Related papers: Improving BM25 Code Retrieval Under Fixed Generic …

Biased-noise qubits, in which one type of error (e.g. $X$- and $Y$-type errors) is significantly suppressed relative to the other (e.g. $Z$-type errors), can significantly reduce the overhead of quantum error correction. Codes such as the…

Passage Retrieval has traditionally relied on lexical methods like TF-IDF and BM25. Recently, some neural network models have surpassed these methods in performance. However, these models face challenges, such as the need for large…

We develop and analyze a broad family of stochastic/randomized algorithms for inverting a matrix. We also develop specialized variants maintaining symmetry or positive definiteness of the iterates. All methods in the family converge…

We propose training fitted Q-iteration with log-loss (FQI-log) for batch reinforcement learning (RL). We show that the number of samples needed to learn a near-optimal policy with FQI-log scales with the accumulated cost of the optimal…

This paper presents an enhancement to Grover's search algorithm for instances where the number of items (or the size of the search problem) $N$ is not a power of 2. By employing an efficient algorithm for the preparation of uniform quantum…

Long-term conversational memory is a retrieval workload classical IR was not built for: the index grows during the query stream, query types shift intra-session, and the latency budget per retrieval is sub-10 ms. Lucene-class engines treat…

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge bases, achieving state-of-the-art results in various coding tasks. The core of RAG is retrieving demonstration examples, which is…

Invertible Bloom Filter (IBF) is a data structure, which employs a small set of hash functions. An IBF allows for an efficient insertion and, with high probability, for an efficient extraction of the data. However, the success probability…

Transformers used for evidence-grounded question answering with binary adjudication (e.g., support/refute or yes/no) can be highly sensitive to the order in which exchangeable evidence is presented, producing dispersion across permutations…

LLM-reranking is limited by the top-k documents retrieved by vector similarity, which neither enables contextual query-document token interactions nor captures multimodal relevance distributions. While LLM query reformulation attempts to…

In this brief, we improve the Broad Learning System (BLS) [7] by reducing the computational complexity of the incremental learning for added inputs. We utilize the inverse of a sum of matrices in [8] to improve a step in the pseudoinverse…

We propose an approach for optimizing nonbinary (NB) quasi-cyclic (QC) LDPC codes. This approach combines constructing of base parity-check matrices by simulated annealing and labeling the obtained base matrices aimed at maximizing the…

Transformer-based document cross-encoder rerankers are a central component of modern information retrieval systems. Despite their success, these models suffer from high computational costs due to processing long query-document sequences at…

Pretrained multilingual language models are often assumed to be script-agnostic, yet their tokenizers can impose systematic costs on certain writing systems. We quantify this script tax by comparing two orthographic variants with identical…

While transformer-based models achieve strong performance on text classification, we explore whether masking input tokens can further enhance their effectiveness. We propose token masking regularization, a simple yet theoretically motivated…

Information retrieval systems retrieves relevant documents based on a query submitted by the user. The documents are initially indexed and the words in the documents are assigned weights using a weighting technique called TFIDF which is the…

Retrieval-based question answering systems often suffer from positional bias, leading to suboptimal answer generation. We propose LoRE (Logit-Ranked Retriever Ensemble), a novel approach that improves answer accuracy and relevance by…

Imagine handling collisions in a hash table by storing, in each cell, the bit-wise exclusive-or of the set of keys hashing there. This appears to be a terrible idea: For $\alpha n$ keys and $n$ buckets, where $\alpha$ is constant, we expect…

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…

Belief Propagation (BP) followed by Ordered Statistics Decoding (OSD) has emerged as the gold standard for decoding quantum low-density parity-check (QLDPC) codes. Recent advancements in this field have proposed new methods and algorithms…