Related papers: Fennec: Fine-grained Language Model Evaluation and…
This work presents a new and simple approach for fine-tuning pretrained word embeddings for text classification tasks. In this approach, the class in which a term appears, acts as an additional contextual variable during the fine tuning…
Machine learning models are widely used for real-world applications, such as document analysis and vision. Constrained machine learning problems are problems where learned models have to both be accurate and respect constraints. For…
As large language models improve, there is increasing interest in techniques that leverage these models' capabilities to refine their own outputs. In this work, we introduce Shepherd, a language model specifically tuned to critique…
Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal perception capabilities, garnering significant attention. While numerous evaluation studies have emerged, assessing LVLMs both holistically…
Text-rich graphs, which exhibit rich textual information on nodes and edges, are prevalent across a wide range of real-world business applications. Large Language Models (LLMs) have demonstrated remarkable abilities in understanding text,…
Fused Deposition Modeling (FDM) is a widely used additive manufacturing (AM) technique valued for its flexibility and cost-efficiency, with applications in a variety of industries including healthcare and aerospace. Recent developments have…
Large Language Models (LLMs) have made remarkable progress, surpassing human performance on several benchmarks in domains such as mathematics and coding. A key driver of this progress has been the development of benchmark datasets. In…
Language model pre-training based on large corpora has achieved tremendous success in terms of constructing enriched contextual representations and has led to significant performance gains on a diverse range of Natural Language…
The expressive and computationally inexpensive bipartite Graph Neural Networks (GNN) have been shown to be an important component of deep learning based Mixed-Integer Linear Program (MILP) solvers. Recent works have demonstrated the…
It has become standard to solve NLP tasks by fine-tuning pre-trained language models (LMs), especially in low-data settings. There is minimal theoretical understanding of empirical success, e.g., why fine-tuning a model with $10^8$ or more…
Most state-of-the-art models in natural language processing (NLP) are neural models built on top of large, pre-trained, contextual language models that generate representations of words in context and are fine-tuned for the task at hand.…
Accurate document retrieval is crucial for the success of retrieval-augmented generation (RAG) applications, including open-domain question answering and code completion. While large language models (LLMs) have been employed as dense…
Grammatical Error Correction (GEC) faces a critical challenge concerning explainability, notably when GEC systems are designed for language learners. Existing research predominantly focuses on explaining grammatical errors extracted in…
Large Language Models (LLMs) are being used more and more extensively for automated evaluation in various scenarios. Previous studies have attempted to fine-tune open-source LLMs to replicate the evaluation explanations and judgments of…
Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…
Learning vector representation for words is an important research field which may benefit many natural language processing tasks. Two limitations exist in nearly all available models, which are the bias caused by the context definition and…
Structured reasoning can improve the inference performance of large language models (LLMs), but it also introduces computational cost and control constraints. When additional reasoning structure helps, and when it instead reduces efficiency…
The text encoder is a critical component of text-to-image and text-to-video diffusion models, fundamentally determining the semantic fidelity of the generated content. However, its development has been hindered by two major challenges: the…
As AI models tackle increasingly complex problems, ensuring reliable human oversight becomes more challenging due to the difficulty of verifying solutions. Approaches to scaling AI supervision include debate, in which two agents engage in…
Large language models (LLMs) call for extension of context to handle many critical applications. However, the existing approaches are prone to expensive costs and inferior quality of context extension. In this work, we proposeExtensible…