Related papers: Efficient Knowledge Injection in LLMs via Self-Dis…
Large language models (LLMs) often struggle to provide up-to-date information due to their one-time training and the constantly evolving nature of the world. To keep LLMs current, existing approaches typically involve continued pre-training…
Large Language Models (LLMs) have shown promising performance in text-to-SQL, which involves translating natural language questions into SQL queries. However, current text-to-SQL LLMs are computationally expensive and challenging to deploy…
Large Language Models (LLMs) have the unique capability to understand and generate human-like text from input queries. When fine-tuned, these models show enhanced performance on domain-specific queries. OpenAI highlights the process of…
Distilling large language models (LLMs) typically involves transferring the teacher model's responses through supervised fine-tuning (SFT). However, this approach neglects the potential to distill both data (output content) and reward…
Modern Natural Language Generation (NLG) models come with massive computational and storage requirements. In this work, we study the potential of compressing them, which is crucial for real-world applications serving millions of users. We…
Causality detection and mining are important tasks in information retrieval due to their enormous use in information extraction, and knowledge graph construction. To solve these tasks, in existing literature there exist several solutions --…
Large language models (LLMs) are often used in environments where facts evolve, yet factual knowledge updates via fine-tuning on unstructured text often suffer from 1) reliance on compute-heavy paraphrasing augmentation and 2) the reversal…
The deployment of large language models (LLMs) faces considerable challenges concerning resource constraints and inference efficiency. Recent research has increasingly focused on smaller, task-specific models enhanced by distilling…
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating additional information from retrieval. However, studies have shown that LLMs still face challenges in effectively using the retrieved information,…
Retrieval Augmented Generation (RAG) frameworks have shown significant promise in leveraging external knowledge to enhance the performance of large language models (LLMs). However, conventional RAG methods often retrieve documents based…
Deploying large language models (LLMs) is challenging because they are memory inefficient and compute-intensive for practical applications. In reaction, researchers train smaller task-specific models by either finetuning with human labels…
LLMs are increasingly explored for bundle generation, thanks to their reasoning capabilities and knowledge. However, deploying large-scale LLMs introduces significant efficiency challenges, primarily high computational costs during…
The knowledge base in a retrieval-augmented generation (RAG) system is typically assembled once and never revised, even though the facts a query requires are often fragmented across documents and buried in irrelevant content. We argue that…
Recent language models have shown remarkable performance on natural language understanding (NLU) tasks. However, they are often sub-optimal when faced with ambiguous samples that can be interpreted in multiple ways, over-confidently…
Knowledge distillation (KD) has become a widely adopted approach for compressing large language models (LLMs) to reduce computational costs and memory footprints. However, the availability of complex teacher models is a prerequisite for…
Transferring the reasoning capability from stronger large language models (LLMs) to smaller ones has been quite appealing, as smaller LLMs are more flexible to deploy with less expense. Among the existing solutions, knowledge distillation…
Large Language models (LLMs) have demonstrated impressive in-context learning (ICL) capabilities, where a LLM makes predictions for a given test input together with a few input-output pairs (demonstrations). Nevertheless, the inclusion of…
Standard Knowledge Distillation (KD) compresses Large Language Models (LLMs) by optimizing final outputs, yet it typically treats the teacher's intermediate layer's thought process as a black box. While feature-based distillation attempts…
We tackle the challenging issue of aggressive fine-tuning encountered during the process of transfer learning of pre-trained language models (PLMs) with limited labeled downstream data. This problem primarily results in a decline in…
Distilling robust reasoning capabilities from large language models (LLMs) into smaller, computationally efficient student models remains an unresolved challenge. Despite recent advances, distilled models frequently suffer from superficial…