Related papers: Revisiting and Improving Retrieval-Augmented Deep …

Retrieval-Augmented Generation (RAG) has emerged as a way to complement the in-context knowledge of Large Language Models (LLMs) by integrating external documents. However, real-world applications demand not only accuracy but also…

Type errors in Python often lead to runtime failures, posing significant challenges to software reliability and developer productivity. Existing static analysis tools aim to detect such errors without execution but frequently suffer from…

Retrieval-Augmented Generation (RAG) has emerged as a promising approach to address key limitations of Large Language Models (LLMs), such as hallucination, outdated knowledge, and lacking reference. However, current RAG frameworks often…

We propose a training-free approach to improve sentence embeddings leveraging test-time compute by applying generative text models for data augmentation at inference time. Unlike conventional data augmentation that utilises synthetic…

Software defects heavily affect software's functionalities and may cause huge losses. Recently, many AI-based approaches have been proposed to detect defects, which can be divided into two categories: software defect prediction and…

Dense retrieval has become a prominent method to obtain relevant context or world knowledge in open-domain NLP tasks. When we use a learned dense retriever on a retrieval corpus at inference time, an often-overlooked design choice is the…

Inspired by the success of reinforcement learning (RL) in Large Language Model (LLM) training for domains like math and code, recent works have begun exploring how to train LLMs to use search engines more effectively as tools for…

We revisit estimation and computation of the Dickey Fuller (DF) and DF-type tests. Firstly, we show that the usual one step approach, based on the "DF autoregression", is likely to be subject to misspecification. Secondly, we clarify a…

Large-scale digitization initiatives have unlocked massive collections of historical newspapers, yet effective computational access remains hindered by OCR corruption, multilingual orthographic variation, and temporal language drift. We…

Online misinformation remains a critical challenge, and fact-checkers increasingly rely on claim matching systems that use sentence embedding models to retrieve relevant fact-checks. However, as users interact with claims online, they often…

Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is…

Real-world data contains various kinds of errors. Before analyzing data, one usually needs to process the raw data. However, traditional data processing based on exactly match often misses lots of valid information. To get high-quality…

The evolution of Large Language Models (LLMs) towards autonomous agents has catalyzed progress in Deep Research. While retrieval capabilities are well-benchmarked, the post-retrieval synthesis stage--where agents must digest massive amounts…

Retrieval-Augmented Generation (RAG) systems commonly adopt retrieval fusion techniques such as multi-query retrieval and reciprocal rank fusion (RRF) to increase document recall, under the assumption that higher recall leads to better…

Prior work has commonly defined argument retrieval from heterogeneous document collections as a sentence-level classification task. Consequently, argument retrieval suffers both from low recall and from sentence segmentation errors making…

In this paper, we introduce Technical-Embeddings, a novel framework designed to optimize semantic retrieval in technical documentation, with applications in both hardware and software development. Our approach addresses the challenges of…

Fact verification (FV) is a challenging task which aims to verify a claim using multiple evidential sentences from trustworthy corpora, e.g., Wikipedia. Most existing approaches follow a three-step pipeline framework, including document…

Recent progress in controllable image generation and editing is largely driven by diffusion-based methods. Although diffusion models perform exceptionally well in specific tasks with tailored designs, establishing a unified model is still…

The longitudinal evaluation of retrieval systems aims to capture how information needs and documents evolve over time. However, classical Cranfield-style retrieval evaluations only consist of a static set of queries and documents and…

Intent discovery is the task of inferring latent intents from a set of unlabeled utterances, and is a useful step towards the efficient creation of new conversational agents. We show that recent competitive methods in intent discovery can…