Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

295988117 · Jun 202019922001200920172026
48 results for retrieval bias

Study compares methods for improving document retrieval accuracy.

problem Improving document retrieval accuracy from large corpora.
method Comparison of query expansion, topic models, and active learning.
result Active learning outperforms keyword lists in most settings.

GMC benchmark isolates retrieval in Transformers, revealing max-margin alignment.

problem Understanding how Transformers develop match-and-copy behavior on natural data.
method Introducing Gaussian Match-and-Copy (GMC) as a minimalist benchmark.
result Gradient descent drives parameters to diverge while aligning with max-margin separator.

Just as semantic hashing can accelerate information retrieval, binary valued embeddings can significantly reduce latency in the retrieval of graphical data. We introduce a simple but effective model for learning such binary vectors for nodes in a graph. By imagining the embeddings as independent coin flips of varying b…

2018-03-25abs ↗pdf ↗

DINOSAUR improves retrieval by accounting for embedding uncertainty in recommender systems.

problem Retrieval bias towards popular items due to noisy embeddings.
method Samples multiple embeddings per item and queries with sampled embeddings to account for uncertainty.
result Improves coverage of long-tail niche content without sacrificing recall.

Model user preferences for conversational LLMs using weak rewards.

problem Lack of persistent user models in conversational LLMs leading to repeated user restatements.
method Vector-Adapted Retrieval Scoring (VARS) framework that updates user vectors online from weak scalar rewards.
result Full VARS agent achieves strongest overall performance, matches strong Reflection baseline in task success, and reduces user effort.

Minwise hashing (Minhash) is a widely popular indexing scheme in practice. Minhash is designed for estimating set resemblance and is known to be suboptimal in many applications where the desired measure is set overlap (i.e., inner product between binary vectors) or set containment. Minhash has inherent bias towards sma…

2014-11-14abs ↗pdf ↗

SOCP uses SOM to find groups and local calibration buffers for better regional coverage.

problem Heterogeneous regional coverage gaps in conformal prediction.
method Self-Organizing Map (SOM) for group discovery; local calibration buffers at BMU or fixed grid.
result Reduces regional coverage gaps on 7/8 benchmarks by 7.1%.

Over the last decade there has been increasing concern about the biases embodied in traditional evaluation methods for Natural Language Processing/Learning, particularly methods borrowed from Information Retrieval. Without knowledge of the Bias and Prevalence of the contingency being tested, or equivalently the expecta…

2015-04-03abs ↗pdf ↗

New error bounds for noisy phase retrieval problems using empirical risk minimization.

problem Estimating signals in noisy phase retrieval problems.
method Empirical 2\ell_2 risk minimization (ERM) with new error bounds for different noise patterns.
result Established new error bounds for NPR and NGPR, showing improved performance under various noise conditions.

Generative AI reduces IR evaluation costs but introduces errors; this work provides reliable CIs.

problem Generating relevance annotations using AI introduces errors that affect IR evaluation metrics.
method Proposes two methods: prediction-powered inference and conformal risk control to place reliable CIs around IR metrics.
result Proposed methods accurately capture both variance and bias in evaluation based on AI-generated annotations.

Lossy compression of statistical data using quantum annealing.

problem Efficiently compressing statistical floating-point data.
method Representation learning with binary variables, classical optimization of basis vectors, quantum annealing for coefficients, bias correction.
result Quantum annealing shows promising results with 3.5x better compression than neural-network autoencoders.

This paper evaluates fairness in deep metric learning and proposes a method to reduce subgroup performance gaps.

problem The negative impact of deep metric learning representations on minority subgroup performance in downstream tasks.
method Definition of fairness in DML through inter-class, intra-class, and uniformity properties; finDML benchmark; Partial Attribute De-correlation (PARADE) method.
result Bias in DML representations propagates to downstream tasks, even with balanced training data.

Improves retrieval accuracy for hierarchical documents, especially for distant matches.

problem Limited expressive power of dual encoder models in hierarchical retrieval.
method Proves feasibility of DEs for HR, introduces pretrain-finetune recipe to improve long-distance retrieval.
result Pretrain-finetune boosts recall on long-distance pairs from 19% to 76%.

This paper improves image retrieval accuracy through novel relevance feedback methods.

problem Improving image retrieval accuracy in Content-Based Image Retrieval (CBIR).
method Novel addition to feature re-weighting and classification techniques, focusing on 0-th iteration improvement.
result Significantly improved retrieval accuracy from relevance feedback.

Transformer models improve query-document retrieval efficiency and accuracy.

problem Efficiently retrieve relevant documents from large corpora for query matching.
method Designed paragraph-level pre-training tasks to optimize embedding-based Transformer models.
result Transformer models significantly outperform BM-25 and non-Transformer embedding models.

Modeling wildfire aerosols using satellite data to predict solar radiation reduction.

problem Accurately estimate and predict AOD propagation from wildfires using multi-source satellite data.
method Physics-informed statistical modeling integrating multi-source satellite data with an advection-diffusion equation.
result The proposed approach accurately predicts AOD propagation and demonstrates model interpretability.

Introduces MPR to measure and optimize representation across intersectional groups in retrieval.

problem Harmful stereotypes, cultural erasure, and social disparities in image search and retrieval.
method Develops MPR metric, practical estimation methods, theoretical guarantees, and optimization algorithms.
result Optimizing MPR yields more proportional representation across multiple intersectional groups, often with minimal retrieval accuracy compromise.

BERT model improves cross-lingual document retrieval.

problem Improving cross-lingual information retrieval between English queries and foreign documents.
method Introduced a deep relevance matching model based on BERT, trained with weak supervision using CLIR data.
result Model outperforms competitive baseline approaches in retrieving Lithuanian documents against short English queries.

A new property fixes look-ahead bias in backtesting and trading pipelines.

problem Fixing look-ahead bias in backtesting and trading pipelines.
method Developed a pipeline calculus separating availability from reference time, and a type-and-effect system for the value-independent fragment.
result The check scales linearly and catches all leaks, including those missed by differential and tiling detectors.

Sharp asymptotics derived for phase retrieval and compressed sensing with random generative priors.

problem Phase retrieval and compressed sensing with random measurement matrices.
method Sharp asymptotics derived for optimal performance and polynomial algorithm for random generative priors.
result Compressed phase retrieval becomes tractable with random generative priors, unlike sparse priors.

Most content-based image retrieval systems consider either one single query, or multiple queries that include the same object or represent the same semantic information. In this paper we consider the content-based image retrieval problem for multiple query images corresponding to different image semantics. We propose a…

2014-02-21abs ↗pdf ↗

For the task of generating complex outputs such as source code, editing existing outputs can be easier than generating complex outputs from scratch. With this motivation, we propose an approach that first retrieves a training example based on the input (e.g., natural language description) and then edits it to the desir…

2018-12-04abs ↗pdf ↗

HybridRAG combines KGs and vector retrieval for financial document Q&A.

problem Challenges in extracting and interpreting financial text data.
method Integrates Knowledge Graphs and Vector Retrieval Augmented Generation.
result HybridRAG outperforms traditional methods in Q&A systems for financial documents.

This paper improves retrieval for LLMs in financial document Q&A.

problem Suboptimal text chunk retrieval by RAG causes inaccuracies in LLM responses.
method Sophisticated chunking techniques, query expansion, metadata annotations, re-ranking algorithms, and embedding fine-tuning.
result Enhanced retrieval quality improves LLM performance and reliability.

We study the task of retrieving relevant experiments given a query experiment. By experiment, we mean a collection of measurements from a set of `covariates' and the associated `outcomes'. While similar experiments can be retrieved by comparing available `annotations', this approach ignores the valuable information ava…

2014-02-19abs ↗pdf ↗

RNNs struggle with in-context retrieval, while Transformers excel.

problem In-context retrieval capability of RNNs.
method Theoretical analysis and experimental techniques (CoT, RAG, Transformer layer).
result Enhancing RNNs with techniques improves their in-context retrieval capability, closing the representation gap with Transformers.