Related papers: Self-Supervised Query Reformulation for Code Searc…

Reinforcement learning (RL) for complex tasks remains a challenge, primarily due to the difficulties of engineering scalar reward functions and the inherent inefficiency of training models from scratch. Instead, it would be better to…

Despite the recent success of contextualized language models on various NLP tasks, language model itself cannot capture textual coherence of a long, multi-sentence document (e.g., a paragraph). Humans often make structural decisions on what…

Test-time scaling has been shown to substantially improve large language models' (LLMs) mathematical reasoning. However, for a large portion of mathematical corpora, especially theorem proving, RLVR's scalability is limited: intermediate…

In recent years, the field of neural machine translation (NMT) for SPARQL query generation has witnessed significant growth. Incorporating the copy mechanism with traditional encoder-decoder architectures and using pre-trained…

Zero-shot composed image retrieval (ZS-CIR), which takes a textual modification and a reference image as a query to retrieve a target image without triplet labeling, has gained more and more attention in data mining. Current ZS-CIR research…

Traditional query optimizers are designed to be fast and stateless: each query is quickly optimized using approximate statistics, sent off to the execution engine, and promptly forgotten. Recent work on learned query optimization have shown…

Query Optimization (QO) has become essential for enhancing Large Language Model (LLM) effectiveness, particularly in Retrieval-Augmented Generation (RAG) systems where query quality directly determines retrieval and response performance.…

Query translation (QT) is a key component in cross-lingual information retrieval system (CLIR). With the help of deep learning, neural machine translation (NMT) has shown promising results on various tasks. However, NMT is generally trained…

Current AI-powered code assistance tools often struggle with poorly-defined problem statements that lack sufficient task context and requirements specification. Recent analysis of software engineering agents reveals that failures on such…

Keyword spotting (KWS) in historical documents is an important tool for the initial exploration of digitized collections. Nowadays, the most efficient KWS methods are relying on machine learning techniques that require a large amount of…

Masked reconstruction serves as a fundamental pretext task for self-supervised learning, enabling the model to enhance its feature extraction capabilities by reconstructing the masked segments from extensive unlabeled data. In human…

Graph database query languages feature expressive, yet computationally expensive pattern matching capabilities. Answering optional query clauses in SPARQL for instance renders the query evaluation problem immediately Pspace-complete.…

Vision-language models (VLMs) have shown remarkable abilities by integrating large language models with visual inputs. However, they often fail to utilize visual evidence adequately, either depending on linguistic priors in vision-centric…

Evaluation of QA systems is very challenging and expensive, with the most reliable approach being human annotations of correctness of answers for questions. Recent works (AVA, BEM) have shown that transformer LM encoder based similarity…

Change captioning aims to describe the difference between a pair of similar images. Its key challenge is how to learn a stable difference representation under pseudo changes caused by viewpoint change. In this paper, we address this by…

Optimizing queries for Retrieval-Augmented Generation (RAG) systems poses a significant challenge, particularly across diverse modal indices. We introduce RL-QR, a novel annotation-free reinforcement learning framework for query rewriting…

Effective cross-lingual dense retrieval methods that rely on multilingual pre-trained language models (PLMs) need to be trained to encompass both the relevance matching task and the cross-language alignment task. However, cross-lingual data…

Many datasets change over time. As a consequence, long-running applications that cache and repeatedly use query results obtained from a SPARQL endpoint may resubmit the queries regularly to ensure up-to-dateness of the results. While this…

The current boom of learned query optimizers (LQO) can be explained not only by the general continuous improvement of deep learning (DL) methods but also by the straightforward formulation of a query optimization problem (QOP) as a machine…

Recent work in commerce search has shown that understanding the semantics in user queries enables more effective query analysis and retrieval of relevant products. However, due to lack of sufficient domain knowledge, user queries often…