Related papers: Improving Code Search with Hard Negative Sampling …

Semantic code search, which aims to retrieve code snippets relevant to a given natural language query, has attracted many research efforts with the purpose of accelerating software development. The huge amount of online publicly available…

This paper addresses the problem of learning binary hash codes for large scale image search by proposing a novel hashing method based on deep neural network. The advantage of our deep model over previous deep model used in hashing is that…

Fine-tuning in information retrieval systems using pre-trained language models (PLM-based IR) requires learning query representations and query-document relations, in addition to downstream task-specific learning. This study introduces…

Neural document retrieval often treats a corpus as a flat cloud of vectors scored at a single granularity, leaving corpus structure underused and explanations opaque. We use Cobweb--a hierarchy-aware framework--to organize sentence…

Dual encoder models are ubiquitous in modern classification and retrieval. Crucial for training such dual encoders is an accurate estimation of gradients from the partition function of the softmax over the large output space; this requires…

Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…

A novel pseudocode search engine is designed to facilitate efficient retrieval and search of academic papers containing pseudocode. By leveraging Elasticsearch, the system enables users to search across various facets of a paper, such as…

Recent progress in Large Language Models (LLMs) has opened new avenues for solving complex optimization problems, including Neural Architecture Search (NAS). However, existing LLM-driven NAS approaches rely heavily on prompt engineering and…

Embedding-based retrieval (EBR) methods are widely used in modern recommender systems thanks to its simplicity and effectiveness. However, along the journey of deploying and iterating on EBR in production, we still identify some fundamental…

Large Language Models (LLMs) demonstrate strong capabilities in general coding tasks but encounter two key challenges when optimizing code: (i) the complexity of writing optimized code (such as performant CUDA kernels and competition-level…

Pre-trained language models have demonstrated powerful capabilities in the field of natural language processing (NLP). Recently, code pre-trained model (PTM), which draw from the experiences of the NLP field, have also achieved…

Traditional multimodal retrieval systems rely primarily on bi-encoder architectures, where performance is closely tied to embedding dimensionality. Recent work, Think-Then-Embed (TTE), shows that incorporating multimodal reasoning to elicit…

Vector retrieval systems exhibit significant performance variance across queries due to heterogeneous embedding quality. We propose a lightweight framework for predicting retrieval performance at the query level by combining quantization…

The use of deep pre-trained bidirectional transformers has led to remarkable progress in a number of applications (Devlin et al., 2018). For tasks that make pairwise comparisons between sequences, matching a given input with a corresponding…

With the recent success of dense retrieval methods based on bi-encoders, studies have applied this approach to various interesting downstream retrieval tasks with good efficiency and in-domain effectiveness. Recently, we have also seen the…

Code search aims to retrieve semantically relevant code snippets for a given natural language query. Recently, many approaches employing contrastive learning have shown promising results on code representation learning and greatly improved…

State-of-the-art cross-encoders can be fine-tuned to be highly effective in passage re-ranking. The typical fine-tuning process of cross-encoders as re-rankers requires large amounts of manually labelled data, a contrastive learning…

A prerequisite for coding agents to perform tasks on large repositories is code localization - the identification of relevant files, classes, and functions to work on. While repository-level code localization has been performed using…

In dense retrieval, effective training hinges on selecting high quality hard negatives while avoiding false negatives. Recent methods apply heuristics based on positive document scores to identify hard negatives, improving both performance…

The Hypencoder, proposed by Killingback et al., is a retrieval framework that replaces the fixed inner-product scoring function used in standard bi-encoders with a query-specific neural network (the $q$-net), whose weights are generated by…