Related papers: Thermodynamic Focusing for Inference-Time Search: …

Transformer-based models have been widely adopted for sentiment analysis tasks due to their exceptional ability to capture contextual information. However, these methods often exhibit suboptimal accuracy in certain scenarios. By analyzing…

Obtaining multiple meaningfully diverse, high quality samples from Large Language Models for a fixed prompt remains an open challenge. Current methods for increasing diversity often only operate at the token-level, paraphrasing the same…

This work aims at solving the problems with intractable sparsity-inducing norms that are often encountered in various machine learning tasks, such as multi-task learning, subspace clustering, feature selection, robust principal component…

Large language models are ubiquitous in natural language processing because they can adapt to new tasks without retraining. However, their sheer scale and complexity present unique challenges and opportunities, prompting researchers and…

Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training…

Inverse classification uses an induced classifier as a queryable oracle to guide test instances towards a preferred posterior class label. The result produced from the process is a set of instance-specific feature perturbations, or…

Optimization algorithms appear in the core calculations of numerous Artificial Intelligence (AI) and Machine Learning methods, as well as Engineering and Business applications. Following recent works on the theoretical deficiencies of AI, a…

Motivated by the need for rigorous and scalable evaluation of large language models, we study contextual preference inference for pairwise comparison functionals of context-dependent preference score functions across domains. Focusing on…

Machine learning models are prone to capturing the spurious correlations between non-causal attributes and classes, with counterfactual data augmentation being a promising direction for breaking these spurious associations. However,…

In-context learning (ICL) of large language models (LLMs) has attracted increasing attention in the community where LLMs make predictions only based on instructions augmented with a few examples. Existing example selection methods for ICL…

With the rising popularity of Transformer-based large language models (LLMs), reducing their high inference costs has become a significant research focus. One effective approach is to compress the long input contexts. Existing methods…

Augmenting large language models (LLMs) with external retrieval has become a standard method to address their inherent knowledge cutoff limitations. However, traditional retrieval-augmented generation methods employ static, pre-inference…

Context propagation remains a central challenge in language model architectures, particularly in tasks requiring the retention of long-range dependencies. Conventional attention mechanisms, while effective in many applications, exhibit…

Generative models excel at synthesizing high-fidelity samples from complex data distributions, but they often violate hard constraints arising from physical laws or task specifications. A common remedy is to project intermediate samples…

Term weighting schemes often dominate the performance of many classifiers, such as kNN, centroid-based classifier and SVMs. The widely used term weighting scheme in text categorization, i.e., tf.idf, is originated from information retrieval…

In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models…

Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous…

Integrating multimodal knowledge for abstractive summarization task is a work-in-progress research area, with present techniques inheriting fusion-then-generation paradigm. Due to semantic gaps between computer vision and natural language…

Large Language Models (LLMs) have demonstrated remarkable efficiency in tackling various tasks based on human instructions, but studies reveal that they often struggle with tasks requiring reasoning, such as math or physics. This limitation…

Training deep neural networks is challenging when large and annotated datasets are unavailable. Extensive manual annotation of data samples is time-consuming, expensive, and error-prone, notably when it needs to be done by experts. To…