Related papers: Hard Negative Mining for Domain-Specific Retrieval…

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)…

This report investigates enhancing semantic caching effectiveness by employing specialized, fine-tuned embedding models. Semantic caching relies on embedding similarity rather than exact key matching, presenting unique challenges in…

Domain-specific languages that use a lot of specific terminology often fall into the category of low-resource languages. Collecting test datasets in a narrow domain is time-consuming and requires skilled human resources with domain…

Efficient semantic access to industrial product data is a key enabler for factory automation and emerging LLM-based agent workflows, where both human engineers and autonomous agents must identify suitable components from highly structured…

Identifying the scientific source behind a social media claim requires matching short, informal, and often multilingual claims against large collections of scientific publications, where semantically related papers may act as challenging…

Retrieval-Augmented Generation (RAG) encounters efficiency challenges when scaling to massive knowledge bases while preserving contextual relevance. We propose Hash-RAG, a framework that integrates deep hashing techniques with systematic…

Retrieval-Augmented Generation (RAG) systems face significant performance gaps when applied to technical domains requiring precise information extraction from complex documents. Current evaluation methodologies relying on document-level…

We consider the problem of semantic matching in product search: given a customer query, retrieve all semantically related products from a huge catalog of size 100 million, or more. Because of large catalog spaces and real-time latency…

We present a new benchmark for evaluating Deep Search--a realistic and complex form of retrieval-augmented generation (RAG) that requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources. These include documents,…

Large Language Models have undoubtedly revolutionized the Natural Language Processing field, the current trend being to promote one-model-for-all tasks (sentiment analysis, translation, etc.). However, the statistical mechanisms at work in…

Scientific retrieval is essential for advancing scientific knowledge discovery. Within this process, document reranking plays a critical role in refining first-stage retrieval results. However, standard LLM listwise reranking faces…

Accurately identifying adversarial techniques in security texts is critical for effective cyber defense. However, existing methods face a fundamental trade-off: they either rely on generic models with limited domain precision or require…

Retrieval-Augmented Generation (RAG) improves the accuracy and relevance of large language model outputs by incorporating knowledge retrieval. However, implementing RAG in enterprises poses challenges around data security, accuracy,…

Language model fusion helps smart assistants recognize words which are rare in acoustic data but abundant in text-only corpora (typed search logs). However, such corpora have properties that hinder downstream performance, including being…

Despite advances in large language model (LLM)-based natural language interfaces for databases, scaling to enterprise-level data catalogs remains an under-explored challenge. Prior works addressing this challenge rely on domain-specific…

Pre-trained code models have emerged as the state-of-the-art paradigm for code search tasks. The paradigm involves pre-training the model on search-irrelevant tasks such as masked language modeling, followed by the fine-tuning stage, which…

Dense neural text retrieval has achieved promising results on open-domain Question Answering (QA), where latent representations of questions and passages are exploited for maximum inner product search in the retrieval process. However,…

Industrial recommendation systems typically involve a two-stage process: retrieval and ranking, which aims to match users with millions of items. In the retrieval stage, classic embedding-based retrieval (EBR) methods depend on effective…

Dense retrievers have demonstrated significant potential for neural information retrieval; however, they exhibit a lack of robustness to domain shifts, thereby limiting their efficacy in zero-shot settings across diverse domains. A…

Modern enterprises manage vast knowledge distributed across heterogeneous systems such as Jira, Git repositories, Confluence, and wikis. Conventional retrieval methods based on keyword search or static embeddings often fail to answer…