paper-with-me

Papers

Deep Learning Based Dense Retrieval: A Comparative Study

2024-10-27 · Ming Zhong, Zhizhi Wu, Nanako Honda

Dense retrievers have achieved state-of-the-art performance in various information retrieval tasks, but their robustness against tokenizer poisoning remains underexplored. In this work, we assess the vulnerability of dense retrieval systems to poisoned tokenizers by evaluating models such as BERT, Dense Passage Retrieval (DPR), Contriever, SimCSE, and ANCE. We find that supervised models like BERT and DPR experience significant performance degradation when tokenizers are compromised, while unsupervised models like ANCE show greater resilience. Our experiments reveal that even small perturbations can severely impact retrieval accuracy, highlighting the need for robust defenses in critical applications.

📄 PDF Abstract BibTeX arXiv:2410.20315

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningInformation RetrievalPassage RetrievalRetrieval

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 &…
Adam 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
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…
SimCSE SimCSE is a contrastive learning framework for generating sentence embeddings. It utilizes an unsupervised approach, which takes an input sentence and predicts itself in…
Weight Decay 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Scaling Sparse and Dense Retrieval in Decoder-Only LLMs

2025-02-21 · Hansi Zeng, Julian Killingback, Hamed Zamani

Scaling large language models (LLMs) has shown great potential for improving retrieval model performance; however, previous studies have mainly focused on dense retrieval trained with contrastive loss (CL), neglecting th…

DecoderKnowledge DistillationRetrieval

On Single and Multiple Representations in Dense Passage Retrieval

2021-08-13 · Craig Macdonald, Nicola Tonellotto, Iadh Ounis

The advent of contextualised language models has brought gains in search effectiveness, not just when applied for re-ranking the output of classical weighting models such as BM25, but also when used directly for passage …

Passage RetrievalRe-RankingRetrieval

LexBoost: Improving Lexical Document Retrieval with Nearest Neighbors

2024-08-25 · Hrishikesh Kulkarni, Nazli Goharian, Ophir Frieder, Sean MacAvaney

Sparse retrieval methods like BM25 are based on lexical overlap, focusing on the surface form of the terms that appear in the query and the document. The use of inverted indices in these methods leads to high retrieval e…

Re-RankingRetrieval

A Comparative Study of Specialized LLMs as Dense Retrievers

2025-07-05 · Hengran Zhang, Keping Bi, Jiafeng Guo arxiv

While large language models (LLMs) are increasingly deployed as dense retrievers, the impact of their domain-specific specialization on retrieval effectiveness remains underexplored. This investigation systematically exa…

Mathematical ReasoningText Retrieval

Do You Remember? Dense Video Captioning with Cross-Modal Memory Retrieval

2024-04-11 · CVPR 2024 1 · Minkuk Kim, Hyeon Bae Kim, Jinyoung Moon, Jinwoo Choi 외

There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video. Several studies introduce methods by designing dense vid…

DecoderDense Video CaptioningRetrievalText Matching+1