Related papers: BiCA: Effective Biomedical Dense Retrieval with Ci…

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…

Ranking consistently emerges as a primary focus in information retrieval research. Retrieval and ranking models serve as the foundation for numerous applications, including web search, open domain QA, enterprise domain QA, and text-based…

Hard negatives play a critical role in training and fine-tuning dense retrieval models, as they are semantically similar to positive documents yet non-relevant, and correctly distinguishing them is essential for improving retrieval…

In dense retrieval, effective training hinges on selecting high quality hard negatives while avoiding false negatives. Recent methods apply heuristics based on positive document scores to identify hard negatives, improving both performance…

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…

Training robust retrieval and reranker models typically relies on large-scale retrieval datasets; for example, the BGE collection contains 1.6 million query-passage pairs sourced from various data sources. However, we find that certain…

Dense Retrieval (DR) models have proven to be effective for Document Retrieval and Information Grounding tasks. Usually, these models are trained and optimized for improving the relevance of top-ranked documents for a given query. Previous…

Neural sentence embedding models for dense retrieval typically rely on binary relevance labels, treating query-document pairs as either relevant or irrelevant. However, real-world relevance often exists on a continuum, and recent advances…

Learning scientific document representations can be substantially improved through contrastive learning objectives, where the challenge lies in creating positive and negative training samples that encode the desired similarity semantics.…

Ranking has always been one of the top concerns in information retrieval research. For decades, lexical matching signal has dominated the ad-hoc retrieval process, but it also has inherent defects, such as the vocabulary mismatch problem.…

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…

Dense retrieval models are commonly used in Information Retrieval (IR) applications, such as Retrieval-Augmented Generation (RAG). Since they often serve as the first step in these systems, their robustness is critical to avoid downstream…

Large Language Models (LLMs) have demonstrated strong capabilities in biomedical question answering, yet their tendency to generate plausible but unverified claims poses serious risks in clinical settings. To mitigate these risks, the TREC…

Multilingual dense retrieval aims to retrieve relevant documents across different languages based on a unified retriever model. The challenge lies in aligning representations of different languages in a shared vector space. The common…

In this paper, we reflect on ways to improve the quality of bio-medical information retrieval by drawing implicit negative feedback from negated information in noisy natural language search queries. We begin by studying the extent to which…

While dense retrieval has been shown effective and efficient across tasks and languages, it remains difficult to create effective fully zero-shot dense retrieval systems when no relevance label is available. In this paper, we recognize the…

In a number of information retrieval applications (e.g., patent search, literature review, due diligence, etc.), preventing false negatives is more important than preventing false positives. However, approaches designed to reduce review…

Conversational search (CS) needs a holistic understanding of conversational inputs to retrieve relevant passages. In this paper, we demonstrate the existence of a retrieval shortcut in CS, which causes models to retrieve passages solely…

The performance of Dense retrieval (DR) is significantly influenced by the quality of negative sampling. Traditional DR methods primarily depend on naive negative sampling techniques or on mining hard negatives through external retriever…

The choice of negative examples is important in noise contrastive estimation. Recent works find that hard negatives -- highest-scoring incorrect examples under the model -- are effective in practice, but they are used without a formal…