Related papers: Exploring the Representation Power of SPLADE Model…

Large Language Models (LLMs) excel at many tasks but struggle with ambiguous scenarios where multiple valid responses exist, often yielding unreliable results. Conversely, Small Language Models (SLMs) demonstrate robustness in such…

Keyphrases are capable of providing semantic metadata characterizing documents and producing an overview of the content of a document. Since keyphrase extraction is able to facilitate the management, categorization, and retrieval of…

Pre-trained Language Models (PLMs) are known to contain various kinds of knowledge. One method to infer relational knowledge is through the use of cloze-style prompts, where a model is tasked to predict missing subjects or objects.…

This paper seeks to combine dictionary learning and hierarchical image representation in a principled way. To make dictionary atoms capturing additional information from extended receptive fields and attain improved descriptive capacity, we…

Iterative data generation and model re-training can effectively align large language models(LLMs) to human preferences. The process of data sampling is crucial, as it significantly influences the success of policy improvement. Repeated…

Automatic Term Extraction (ATE) identifies domain-specific expressions that are crucial for downstream tasks such as machine translation and information retrieval. Although large language models (LLMs) have significantly advanced various…

The goal of information retrieval is to recommend a list of document candidates that are most relevant to a given query. Listwise learning trains neural retrieval models by comparing various candidates simultaneously on a large scale,…

Pretraining sentence encoders with language modeling and related unsupervised tasks has recently been shown to be very effective for language understanding tasks. By supplementing language model-style pretraining with further training on…

Recent studies have demonstrated the effectiveness of using large language language models (LLMs) in passage ranking. The listwise approaches, such as RankGPT, have become new state-of-the-art in this task. However, the efficiency of…

The Semantic Layered Embedding Diffusion (SLED) mechanism redefines the representation of hierarchical semantics within transformer-based architectures, enabling enhanced contextual consistency across a wide array of linguistic tasks. By…

The CLIP model has established itself as a cornerstone of large-scale retrieval systems. However, its performance often degrades under distributional shifts such as multilingual, long-form, or multimodal queries. To avoid the prohibitive…

Since the amount of information on the internet is growing rapidly, it is not easy for a user to find relevant information for his/her query. To tackle this issue, much attention has been paid to Automatic Document Summarization. The key…

Solving text classification in a weakly supervised manner is important for real-world applications where human annotations are scarce. In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision…

A common strategy in transfer learning is few shot fine-tuning, but its success is highly dependent on the quality of samples selected as training examples. Active learning methods such as uncertainty sampling and diversity sampling can…

Large language models~(LLMs) exhibit exceptional performance in language tasks, yet their auto-regressive inference is limited due to high computational requirements and is sub-optimal due to the exposure bias. Inspired by speculative…

Neural document ranking models perform impressively well due to superior language understanding gained from pre-training tasks. However, due to their complexity and large number of parameters, these (typically transformer-based) models are…

We consider the problem of learning overcomplete dictionaries in the context of sparse coding, where each sample selects a sparse subset of dictionary elements. Our main result is a strategy to approximately recover the unknown dictionary…

Large Language Models (LLMs) are traditionally viewed as black-box algorithms, therefore reducing trustworthiness and obscuring potential approaches to increasing performance on downstream tasks. In this work, we apply an effective LLM…

This paper revisits cluster-based retrieval that partitions the inverted index into multiple groups and skips the index partially at cluster and document levels during online inference using a learned sparse representation. It proposes an…

In this paper, we propose a semi-supervised dictionary learning method that uses both the information in labelled and unlabelled data and jointly trains a linear classifier embedded on the sparse codes. The manifold structure of the data in…