Related papers: Data Whisperer: Efficient Data Selection for Task-…

A major limitation of prompt tuning is its dependence on large labeled training datasets. Under few-shot learning settings, prompt tuning lags far behind full-model fine-tuning, limiting its scope of application. In this paper, we leverage…

In this work, we evaluate 10 open-source instructed LLMs on four representative code comprehension and generation tasks. We have the following main findings. First, for the zero-shot setting, instructed LLMs are very competitive on code…

Effective data selection is critical for efficient training of modern Large Language Models (LLMs). This paper introduces Influence Distillation, a novel, mathematically-justified framework for data selection that employs second-order…

The performance of large language models in domain-specific tasks necessitates fine-tuning, which is computationally expensive and technically challenging. This paper focuses on parameter-efficient fine-tuning using soft prompting, a…

Large language models (LLMs) are initially pretrained for broad capabilities and then finetuned with instruction-following datasets to improve their performance in interacting with humans. Despite advances in finetuning, a standardized…

The performance of finetuned large language models (LLMs) hinges critically on the composition of the training mixture. However, selecting an optimal blend of task datasets remains a largely manual, heuristic driven process, with…

Large Language Models have become the de facto approach to sequence-to-sequence text generation tasks, but for specialized tasks/domains, a pretrained LLM lacks specific capabilities to produce accurate or well-formatted responses.…

Reward Models (RMs) are crucial to aligning large language models (LLMs), but the degree to which an RM specialized to one task (e.g. writing) generalizes to new tasks (e.g. math) is often not known a priori, often making using only one…

Recent research has demonstrated the feasibility of training efficient intent detectors based on pre-trained language model~(PLM) with limited labeled data. However, deploying these detectors in resource-constrained environments such as…

Data selection for fine-tuning large language models (LLMs) aims to choose a high-quality subset from existing datasets, allowing the trained model to outperform baselines trained on the full dataset. However, the expanding body of research…

With the capabilities of understanding and executing natural language instructions, Large language models (LLMs) can potentially act as a powerful tool for textual data augmentation. However, the quality of augmented data depends heavily on…

Despite the impressive capabilities of large language models (LLMs), their performance on information extraction tasks is still not entirely satisfactory. However, their remarkable rewriting capabilities and extensive world knowledge offer…

Fine tuning has been regarded as a de facto approach for adapting large language models (LLMs) to downstream tasks, but the high training memory consumption inherited from LLMs makes this process inefficient. Among existing memory efficient…

Whisper has become the de-facto encoder for extracting general-purpose audio features in large audio-language models, where a 30-second clip is typically represented by 1500 frame features projected into an LLM. In contrast, audio-text…

Recent advancements in large language models (LLMs) have significantly improved code generation and program comprehension, accelerating the evolution of software engineering. Current methods primarily enhance model performance by leveraging…

Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs that…

As large language models (LLMs) show impressive performance on complex tasks, they still struggle with longer contextual understanding and high computational costs. To balance efficiency and quality, we introduce LLMSteer, a…

Traditionally, success in multilingual machine translation can be attributed to three key factors in training data: large volume, diverse translation directions, and high quality. In the current practice of fine-tuning large language models…

Fine-tuning Multimodal Large Language Models (MLLMs) on task-specific data is an effective way to improve performance on downstream applications. However, such adaptation often leads to a degradation in generalization on pretrained tasks, a…

Large-scale, weakly-supervised speech recognition models, such as Whisper, have demonstrated impressive results on speech recognition across domains and languages. However, their application to long audio transcription via buffered or…