相关论文: HiNS: Hierarchical Negative Sampling for More Comp…

Inspired by recent findings on the fractal geometry of language, we introduce Recursive INference Scaling (RINS) as a complementary, plug-in recipe for scaling inference time in language and multimodal systems. RINS is a particular form of…

Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. Recently, to alleviate expensive data collection, co-occurring pairs from the Internet are automatically harvested for training. However, it…

Constructing memory from users' long-term conversations overcomes LLMs' contextual limitations and enables personalized interactions. Recent studies focus on hierarchical memory to model users' multi-granular behavioral patterns via…

Enterprise search systems often struggle to retrieve accurate, domain-specific information due to semantic mismatches and overlapping terminologies. These issues can degrade the performance of downstream applications such as knowledge…

This paper introduces Ranking Info Noise Contrastive Estimation (RINCE), a new member in the family of InfoNCE losses that preserves a ranked ordering of positive samples. In contrast to the standard InfoNCE loss, which requires a strict…

Building models of natural language processing (NLP) is challenging in low-resource scenarios where only limited data are available. Optimization-based meta-learning algorithms achieve promising results in low-resource scenarios by adapting…

Accurate syntactic representations are essential for robust generalization in natural language. Recent work has found that pre-training can teach language models to rely on hierarchical syntactic features - as opposed to incorrect linear…

Contrastive learning has become pivotal in unsupervised representation learning, with frameworks like Momentum Contrast (MoCo) effectively utilizing large negative sample sets to extract discriminative features. However, traditional…

The recent advance in neural network architecture and training algorithms have shown the effectiveness of representation learning. The neural network-based models generate better representation than the traditional ones. They have the…

The organization of latent token representations plays a crucial role in determining the stability, generalization, and contextual consistency of language models, yet conventional approaches to embedding refinement often rely on parameter…

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

Much effort has been devoted to evaluate whether multi-task learning can be leveraged to learn rich representations that can be used in various Natural Language Processing (NLP) down-stream applications. However, there is still a lack of…

Data selection is critical for enhancing the performance of language models, particularly when aligning training datasets with a desired target distribution. This study explores the effects of different data selection methods and feature…

This study investigates the use of unsupervised word embeddings and sequence features for sample representation in an active learning framework built to extract clinical concepts from clinical free text. The objective is to further reduce…

Memory embeddings are crucial for memory-augmented systems, such as OpenClaw, but their evaluation is underexplored in current text embedding benchmarks, which narrowly focus on traditional passage retrieval and fail to assess models'…

This paper investigates algorithmic bias in language-based models for automated depression detection, focusing on socio-demographic disparities related to gender and race/ethnicity. Models trained using deep neural networks (DNN) based…

One of the challenges in contrastive learning is the selection of appropriate \textit{hard negative} examples, in the absence of label information. Random sampling or importance sampling methods based on feature similarity often lead to…

Automatic Speech Scoring (ASS) is the computer-assisted evaluation of a candidate's speaking proficiency in a language. ASS systems face many challenges like open grammar, variable pronunciations, and unstructured or semi-structured…

Retrieval-augmented language models (RALMs) hold promise to produce language understanding systems that are are factual, efficient, and up-to-date. An important desideratum of RALMs, is that retrieved information helps model performance…

Cross-modal video-text retrieval, a challenging task in the field of vision and language, aims at retrieving corresponding instance giving sample from either modality. Existing approaches for this task all focus on how to design encoding…