Related papers: REGENT: Relevance-Guided Attention for Entity-Awar…

While entity-oriented neural IR models have advanced significantly, they often overlook a key nuance: the varying degrees of influence individual entities within a document have on its overall relevance. Addressing this gap, we present…

Pairing a lexical retriever with a neural re-ranking model has set state-of-the-art performance on large-scale information retrieval datasets. This pipeline covers scenarios like question answering or navigational queries, however, for…

Recurrent neural networks have proven effective in modeling sequential user feedbacks for recommender systems. However, they usually focus solely on item relevance and fail to effectively explore diverse items for users, therefore harming…

Referring Expression Comprehension (REC) aims to localize specified entities or regions in an image based on natural language descriptions. While existing methods handle single-entity localization, they often ignore complex inter-entity…

In information retrieval, learning to rank constructs a machine-based ranking model which given a query, sorts the search results by their degree of relevance or importance to the query. Neural networks have been successfully applied to…

Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains models to estimate passage-query relevance using the attention scores of selected heads. This approach…

Accurate document retrieval is crucial for the success of retrieval-augmented generation (RAG) applications, including open-domain question answering and code completion. While large language models (LLMs) have been employed as dense…

As Large Language Models (LLMs) continue to advance, Retrieval-Augmented Generation (RAG) has emerged as a vital technique to enhance factual accuracy by integrating external knowledge into the generation process. However, LLMs often fail…

When combined with In-Context Learning, a technique that enables models to adapt to new tasks by incorporating task-specific examples or demonstrations directly within the input prompt, autoregressive language models have achieved good…

Neural IR has advanced through two distinct paths: entity-oriented approaches leveraging knowledge graphs and multi-vector models capturing fine-grained semantics. We introduce QDER, a neural re-ranking model that unifies these approaches…

Entity Linking has two main open areas of research: 1) generate candidate entities without using alias tables and 2) generate more contextual representations for both mentions and entities. Recently, a solution has been proposed for the…

Entity linking aims to establish a link between entity mentions in a document and the corresponding entities in knowledge graphs (KGs). Previous work has shown the effectiveness of global coherence for entity linking. However, most of the…

Building generalist agents that can rapidly adapt to new environments is a key challenge for deploying AI in the digital and real worlds. Is scaling current agent architectures the most effective way to build generalist agents? We propose a…

While Generative AI has demonstrated strong potential and versatility in content generation, its application to educational contexts presents several challenges. Models often fail to align with curriculum standards and maintain…

In agent memory systems, the reranking model serves as the critical bridge connecting user queries with long-term memory. Most systems adopt the "retrieve-then-rerank" two-stage paradigm, but generic reranking models rely on semantic…

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…

Classifying semantic relations between entity pairs in sentences is an important task in Natural Language Processing (NLP). Most previous models for relation classification rely on the high-level lexical and syntactic features obtained by…

Recurrent neural networks (RNNs) are capable of modeling temporal dependencies of complex sequential data. In general, current available structures of RNNs tend to concentrate on controlling the contributions of current and previous…

Recurrent neural networks (RNNs) are capable of modeling the temporal dynamics of complex sequential information. However, the structures of existing RNN neurons mainly focus on controlling the contributions of current and historical…

Named-entity recognition (NER) detects texts with predefined semantic labels and is an essential building block for natural language processing (NLP). Notably, recent NER research focuses on utilizing massive extra data, including…