Related papers: Evaluating Embedding Models and Pipeline Optimizat…

Transformer-based models have advanced the field of question answering, but multi-hop reasoning, where answers require combining evidence across multiple passages, remains difficult. This paper presents a comprehensive evaluation of…

Systematic reviews require the use of rigorously designed search strategies to ensure both comprehensive retrieval and minimization of bias. Conventional manual approaches, although methodologically systematic, are resource-intensive and…

Large Language Models (LLMs) have achieved impressive progress in natural language processing, but their limited ability to retain long-term context constrains performance on document-level or multi-turn tasks. Retrieval-Augmented…

Learning a distinct representation for each sense of an ambiguous word could lead to more powerful and fine-grained models of vector-space representations. Yet while `multi-sense' methods have been proposed and tested on artificial…

Dense retrieval, which encodes queries and documents into a single dense vector, has become the dominant neural retrieval approach due to its simplicity and compatibility with fast approximate nearest neighbor algorithms. As the tasks dense…

Vector search and retrieval-augmented generation (RAG) rest on the assumption that cosine similarity between text embeddings reflects conceptual relatedness. We measure where this assumption breaks. We build an augmented citation graph over…

In the Bag-of-Words (BoW) model based image retrieval task, the precision of visual matching plays a critical role in improving retrieval performance. Conventionally, local cues of a keypoint are employed. However, such strategy does not…

Retrieval-augmented generation (RAG) has emerged as a promising paradigm for improving factual accuracy in large language models (LLMs). We introduce a benchmark designed to evaluate RAG pipelines as a whole, evaluating a pipeline's ability…

Modern deterministic retrieval pipelines prioritize achieving state-of-the-art performance but often lack interpretability in decision-making. These models face challenges in assessing uncertainty, leading to overconfident predictions. To…

Sentiment analysis is one of the well-known tasks and fast growing research areas in natural language processing (NLP) and text classifications. This technique has become an essential part of a wide range of applications including politics,…

Information retrieval involves selecting artifacts from a corpus that are most relevant to a given search query. The flavor of retrieval typically used in classical applications can be termed as homogeneous and relaxed, where queries and…

The increasing volume and complexity of scientific literature demand robust methods for organizing and understanding research documents. In this study, we investigate whether structured knowledge, specifically, subject-predicate-object…

Objective: Applying large language models (LLMs) to the clinical domain is challenging due to the context-heavy nature of processing medical records. Retrieval-augmented generation (RAG) offers a solution by facilitating reasoning over…

This research paper presents a comprehensive analysis of integrating advanced language models with search and retrieval systems in the fields of information retrieval and natural language processing. The objective is to evaluate and compare…

Generative search engines and deep research LLM agents promise trustworthy, source-grounded synthesis, yet users regularly encounter overconfidence, weak sourcing, and confusing citation practices. We introduce DeepTRACE, a novel…

We compile 129 heterogeneous LLM prompt datasets (>1.22 TB, >673M instances) into a structured taxonomy and conduct a multi-level linguistic analysis (lexical, syntactic, and semantic) on seven representative corpora, surfacing systematic…

Investigative journalists routinely confront large document collections. Large language models (LLMs) with retrieval-augmented generation (RAG) capabilities promise to accelerate the process of document discovery, but newsroom adoption…

Recent advancements in language models have started a new era of superior information retrieval and content generation, with embedding models playing an important role in optimizing data representation efficiency and performance. While…

With the increasing size of large language models, layer pruning has gained increased attention as a hardware-friendly approach for model compression. However, existing layer pruning methods struggle to simultaneously address key practical…

Machine learning pipeline potentially consists of several stages of operations like data preprocessing, feature engineering and machine learning model training. Each operation has a set of hyper-parameters, which can become irrelevant for…