Related papers: Information retrieval for label noise document ran…

Recent research has explored distilling knowledge from large language models (LLMs) to optimize retriever models, especially within the retrieval-augmented generation (RAG) framework. However, most existing training methods rely on…

The LongEval lab focuses on the evaluation of information retrieval systems over time. Two datasets are provided that capture evolving search scenarios with changing documents, queries, and relevance assessments. Systems are assessed from a…

We present a novel model for the problem of ranking a collection of documents according to their semantic similarity to a source (query) document. While the problem of document-to-document similarity ranking has been studied, most modern…

Learning with noisy labels has gained increasing attention because the inevitable imperfect labels in real-world scenarios can substantially hurt the deep model performance. Recent studies tend to regard low-loss samples as clean ones and…

This paper revisits cluster-based retrieval that partitions the inverted index into multiple groups and skips the index partially at cluster and document levels during online inference using a learned sparse representation. It proposes an…

A vital step towards the widespread adoption of neural retrieval models is their resource efficiency throughout the training, indexing and query workflows. The neural IR community made great advancements in training effective dual-encoder…

Large language models (LLMs) can learn vast amounts of knowledge from diverse domains during pre-training. However, long-tail knowledge from specialized domains is often scarce and underrepresented, rarely appearing in the models'…

This paper outlines a conceptual framework for understanding recent developments in information retrieval and natural language processing that attempts to integrate dense and sparse retrieval methods. I propose a representational approach…

Information retrieval systems are crucial for enabling effective access to large document collections. Recent approaches have leveraged Large Language Models (LLMs) to enhance retrieval performance through query augmentation, but often rely…

Retrieval augmented generation (RAG) has been widely adopted to help Large Language Models (LLMs) to process tasks involving long documents. However, existing retrieval models are not designed for long document retrieval and fail to address…

Retrieving documents and prepending them in-context at inference time improves performance of language model (LMs) on a wide range of tasks. However, these documents, often spanning hundreds of words, make inference substantially more…

Deep neural networks have shown impressive performance in supervised learning, enabled by their ability to fit well to the provided training data. However, their performance is largely dependent on the quality of the training data and often…

Document-level Relation Triplet Extraction (DocRTE) is a fundamental task in information systems that aims to simultaneously extract entities with semantic relations from a document. Existing methods heavily rely on a substantial amount of…

Expansion-enhanced sparse lexical representation improves information retrieval (IR) by minimizing vocabulary mismatch problems during lexical matching. In this paper, we explore the potential of jointly learning dense semantic…

Large Language Model (LLM) pre-training exhausts an ever growing compute budget, yet recent research has demonstrated that careful document selection enables comparable model quality with only a fraction of the FLOPs. Inspired by efforts…

Class imbalance and noisy labels are the norm rather than the exception in many large-scale classification datasets. Nevertheless, most works in machine learning typically assume balanced and clean data. There have been some recent attempts…

Face recognition has made remarkable strides, driven by the expanding scale of datasets, advancements in various backbone and discriminative losses. However, face recognition performance is heavily affected by the label noise, especially…

Conducting a systematic review (SR) is comprised of multiple tasks: (i) collect documents (studies) that are likely to be relevant from digital libraries (eg., PubMed), (ii) manually read and label the documents as relevant or irrelevant,…

The evaluation of abstractive summarization models typically uses test data that is identically distributed as training data. In real-world practice, documents to be summarized may contain input noise caused by text extraction artifacts or…

We present a novel deep neural model for text detection in document images. For robust text detection in noisy scanned documents, the advantages of multi-task learning are adopted by adding an auxiliary task of text enhancement. Namely, our…