Related papers: Improving Document Retrieval Coherence for Semanti…

Recent research demonstrates the effectiveness of using fine-tuned language models~(LM) for dense retrieval. However, dense retrievers are hard to train, typically requiring heavily engineered fine-tuning pipelines to realize their full…

Deploying dense retrieval models efficiently is becoming increasingly important across various industries. This is especially true for enterprise search services, where customizing search engines to meet the time demands of different…

Many discriminative natural language understanding (NLU) tasks have large label spaces. Learning such a process of large-space decision making is particularly challenging due to the lack of training instances per label and the difficulty of…

Recent advances in AI have catalyzed the adoption of intelligent educational tools, yet many semantic retrieval systems remain ill-suited to the unique linguistic and structural characteristics of academic content. This study presents two…

Knowledge-intensive tasks, particularly open-domain question answering (ODQA), document reranking, and retrieval-augmented language modeling, require a balance between retrieval accuracy and generative flexibility. Traditional retrieval…

Sponsored search is a key revenue source for search engines, where advertisers bid on keywords to target users or search queries of interest. However, finding relevant keywords for a given query is challenging due to the large and dynamic…

Information retrieval (IR) for precision medicine (PM) often involves looking for multiple pieces of evidence that characterize a patient case. This typically includes at least the name of a condition and a genetic variation that applies to…

Various techniques have been developed in recent years to improve dense retrieval (DR), such as unsupervised contrastive learning and pseudo-query generation. Existing DRs, however, often suffer from effectiveness tradeoffs between…

Document retrieval is one of the most challenging tasks in Information Retrieval. It requires handling longer contexts, often resulting in higher query latency and increased computational overhead. Recently, Learned Sparse Retrieval (LSR)…

Deep neural networks have achieved significant improvements in information retrieval (IR). However, most existing models are computational costly and can not efficiently scale to long documents. This paper proposes a novel End-to-End neural…

Speculative decoding (SD) accelerates Large Language Model (LLM) generation by using an efficient draft model to propose the next few tokens, which are verified by the LLM in a single forward call, reducing latency while preserving its…

Temporal awareness is crucial in many information retrieval tasks, particularly in scenarios where the relevance of documents depends on their alignment with the query's temporal context. Traditional approaches such as BM25 and Dense…

In open-domain question answering, dense passage retrieval has become a new paradigm to retrieve relevant passages for finding answers. Typically, the dual-encoder architecture is adopted to learn dense representations of questions and…

Long Document retrieval (DR) has always been a tremendous challenge for reading comprehension and information retrieval. The pre-training model has achieved good results in the retrieval stage and Ranking for long documents in recent years.…

DNN-based cross-modal retrieval has become a research hotspot, by which users can search results across various modalities like image and text. However, existing methods mainly focus on the pairwise correlation and reconstruction error of…

Exploiting information induced from (query-specific) clustering of top-retrieved documents has long been proposed as a means for improving precision at the very top ranks of the returned results. We present a novel language model approach…

Scaling up neural models has yielded significant advancements in a wide array of tasks, particularly in language generation. Previous studies have found that the performance of neural models frequently adheres to predictable scaling laws,…

In modern e-commerce search systems, dense retrieval has become an indispensable component. By computing similarities between query and item (product) embeddings, it efficiently selects candidate products from large-scale repositories. With…

Zero-shot dense retrieval is a challenging setting where a document corpus is provided without relevant queries, necessitating a reliance on pretrained dense retrievers (DRs). However, since these DRs are not trained on the target corpus,…

Neural Encoders are frequently used in the NLP domain to perform dense retrieval tasks, for instance, to generate the candidate documents for a given query in question-answering tasks. However, sparse annotation and label noise in the…