because phrases can be direc…

Entity LinkingOpen-Domain Question AnsweringPassage RetrievalQuantization+4

Unsupervised dense retrieval with conterfactual contrastive learning

2024-12-30 · Haitian Chen, Qingyao Ai, Xiao Wang, Yiqun Liu 외

Efficiently retrieving a concise set of candidates from a large document corpus remains a pivotal challenge in Information Retrieval (IR). Neural retrieval models, particularly dense retrieval models built with transform…

Contrastive LearningcounterfactualInformation RetrievalRetrieval+1

Control Token with Dense Passage Retrieval

2024-05-13 · Juhwan Lee, Jisu Kim

This study addresses the hallucination problem in large language models (LLMs). We adopted Retrieval-Augmented Generation(RAG) (Lewis et al., 2020), a technique that involves embedding relevant information in the prompt …

HallucinationPassage RetrievalRAGRetrieval+1

RELIC: Retrieving Evidence for Literary Claims

2022-03-18 · ACL 2022 5 · Katherine Thai, Yapei Chang, Kalpesh Krishna, Mohit Iyyer

Humanities scholars commonly provide evidence for claims that they make about a work of literature (e.g., a novel) in the form of quotations from the work. We collect a large-scale dataset (RELiC) of 78K literary quotati…

Information RetrievalRetrievalSemantic SimilaritySemantic Textual Similarity

W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question Answering

2024-08-15 · Jinming Nian, Zhiyuan Peng, Qifan Wang, Yi Fang

In knowledge-intensive tasks such as open-domain question answering (OpenQA), large language models (LLMs) often struggle to generate factual answers, relying solely on their internal (parametric) knowledge. To address t…

Open-Domain Question AnsweringQuestion AnsweringRAGRetrieval+1