Related papers: RECIPER: A Dual-View Retrieval Pipeline for Proced…

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…

Utilizing large language models (LLMs) for zero-shot document ranking is done in one of two ways: (1) prompt-based re-ranking methods, which require no further training but are only feasible for re-ranking a handful of candidate documents…

Despite recent advancements in Large Language Models (LLMs), their performance on tasks involving long contexts remains sub-optimal. In this work, we propose DoubleDipper, a novel In-Context-Learning method that automatically generates…

Software developers write a lot of source code and documentation during software development. Intrinsically, developers often recall parts of source code or code summaries that they had written in the past while implementing software or…

A common retrieve-and-rerank paradigm involves retrieving relevant candidates from a broad set using a fast bi-encoder (BE), followed by applying expensive but accurate cross-encoders (CE) to a limited candidate set. However, relying on…

In the recent years, the dual-encoder vision-language models (\eg CLIP) have achieved remarkable text-to-image retrieval performance. However, we discover that these models usually results in very different retrievals for a pair of…

Dense retrieval compresses texts into single embeddings ranked by cosine similarity. While efficient for recall, this interface is brittle for identity-level matching: minimal compositional edits (negation, role swaps) flip meaning yet…

This paper presents a procedure to retrieve subsets of relevant documents from large text collections for Content Analysis, e.g. in social sciences. Document retrieval for this purpose needs to take account of the fact that analysts often…

Dense retrieval is a basic building block of information retrieval applications. One of the main challenges of dense retrieval in real-world settings is the handling of queries containing misspelled words. A popular approach for handling…

Effective and efficient access to relevant information is essential for disaster management. However, no retrieval model is specialized for disaster management, and existing general-domain models fail to handle the varied search intents…

This paper introduces Golden-Retriever, designed to efficiently navigate vast industrial knowledge bases, overcoming challenges in traditional LLM fine-tuning and RAG frameworks with domain-specific jargon and context interpretation.…

Knowledge-intensive tasks, such as open-domain question answering (QA), require access to a large amount of world or domain knowledge. A common approach for knowledge-intensive tasks is to employ a retrieve-then-read pipeline that first…

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…

This paper presents the systems we developed for RIRAG-2025, a shared task that requires answering regulatory questions by retrieving relevant passages. The generated answers are evaluated using RePASs, a reference-free and model-based…

Many users turn to document retrieval systems (e.g. search engines) to seek answers to controversial questions. Answering such user queries usually require identifying responses within web documents, and aggregating the responses based on…

Conversational search requires accurate interpretation of user intent from complex multi-turn contexts. This paper presents ChatRetriever, which inherits the strong generalization capability of large language models to robustly represent…

Relevance feedback techniques assume that users provide relevance judgments for the top k (usually 10) documents and then re-rank using a new query model based on those judgments. Even though this is effective, there has been little…

Reranking, the process of refining the output of a first-stage retriever, is often considered computationally expensive, especially with Large Language Models. Borrowing from recent advances in document compression for RAG, we reduce the…

In simple open-domain question answering (QA), dense retrieval has become one of the standard approaches for retrieving the relevant passages to infer an answer. Recently, dense retrieval also achieved state-of-the-art results in multi-hop…

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,…