Related papers: A Domain Generalization Perspective on Listwise Co…

Passage re-ranking is to obtain a permutation over the candidate passage set from retrieval stage. Re-rankers have been boomed by Pre-trained Language Models (PLMs) due to their overwhelming advantages in natural language understanding.…

Domain adaptation approaches seek to learn from a source domain and generalize it to an unseen target domain. At present, the state-of-the-art unsupervised domain adaptation approaches for subjective text classification problems leverage…

Ranking passages by prompting a large language model (LLM) can achieve promising performance in modern information retrieval (IR) systems. A common approach to sort the ranking list is by prompting LLMs for a pairwise or setwise comparison…

Retrieval-Augmented Language Modeling (RALM) methods, which condition a language model (LM) on relevant documents from a grounding corpus during generation, were shown to significantly improve language modeling performance. In addition,…

Domain generalization is a critical challenge for machine learning systems. Prior domain generalization methods focus on extracting domain-invariant features across several stationary domains to enable generalization to new domains.…

Large language models (LLMs) have shown impressive capabilities across various tasks, but their performance on domain-specific tasks remains limited. While methods like retrieval augmented generation and fine-tuning can help to address…

Interest in larger-context neural machine translation, including document-level and multi-modal translation, has been growing. Multiple works have proposed new network architectures or evaluation schemes, but potentially helpful context is…

In web search and recommendation systems, user clicks are widely used to train ranking models. However, click data is heavily biased, i.e., users tend to click higher-ranked items (position bias), choose only what was shown to them…

Tabular data, a fundamental data format in machine learning, is predominantly utilized in competitions and real-world applications. The performance of tabular models--such as gradient boosted decision trees and neural networks--can vary…

Retrieval-Augmented Generation (RAG) is a framework for grounding Large Language Models (LLMs) in external, up-to-date information. However, recent advancements in context window size allow LLMs to process inputs of up to 128K tokens or…

Generalization capability to unseen domains is crucial for machine learning models when deploying to real-world conditions. We investigate the challenging problem of domain generalization, i.e., training a model on multi-domain source data…

Deep Neural Networks (DNNs) suffer from domain shift when the test dataset follows a distribution different from the training dataset. Domain generalization aims to tackle this issue by learning a model that can generalize to unseen…

Global sentence information is crucial for sequence labeling tasks, where each word in a sentence must be assigned a label. While BiLSTM models are widely used, they often fail to capture sufficient global context for inner words. Previous…

Text ranking is a critical task in information retrieval. Recent advances in pre-trained language models (PLMs), especially large language models (LLMs), present new opportunities for applying them to text ranking. While supervised…

Despite impressive performance as evaluated on i.i.d. holdout data, deep neural networks depend heavily on superficial statistics of the training data and are liable to break under distribution shift. For example, subtle changes to the…

Continual learning has gained increasing importance as it facilitates the acquisition and refinement of scalable knowledge and skills in language models. However, existing methods typically encounter strict limitations and challenges in…

Deep neural networks have achieved significant improvements in information retrieval (IR). However, most existing models are computational costly and can not efficiently scale to long documents. This paper proposes a novel End-to-End neural…

Recommender systems are indispensable in the realm of online applications, and sequential recommendation has enjoyed considerable prevalence due to its capacity to encapsulate the dynamic shifts in user interests. However, previous…

Planning - the ability to analyze the structure of a problem in the large and decompose it into interrelated subproblems - is a hallmark of human intelligence. While deep reinforcement learning (RL) has shown great promise for solving…

Domain generalization refers to the problem where we aim to train a model on data from a set of source domains so that the model can generalize to unseen target domains. Naively training a model on the aggregate set of data (pooled from all…