Self-training Large Language Models through Knowledge Detection
- URL: http://arxiv.org/abs/2406.11275v1
- Date: Mon, 17 Jun 2024 07:25:09 GMT
- Title: Self-training Large Language Models through Knowledge Detection
- Authors: Wei Jie Yeo, Teddy Ferdinan, Przemyslaw Kazienko, Ranjan Satapathy, Erik Cambria,
- Abstract summary: Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks.
This paper explores a self-training paradigm, where the LLM autonomously curates its own labels and selectively trains on unknown data samples.
Empirical evaluations demonstrate significant improvements in reducing hallucination in generation across multiple subjects.
- Score: 26.831873737733737
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks. This paper explores a self-training paradigm, where the LLM autonomously curates its own labels and selectively trains on unknown data samples identified through a reference-free consistency method. Empirical evaluations demonstrate significant improvements in reducing hallucination in generation across multiple subjects. Furthermore, the selective training framework mitigates catastrophic forgetting in out-of-distribution benchmarks, addressing a critical limitation in training LLMs. Our findings suggest that such an approach can substantially reduce the dependency on large labeled datasets, paving the way for more scalable and cost-effective language model training.
Related papers
- PISTOL: Dataset Compilation Pipeline for Structural Unlearning of LLMs [31.16117964915814]
Machine unlearning, which seeks to erase specific data stored in the pre-trained or fine-tuned models, has emerged as a crucial protective measure for LLMs.
To facilitate the development of structural unlearning methods, we propose PISTOL, a pipeline for compiling multi-scenario datasets.
We conduct benchmarks with four distinct unlearning methods on both Llama2-7B and Mistral-7B models.
arXiv Detail & Related papers (2024-06-24T17:22:36Z) - Enhancing Text Classification through LLM-Driven Active Learning and Human Annotation [2.0411082897313984]
This study introduces a novel methodology that integrates human annotators and Large Language Models.
The proposed framework integrates human annotation with the output of LLMs, depending on the model uncertainty levels.
The empirical results show a substantial decrease in the costs associated with data annotation while either maintaining or improving model accuracy.
arXiv Detail & Related papers (2024-06-17T21:45:48Z) - Unlearning with Control: Assessing Real-world Utility for Large Language Model Unlearning [97.2995389188179]
Recent research has begun to approach large language models (LLMs) unlearning via gradient ascent (GA)
Despite their simplicity and efficiency, we suggest that GA-based methods face the propensity towards excessive unlearning.
We propose several controlling methods that can regulate the extent of excessive unlearning.
arXiv Detail & Related papers (2024-06-13T14:41:00Z) - CLAIM Your Data: Enhancing Imputation Accuracy with Contextual Large Language Models [0.18416014644193068]
This paper introduces the Contextual Language model for Accurate Imputation Method (CLAIM)
Unlike traditional imputation methods, CLAIM utilizes contextually relevant natural language descriptors to fill missing values.
Our evaluations across diverse datasets and missingness patterns reveal CLAIM's superior performance over existing imputation techniques.
arXiv Detail & Related papers (2024-05-28T00:08:29Z) - Take the Bull by the Horns: Hard Sample-Reweighted Continual Training
Improves LLM Generalization [165.98557106089777]
A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data.
Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets.
We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
arXiv Detail & Related papers (2024-02-22T04:10:57Z) - Querying Easily Flip-flopped Samples for Deep Active Learning [63.62397322172216]
Active learning is a machine learning paradigm that aims to improve the performance of a model by strategically selecting and querying unlabeled data.
One effective selection strategy is to base it on the model's predictive uncertainty, which can be interpreted as a measure of how informative a sample is.
This paper proposes the it least disagree metric (LDM) as the smallest probability of disagreement of the predicted label.
arXiv Detail & Related papers (2024-01-18T08:12:23Z) - LLMaAA: Making Large Language Models as Active Annotators [32.57011151031332]
We propose LLMaAA, which takes large language models as annotators and puts them into an active learning loop to determine what to annotate efficiently.
We conduct experiments and analysis on two classic NLP tasks, named entity recognition and relation extraction.
With LLMaAA, task-specific models trained from LLM-generated labels can outperform the teacher within only hundreds of annotated examples.
arXiv Detail & Related papers (2023-10-30T14:54:15Z) - From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning [52.257422715393574]
We introduce a self-guided methodology for Large Language Models (LLMs) to autonomously discern and select cherry samples from open-source datasets.
Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model's expected responses and its intrinsic generation capability.
arXiv Detail & Related papers (2023-08-23T09:45:29Z) - Bring Your Own Data! Self-Supervised Evaluation for Large Language
Models [52.15056231665816]
We propose a framework for self-supervised evaluation of Large Language Models (LLMs)
We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence.
We find strong correlations between self-supervised and human-supervised evaluations.
arXiv Detail & Related papers (2023-06-23T17:59:09Z) - To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis [50.31589712761807]
Large language models (LLMs) are notoriously token-hungry during pre-training, and high-quality text data on the web is approaching its scaling limit for LLMs.
We investigate the consequences of repeating pre-training data, revealing that the model is susceptible to overfitting.
Second, we examine the key factors contributing to multi-epoch degradation, finding that significant factors include dataset size, model parameters, and training objectives.
arXiv Detail & Related papers (2023-05-22T17:02:15Z) - Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM [31.25193238045053]
We introduce a novel method, namely GenCo, which leverages the strong generative power of large language models to assist in training a smaller language model.
In our method, an LLM plays an important role in the self-training loop of a smaller model in two important ways.
It helps crafting additional high-quality training pairs, by rewriting input texts conditioned on predicted labels.
arXiv Detail & Related papers (2023-04-24T07:35:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.