Related papers: Annotating Data for Fine-Tuning a Neural Ranker? C…

The in-context learning ability of large language models (LLMs) enables them to generalize to novel downstream tasks with relatively few labeled examples. However, they require enormous computational resources to be deployed. Alternatively,…

Parameter-efficient (PE) methods (like Prompts or Adapters) for adapting pre-trained language models (PLM) to downstream tasks have been popular recently. However, hindrances still prevent these methods from reaching their full potential.…

Aligning large language models (LLMs) to human preferences is a crucial step in building helpful and safe AI tools, which usually involve training on supervised datasets. Popular algorithms such as Direct Preference Optimization (DPO) rely…

Large language models (LLMs) often develop learned mechanisms specialized to specific datasets, such as reliance on domain-specific correlations, which yield high-confidence predictions without generalizable reasoning. While beneficial in…

Large Language Models (LLMs) exhibit remarkable text classification capabilities, excelling in zero- and few-shot learning (ZSL and FSL) scenarios. However, since they are trained on different datasets, performance varies widely across…

The integration of large language models (LLMs) into automated algorithm design has shown promising potential. A prevalent approach embeds LLMs within search routines to iteratively generate and refine candidate algorithms. However, most…

Preference learning is critical for aligning large language models (LLMs) with human values, with the quality of preference datasets playing a crucial role in this process. While existing metrics primarily assess data quality based on…

Specializing LLMs in various domain-specific tasks has emerged as a critical step towards achieving high performance. However, the construction and annotation of datasets in specific domains are always very costly. Apart from using superior…

Deep learning has achieved widespread success in medical image analysis, leading to an increasing demand for large-scale expert-annotated medical image datasets. Yet, the high cost of annotating medical images severely hampers the…

The rise of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) has rapidly increased the need for high-quality, curated information retrieval datasets. These datasets, however, are currently created with off-the-shelf…

This paper explores pruning attention heads as a post-processing bias mitigation method for large language models (LLMs). Modern AI systems such as LLMs are expanding into sensitive social contexts where fairness concerns become especially…

Reinforcement learning (RL) is a key post-pretraining step for aligning large language models (LLMs) with complex tasks and human preferences. While it is often assumed that RL fine-tuning requires updating most of a model's parameters, we…

The rapid expansion of Large Language Models (LLMs) has posed significant challenges regarding the computational resources required for fine-tuning and deployment. Recent advancements in low-rank adapters have demonstrated their efficacy in…

The advent of large language models (LLMs) capable of producing general-purpose representations lets us revisit the practicality of deep active learning (AL): By leveraging frozen LLM embeddings, we can mitigate the computational costs of…

Memory, additional information beyond the training of large language models (LLMs), is crucial to various real-world applications, such as personal assistant. The two mainstream solutions to incorporate memory into the generation process…

Adopting a two-stage paradigm of pretraining followed by fine-tuning, Pretrained Language Models (PLMs) have achieved substantial advancements in the field of natural language processing. However, in real-world scenarios, data labels are…

We consider the task of few-shot intent detection, which involves training a deep learning model to classify utterances based on their underlying intents using only a small amount of labeled data. The current approach to address this…

Named entity recognition (NER) aims to identify mentions of named entities in an unstructured text and classify them into predefined named entity classes. While deep learning-based pre-trained language models help to achieve good predictive…

Modern LLMs inherit strong priors from web-scale pretraining, which can limit the headroom of post-training data-selection strategies. While Active Preference Learning (APL) seeks to optimize query efficiency in online Direct Preference…

Instruction tuning is a vital step of training large language models (LLMs), so how to enhance the effect of instruction tuning has received increased attention. Existing works indicate that the quality of the dataset is more crucial than…