Related papers: Improving information retrieval through correspond…

Mined Semantic Analysis (MSA) is a novel concept space model which employs unsupervised learning to generate semantic representations of text. MSA represents textual structures (terms, phrases, documents) as a Bag of Concepts (BoC) where…

Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments. Low-rank Adaptation…

Reference-based image super-resolution (RefSR) has shown promising success in recovering high-frequency details by utilizing an external reference image (Ref). In this task, texture details are transferred from the Ref image to the…

Large Language Models (LLMs) have significantly impacted many facets of natural language processing and information retrieval. Unlike previous encoder-based approaches, the enlarged context window of these generative models allows for…

Contrastive learning has shown effectiveness in improving sequential recommendation models. However, existing methods still face challenges in generating high-quality contrastive pairs: they either rely on random perturbations that corrupt…

Large Vision Language Models (LVLMs) achieve great performance on visual-language reasoning tasks, however, the black-box nature of LVLMs hinders in-depth research on the reasoning mechanism. As all images need to be converted into image…

Distributed LLM serving systems optimize per-request latency and throughput. However, under long-context workloads, inference accuracy becomes more variable. When incorrect responses trigger retries, accuracy directly translates into…

Second language acquisition (SLA) modeling is to predict whether second language learners could correctly answer the questions according to what they have learned. It is a fundamental building block of the personalized learning system and…

Recent studies have demonstrated that large language models (LLMs) exhibit significant biases in evaluation tasks, particularly in preferentially rating and favoring self-generated content. However, the extent to which this bias manifests…

Latent semantic similarity (LSS) is a measure of the similarity of information exchanges in a conversation. Challenging the assumption that higher LSS bears more positive psychological meaning, we propose that this association might depend…

Direct alignment algorithms (DAAs), such as direct preference optimization (DPO), have become popular alternatives for Reinforcement Learning from Human Feedback (RLHF) due to their simplicity, efficiency, and stability. However, the…

Correspondence analysis (CA) is a popular technique to visualize the relationship between two categorical variables. CA uses the data from a two-way contingency table and is affected by the presence of outliers. The supplementary points…

Variables in many massive high-dimensional data sets are structured, arising for example from measurements on a regular grid as in imaging and time series or from spatial-temporal measurements as in climate studies. Classical multivariate…

We propose MESA and DMESA as novel feature matching methods, which utilize Segment Anything Model (SAM) to effectively mitigate matching redundancy. The key insight of our methods is to establish implicit-semantic area matching prior to…

Reducing the likelihood of generating harmful and toxic output is an essential task when aligning large language models (LLMs). Existing methods mainly rely on training an external reward model (i.e., another language model) or fine-tuning…

The scalability of statistical estimators is of increasing importance in modern applications. One approach to implementing scalable algorithms is to compress data into a low dimensional latent space using dimension reduction methods. In…

We present a supervised dimensionality reduction technique called Convex Linear Discriminant Analysis (ConvexLDA). The proposed model optimizes a multi-objective cost function by balancing two complementary terms. The first term pulls the…

A systematic, reliable, and low-cost evaluation of Conversational Information Access (CIA) systems remains an open challenge. Existing reference-based evaluation methods are proven insufficient for evaluating the dynamic nature of…

Legal text classification is a fundamental NLP task in the legal domain. Benchmark datasets in this area often exhibit a long-tail label distribution, where many labels are underrepresented, leading to poor model performance on rare…

Despite large successes of recent language models on diverse tasks, they suffer from severe performance degeneration in low-resource settings with limited training data available. Many existing works tackle this problem by generating…