Related papers: Efficient Title Reranker for Fast and Improved Kno…

Generating knowledge-intensive and comprehensive long texts, such as encyclopedia articles, remains significant challenges for Large Language Models. It requires not only the precise integration of facts but also the maintenance of thematic…

The standard evaluation protocol for measuring the quality of Knowledge Graph Completion methods - the task of inferring new links to be added to a graph - typically involves a step which ranks every entity of a Knowledge Graph to assess…

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when deploying Large Language Models (LLMs), as it can address typical limitations such as generating hallucinated or outdated information.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…

Retrieval-Augmented Code Generation (RACG) is a critical technique for enhancing code generation by retrieving relevant information. In this work, we conduct an in-depth analysis of code retrieval by systematically masking specific features…

Recent developments of dense retrieval rely on quality representations of queries and contexts from pre-trained query and context encoders. In this paper, we introduce TOUR (Test-Time Optimization of Query Representations), which further…

Large language model (LLM) based listwise reranking has emerged as the dominant paradigm for achieving state-of-the-art ranking effectiveness in information retrieval. However, its reliance on feeding full passage texts into the LLM…

The knowledge replay technique has been widely used in many tasks such as continual learning and continuous domain adaptation. The key lies in how to effectively encode the knowledge extracted from previous data and replay them during…

Recent advancements in QA with LLM, like GPT-4, have shown limitations in handling complex multi-hop queries. We propose AT-RAG, a novel multistep RAG incorporating topic modeling for efficient document retrieval and reasoning. Using…

The text retrieval is the task of retrieving similar documents to a search query, and it is important to improve retrieval accuracy while maintaining a certain level of retrieval speed. Existing studies have reported accuracy improvements…

In this paper, we identify a critical problem, "lost-in-retrieval", in retrieval-augmented multi-hop question answering (QA): the key entities are missed in LLMs' sub-question decomposition. "Lost-in-retrieval" significantly degrades the…

Search algorithms and user query relevance have given LLMs the ability to return relevant information, but the effect of content phrasing on ad visibility remains underexplored. We investigate how LLM-based rewriting of advertisements can…

Retrieval in Retrieval-Augmented Generation(RAG) must ensure that retrieved passages are not only individually relevant but also collectively form a comprehensive set. Existing approaches primarily rerank top-k passages based on their…

The Retrieval-Augmented Generation (RAG) framework introduces a retrieval module to dynamically inject retrieved information into the input context of large language models (LLMs), and has demonstrated significant success in various NLP…

Retrieval-augmented generation models offer many benefits over standalone language models: besides a textual answer to a given query they provide provenance items retrieved from an updateable knowledge base. However, they are also more…

The results of information retrieval (IR) are usually presented in the form of a ranked list of candidate documents, such as web search for humans and retrieval-augmented generation for large language models (LLMs). List-aware retrieval…

Linking issue reports to the commits that resolve them is essential for software traceability, maintenance, and evolution. Accurate issue-commit links help developers to understand system changes and the rationale behind them. While…

Retrieval-Augmented Generation (RAG) has significantly improved the performance of large language models (LLMs) on knowledge-intensive tasks in recent years. However, since retrieval systems may return irrelevant content, incorporating such…

Supervised ranking methods based on bi-encoder or cross-encoder architectures have shown success in multi-stage text ranking tasks, but they require large amounts of relevance judgments as training data. In this work, we propose Listwise…

Retrieving known items from vague descriptions, Tip-of-the-Tongue (ToT) retrieval, remains a significant challenge. We propose using a single call to a generic 8B-parameter LLM for query reformulation, bridging the gap between ill-formed…

The goal of local citation recommendation is to recommend a missing reference from the local citation context and optionally also from the global context. To balance the tradeoff between speed and accuracy of citation recommendation in the…