相关论文: GASLITEing the Retrieval: Exploring Vulnerabilitie…

Large Language Models (LLMs) have achieved impressive progress in natural language processing, but their limited ability to retain long-term context constrains performance on document-level or multi-turn tasks. Retrieval-Augmented…

This work stems from an observed limitation of text encoders: embeddings may not be able to recognize fine-grained entities or events within encoded semantics, resulting in failed retrieval even in simple cases. To examine such behaviors,…

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm to enhance large language models (LLMs) with external knowledge, reducing hallucinations and compensating for outdated information. However, recent studies have…

Retrieval-augmented generation (RAG) enhances large language model (LLM) reasoning by retrieving external documents, but also opens up new attack surfaces. We study knowledge-base poisoning attacks in RAG, where an attacker injects…

Retrieval-Augmented Generation (RAG) improves the reliability of large language model applications by grounding generation in retrieved evidence, but it also introduces a new attack surface: corpus poisoning. In this setting, an adversary…

Dense retrieval is becoming one of the standard approaches for document and passage ranking. The dual-encoder architecture is widely adopted for scoring question-passage pairs due to its efficiency and high performance. Typically, dense…

Recent advancements in dense retrieval have introduced vision-language model (VLM)-based retrievers, such as DSE and ColPali, which leverage document screenshots embedded as vectors to enable effective search and offer a simplified pipeline…

Retrieval-augmented generation (RAG) systems can effectively mitigate the hallucination problem of large language models (LLMs),but they also possess inherent vulnerabilities. Identifying these weaknesses before the large-scale real-world…

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 transformers and pretrained…

Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversarially…

Generative Retrieval (GR), autoregressively decoding relevant document identifiers given a query, has been shown to perform well under the setting of small-scale corpora. By memorizing the document corpus with model parameters, GR…

Explaining why dense retrievers assign high relevance scores remains challenging because retrieval decisions are made through opaque high-dimensional embeddings. Existing explanations often focus on surface signals, such as lexical matches,…

Large Language Models (LLMs) are constrained by outdated information and a tendency to generate incorrect data, commonly referred to as "hallucinations." Retrieval-Augmented Generation (RAG) addresses these limitations by combining the…

Search engines are vulnerable to attacks against indexing and searching via text encoding manipulation. By imperceptibly perturbing text using uncommon encoded representations, adversaries can control results across search engines for…

Dense embedding models have become critical for modern information retrieval, particularly in RAG pipelines, but their performance often degrades when applied to specialized corpora outside their pre-training distribution. To address thi we…

Retrieval Augmented Generation (RAG) frameworks improve the accuracy of large language models (LLMs) by integrating external knowledge from retrieved documents, thereby overcoming the limitations of models' static intrinsic knowledge.…

Decoder-only large language models (LLMs) are increasingly replacing BERT-style architectures as the backbone for dense retrieval, achieving substantial performance gains and broad adoption. However, the robustness of these LLM-based…

Generative retrieval represents a novel approach to information retrieval. It uses an encoder-decoder architecture to directly produce relevant document identifiers (docids) for queries. While this method offers benefits, current approaches…

Recent advances in dense retrieval techniques have offered the promise of being able not just to re-rank documents using contextualised language models such as BERT, but also to use such models to identify documents from the collection in…

Generative retrieval models encode pointers to information in a corpus as an index within the model's parameters. These models serve as part of a larger pipeline, where retrieved information conditions generation for knowledge-intensive NLP…