Related papers: Least Information Modeling for Information Retriev…
Large Language Models (LLMs) are proficient at retrieving single facts from extended contexts, yet they struggle with tasks requiring the simultaneous retrieval of multiple facts, especially during generation. This paper identifies a novel…
This paper proposes a theoretical framework which models the information provided by retrieval systems in terms of Information Theory. The proposed framework allows to formalize: (i) system effectiveness as an information theoretic…
In the information-based paradigm of inference, model selection is performed by selecting the candidate model with the best estimated predictive performance. The success of this approach depends on the accuracy of the estimate of the…
Effective information retrieval (IR) in settings with limited training data, particularly for complex queries, remains a challenging task. This paper introduces IR2, Information Regularization for Information Retrieval, a technique for…
Information retrieval plays a crucial role in resource localization. Current dense retrievers retrieve the relevant documents within a corpus via embedding similarities, which compute similarities between dense vectors mainly depending on…
Information verification is quite a challenging task, this is because many times verifying a claim can require picking pieces of information from multiple pieces of evidence which can have a hierarchy of complex semantic relations.…
Users increasingly expect modern search systems to offer a unified interface that seamlessly retrieves information from diverse data sources and formats. However, current information retrieval (IR) evaluation benchmarks have not kept pace…
Recently, a Distribution Separation Method (DSM) is proposed for relevant feedback in information retrieval, which aims to approximate the true relevance distribution by separating a seed irrelevance distribution from the mixture one. While…
We propose a framework for discriminative Information Retrieval (IR) atop linguistic features, trained to improve the recall of tasks such as answer candidate passage retrieval, the initial step in text-based Question Answering (QA). We…
Summarizing content contributed by individuals can be challenging, because people make different lexical choices even when describing the same events. However, there remains a significant need to summarize such content. Examples include the…
The information ratio offers an approach to assessing the efficacy with which an agent balances between exploration and exploitation. Originally, this was defined to be the ratio between squared expected regret and the mutual information…
The success of neural networks on a diverse set of NLP tasks has led researchers to question how much these networks actually ``know'' about natural language. Probes are a natural way of assessing this. When probing, a researcher chooses a…
Nowadays, according to the increasingly increasing information, the importance of its presentation is also increasing. The internet has become one of the main sources of information for users and their favorite topics. It also provides…
In inference problems, we often have domain knowledge which allows us to define summary statistics that capture most of the information content in a dataset. In this paper, we present a hybrid approach, where such physics-based summaries…
Literature search questions, such as "Where can I find research on the evaluation of consistency in generated summaries?" pose significant challenges for modern search engines and retrieval systems. These questions often require a deep…
Generative models for Information Retrieval, where ranking of documents is viewed as the task of generating a query from a document's language model, were very successful in various IR tasks in the past. However, with the advent of modern…
Tokenization significantly influences language models(LMs)' performance. This paper traces the evolution of tokenizers from word-level to subword-level, analyzing how they balance tokens and types to enhance model adaptability while…
We present LEAF ("Lightweight Embedding Alignment Framework"), a knowledge distillation framework for text embedding models. A key distinguishing feature is that our distilled leaf models are aligned to their teacher. In the context of…
We present the Benchmark of Information Retrieval (IR) tasks with Complex Objectives (BIRCO). BIRCO evaluates the ability of IR systems to retrieve documents given multi-faceted user objectives. The benchmark's complexity and compact size…
Modern information retrieval (IR) is no longer consumed primarily by humans but increasingly by large language models (LLMs) via retrieval-augmented generation (RAG) and agentic search. Unlike human users, LLMs are constrained by limited…