Related papers: CorpusBrain: Pre-train a Generative Retrieval Mode…

Recent advances in large-scale pre-training such as GPT-3 allow seemingly high quality text to be generated from a given prompt. However, such generation systems often suffer from problems of hallucinated facts, and are not inherently…

This paper contains what the Georgetown InfoSense group has done in regard to solving the challenges presented by TREC iKAT 2023. Our submitted runs outperform the median runs by a significant margin, exhibiting superior performance in nDCG…

Generative retrieval constitutes an innovative approach in information retrieval, leveraging generative language models (LM) to generate a ranked list of document identifiers (docid) for a given query. It simplifies the retrieval pipeline…

Generative AI models face the challenge of hallucinations that can undermine users' trust in such systems. We approach the problem of conversational information seeking as a two-step process, where relevant passages in a corpus are…

While language models have shown remarkable performance across diverse tasks, they still encounter challenges in complex reasoning scenarios. Recent research suggests that language models trained on linearized search traces toward…

Knowledge tracing (KT), wherein students' problem-solving histories are used to estimate their current levels of knowledge, has attracted significant interest from researchers. However, most existing KT models were developed with an…

While dense retrieval models, which embed queries and documents into a shared low-dimensional space, have gained widespread popularity, they were shown to exhibit important theoretical limitations and considerably lag behind traditional…

Large Language Models (LLMs) excel at reasoning and generation but are inherently limited by static pretraining data, resulting in factual inaccuracies and weak adaptability to new information. Retrieval-Augmented Generation (RAG) addresses…

In this paper, we present a novel integrated approach for keyphrase generation (KG). Unlike previous works which are purely extractive or generative, we first propose a new multi-task learning framework that jointly learns an extractive…

Large language models (LLMs) typically enhance their performance through either the retrieval of semantically similar information or the improvement of their reasoning capabilities. However, a significant challenge remains in effectively…

Ranking has always been one of the top concerns in information retrieval research. For decades, lexical matching signal has dominated the ad-hoc retrieval process, but it also has inherent defects, such as the vocabulary mismatch problem.…

Large language models (LLMs) exhibit remarkable generative capabilities but often suffer from hallucinations. Retrieval-augmented generation (RAG) offers an effective solution by incorporating external knowledge, but existing methods still…

Information retrieval aims to find information that meets users' needs from the corpus. Different needs correspond to different IR tasks such as document retrieval, open-domain question answering, retrieval-based dialogue, etc., while they…

In book search, relevant book information should be returned in response to a query. Books contain complex, multi-faceted information such as metadata, outlines, and main text, where the outline provides hierarchical information between…

Knowledge retrieval is one of the major challenges in building a knowledge-grounded dialogue system. A common method is to use a neural retriever with a distributed approximate nearest-neighbor database to quickly find the relevant…

Kernel selection plays a central role in determining the performance of Gaussian Process (GP) models, as the chosen kernel determines both the inductive biases and prior support of functions under the GP prior. This work addresses the…

Researchers have investigated the potential of leveraging pre-trained language models, such as CodeBERT, to enhance source code-related tasks. Previous methodologies have relied on CodeBERT's '[CLS]' token as the embedding representation of…

Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the adoption of pre-trained language models (such as BERT) has led…

While generative modeling has become prevalent across numerous research fields, its integration into the realm of image retrieval remains largely unexplored and underjustified. In this paper, we present a novel methodology, reframing image…

Semi-supervised learning through deep generative models and multi-lingual pretraining techniques have orchestrated tremendous success across different areas of NLP. Nonetheless, their development has happened in isolation, while the…