Related papers: Succeeding at Scale: Automated Dataset Constructio…

In enterprise search, building high-quality datasets at scale remains a central challenge due to the difficulty of acquiring labeled data. To resolve this challenge, we propose an efficient approach to fine-tune small language models (SLMs)…

Scalability and accuracy are well recognized challenges in deep extreme multi-label learning where the objective is to train architectures for automatically annotating a data point with the most relevant subset of labels from an extremely…

Dense retrievers have made significant strides in text retrieval and open-domain question answering. However, most of these achievements have relied heavily on extensive human-annotated supervision. In this study, we aim to develop…

Large-scale commercial search systems optimize for relevance to drive successful sessions that help users find what they are looking for. To maximize relevance, we leverage two complementary objectives: behavioral relevance (results users…

With the advent of software-defined networking, network configuration through programmable interfaces becomes practical, leading to various on-demand opportunities for network routing update in multi-tenant datacenters, where tenants have…

Effective document reranking is essential for improving search relevance across diverse applications. While Large Language Models (LLMs) excel at reranking due to their deep semantic understanding and reasoning, their high computational…

Dense retrieval systems increasingly need to handle complex queries. In many realistic settings, users express intent through long instructions or task-specific descriptions, while target documents remain relatively simple and static. This…

Enterprise search systems often struggle to retrieve accurate, domain-specific information due to semantic mismatches and overlapping terminologies. These issues can degrade the performance of downstream applications such as knowledge…

Code search has usually been evaluated as first-stage retrieval, even though production systems rely on broader pipelines with reranking and developer-style queries. Existing benchmarks also suffer from data contamination, label noise, and…

Large Language Models (LLMs) excel at understanding the semantic relationships between queries and documents, even with lengthy and complex long-tail queries. These queries are challenging for feedback-based rankings due to sparse user…

Retrieval-Augmented Generation (RAG) has become ubiquitous when deploying Large Language Models (LLMs), as it can address typical limitations such as generating hallucinated or outdated information. However, when building real-world RAG…

Accurately retrieving relevant bid keywords for user queries is critical in Sponsored Search but remains challenging, particularly for short, ambiguous queries. Existing dense and generative retrieval models often fail to capture nuanced…

Despite considerable progress in neural relevance ranking techniques, search engines still struggle to process complex queries effectively - both in terms of precision and recall. Sparse and dense Pseudo-Relevance Feedback (PRF) approaches…

Business-specific Frequently Asked Questions (FAQ) retrieval in task-oriented dialog systems poses unique challenges vis-\`a-vis community based FAQs. Each FAQ question represents an intent which is usually an umbrella term for many related…

Multi-label text classification (MLC) is a challenging task in settings of large label sets, where label support follows a Zipfian distribution. In this paper, we address this problem through retrieval augmentation, aiming to improve the…

Multi-label classification problems with thousands of classes are hard to solve with in-context learning alone, as language models (LMs) might lack prior knowledge about the precise classes or how to assign them, and it is generally…

In this work we present a systematic empirical study focused on the suitability of the state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks across a number of diverse language pairs. We first treat…

Parameter Efficient Fine-Tuning (PEFT) methods have been extensively utilized in Large Language Models (LLMs) to improve the down-streaming tasks without the cost of fine-tuing the whole LLMs. Recent studies have shown how to effectively…

As user content and queries become increasingly multi-modal, the need for effective multi-modal search systems has grown. Traditional search systems often rely on textual and metadata annotations for indexed images, while multi-modal…

In the context of Extreme Multi-label Text Classification (XMTC), where labels are assigned to text instances from a large label space, the long-tail distribution of labels presents a significant challenge. Labels can be broadly categorized…