Related papers: Learning To Retrieve: How to Train a Dense Retriev…

Pre-trained deep language models~(LM) have advanced the state-of-the-art of text retrieval. Rerankers fine-tuned from deep LM estimates candidate relevance based on rich contextualized matching signals. Meanwhile, deep LMs can also be…

Large Language Models (LLMs) have shown strong capabilities in document re-ranking, a key component in modern Information Retrieval (IR) systems. However, existing LLM-based approaches face notable limitations, including ranking…

This paper summarizes our work on the first track of the ninth Dialog System Technology Challenge (DSTC 9), "Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access". The goal of the task is to generate…

Learned sparse and dense representations capture different successful approaches to text retrieval and the fusion of their results has proven to be more effective and robust. Prior work combines dense and sparse retrievers by fusing their…

Retrieval models based on dense representations in semantic space have become an indispensable branch for first-stage retrieval. These retrievers benefit from surging advances in representation learning towards compressive global…

Dense retrievers compress source documents into (possibly lossy) vector representations, yet there is little analysis of what information is lost versus preserved, and how it affects downstream tasks. We conduct the first analysis of the…

Large language models record impressive performance on many natural language processing tasks. However, their knowledge capacity is limited to the pretraining corpus. Retrieval augmentation offers an effective solution by retrieving context…

In this paper we present Large Language Model Assisted Retrieval Model Ranking (LARMOR), an effective unsupervised approach that leverages LLMs for selecting which dense retriever to use on a test corpus (target). Dense retriever selection…

Effective information retrieval requires reasoning over partial evidence and refining strategies as information emerges. Yet current approaches fall short: neural retrievers lack reasoning capabilities, large language models (LLMs) provide…

We present an end-to-end differentiable training method for retrieval-augmented open-domain question answering systems that combine information from multiple retrieved documents when generating answers. We model retrieval decisions as…

Although advancements in deep learning have significantly enhanced the recommendation accuracy of deep recommendation models, these methods still suffer from low recommendation efficiency. Recently proposed tree-based deep recommendation…

Generative retrieval shed light on a new paradigm of document retrieval, aiming to directly generate the identifier of a relevant document for a query. While it takes advantage of bypassing the construction of auxiliary index structures,…

Large Language Models (LLMs) often falter in complex reasoning tasks due to their static, parametric knowledge, leading to hallucinations and poor performance in specialized domains like mathematics. This work explores a fundamental…

We propose Latent Terms, a method revealing that models trained for dense retrieval, whether single- or multi-vector, learn representations that can trivially be decomposed into retrieval-ready sparse features. When trained on frozen…

Dense retrieval (DR) converts queries and documents into dense embeddings and measures the similarity between queries and documents in vector space. One of the challenges in DR is the lack of domain-specific training data. While DR models…

Information retrieval (IR) is essential in search engines and dialogue systems as well as natural language processing tasks such as open-domain question answering. IR serve an important function in the biomedical domain, where content and…

Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. Autoencoder-based language models are appealing in dense retrieval as they train the encoder to output high-quality…

Dialogue systems can benefit from being able to search through a corpus of text to find information relevant to user requests, especially when encountering a request for which no manually curated response is available. The state-of-the-art…

Dense retrieval calls for discriminative embeddings to represent the semantic relationship between query and document. It may benefit from the using of large language models (LLMs), given LLMs' strong capability on semantic understanding.…

Dense retrievers exhibit positional bias, favoring documents whose query-relevant information appears near the beginning and degrading retrieval performance when the information appears later. While prior work on positional bias in dense…