Related papers: Task-aware Retrieval with Instructions
Large language models are able to perform a task by conditioning on a few input-output demonstrations - a paradigm known as in-context learning. We show that language models can explicitly infer an underlying task from a few demonstrations…
Exclusion is an important and universal linguistic skill that humans use to express what they do not want. However, in information retrieval community, there is little research on exclusionary retrieval, where users express what they do not…
Large pre-trained language models help to achieve state of the art on a variety of natural language processing (NLP) tasks, nevertheless, they still suffer from forgetting when incrementally learning a sequence of tasks. To alleviate this…
Temporal Information Retrieval (TIR) is a critical yet unresolved task for modern search systems, retrieving documents that not only satisfy a query's information need but also adhere to its temporal constraints. This task is shaped by two…
We present an end-to-end differentiable training method for retrieval-augmented open-domain question answering systems that combine information from multiple retrieved documents when generating answers. We model retrieval decisions as…
Interactive video retrieval is a cooperative process between humans and retrieval systems. Large-scale evaluation campaigns, however, often overlook human factors, such as the effects of perception, attention, and memory, when assessing…
Existing referring understanding tasks tend to involve the detection of a single text-referred object. In this paper, we propose a new and general referring understanding task, termed referring multi-object tracking (RMOT). Its core idea is…
The machine reading comprehension (MRC) of user manuals has huge potential in customer service. However, current methods have trouble answering complex questions. Therefore, we introduce the Knowing-how & Knowing-that task that requires the…
The Recherche Appliquee en Linguistique Informatique (RALI) team participated in the 2024 TREC Interactive Knowledge Assistance (iKAT) Track. In personalized conversational search, effectively capturing a user's complex search intent…
Inspirational quotes from famous individuals are often used to convey thoughts in news articles, essays, and everyday conversations. In this paper, we propose a novel context-based quote extraction system that aims to extract the most…
Prompt tuning attempts to update few task-specific parameters in pre-trained models. It has achieved comparable performance to fine-tuning of the full parameter set on both language understanding and generation tasks. In this work, we study…
Despite recent progress, learning new tasks through language instructions remains an extremely challenging problem. On the ALFRED benchmark for task learning, the published state-of-the-art system only achieves a task success rate of less…
In this paper, we present Tetris, a new task of Goal-Oriented Script Completion. Unlike previous work, it considers a more realistic and general setting, where the input includes not only the goal but also additional user context, including…
While interests in tabular deep learning has significantly grown, conventional tree-based models still outperform deep learning methods. To narrow this performance gap, we explore the innovative retrieval mechanism, a methodology that…
The exponential growth of volume, variety and velocity of data is raising the need for investigations of automated or semi-automated ways to extract useful patterns from the data. It requires deep expert knowledge and extensive…
Named entity recognition (NER) has been studied extensively and the earlier algorithms were based on sequence labeling like Hidden Markov Models (HMM) and conditional random fields (CRF). These were followed by neural network based deep…
Multi-label learning has emerged as a crucial paradigm in data analysis, addressing scenarios where instances are associated with multiple class labels simultaneously. With the growing prevalence of multi-label data across diverse…
Search agents powered by large language models can autonomously decompose queries, retrieve information, and synthesize answers through multi-step reasoning. However, the rapid growth of training methods has outpaced controlled comparison:…
Domain-specific intelligence demands specialized knowledge and sophisticated reasoning for problem-solving, posing significant challenges for large language models (LLMs) that struggle with knowledge hallucination and inadequate reasoning…
Tool learning aims to extend the capabilities of large language models (LLMs) with external tools. A major challenge in tool learning is how to support a large number of tools, including unseen tools. To address this challenge, previous…