相关论文: Improving BM25 Code Retrieval Under Fixed Generic …

In this paper, we propose how to construct a reconciliation method for the BB84 Quantum Key Distribution (QKD) protocol. Theoretically, it is unconditionally secure because it is based on the quantum laws of physics, rather than the assumed…

Learning RBMs using standard algorithms such as CD(k) involves gradient descent on the negative log-likelihood. One of the terms in the gradient, which involves expectation w.r.t. the model distribution, is intractable and is obtained…

Sequential fine-tuning of pretrained language encoders often overwrites previously acquired capabilities, but the forgetting behavior of parameter-efficient updates remains under-characterized. We present a controlled empirical study of…

We study the problem of designing worst-case to average-case reductions for quantum algorithms. For all linear problems, we provide an explicit and efficient transformation of quantum algorithms that are only correct on a small (even…

Fusion-in-Decoder (FiD) is an effective retrieval-augmented language model applied across a variety of open-domain tasks, such as question answering, fact checking, etc. In FiD, supporting passages are first retrieved and then processed…

Knowledge-intensive tasks, particularly open-domain question answering (ODQA), document reranking, and retrieval-augmented language modeling, require a balance between retrieval accuracy and generative flexibility. Traditional retrieval…

We study the expectation value of the logarithm of the partition function of large binary-to-binary lattice-gas Restricted Boltzmann Machines (RBMs) within a replica-symmetric ansatz, averaging over the disorder represented by the…

Information retrieval systems have traditionally relied on exact term match methods such as BM25 for first-stage retrieval. However, recent advancements in neural network-based techniques have introduced a new method called dense retrieval.…

We study leveraging adaptive retrieval to ensure sufficient "bridge" documents are retrieved for reasoning-intensive retrieval. Bridge documents are those that contribute to the reasoning process yet are not directly relevant to the initial…

Classical information retrieval systems such as BM25 rely on exact lexical match and carry out search efficiently with inverted list index. Recent neural IR models shifts towards soft semantic matching all query document terms, but they…

We introduce a method for solving combinatorial optimization problems on digital quantum computers, where we incorporate auxiliary counterdiabatic (CD) terms into the adiabatic Hamiltonian, while integrating bias terms derived from an…

Sparse retrieval methods like BM25 are based on lexical overlap, focusing on the surface form of the terms that appear in the query and the document. The use of inverted indices in these methods leads to high retrieval efficiency. On the…

In this paper, our objective is primarily to use adaptive inverse-quadratic (IQ) and inverse-multi-quadratic (IMQ) radial basis function (RBF) interpolation techniques to develop an enhanced Adam-Bashforth and Adam-Moulton methods. By…

Discovering which tables in large, heterogeneous repositories can be joined and by what transformations is a central challenge in data integration and data discovery. Traditional join discovery methods are largely designed for equi-joins,…

Logs are essential for diagnosing failures and conducting retrospective studies, leading many software organizations to retain log messages for a long time. Nevertheless, the volume of generated log data grows rapidly as software systems…

In this work, a deep learning-based method for log-likelihood ratio (LLR) lossy compression and quantization is proposed, with emphasis on a single-input single-output uncorrelated fading communication setting. A deep autoencoder network is…

In this work, we establish a novel theoretical connection between supervised fine-tuning and offline reinforcement learning under the token-level Markov decision process, revealing that large language models indeed learn an implicit…

Recent findings suggest that Information Retrieval (IR)-based bug localization techniques do not perform well if the bug report lacks rich structured information (eg relevant program entity names). Conversely, excessive structured…

A number of engineering and scientific problems require representing and manipulating probability distributions over large alphabets, which we may think of as long vectors of reals summing to $1$. In some cases it is required to represent…

Term-based ranking with pre-trained transformer-based language models has recently gained attention as they bring the contextualization power of transformer models into the highly efficient term-based retrieval. In this work, we examine the…