A Framework for Fine-Tuning LLMs using Heterogeneous Feedback
- URL: http://arxiv.org/abs/2408.02861v1
- Date: Mon, 5 Aug 2024 23:20:32 GMT
- Title: A Framework for Fine-Tuning LLMs using Heterogeneous Feedback
- Authors: Ryan Aponte, Ryan A. Rossi, Shunan Guo, Franck Dernoncourt, Tong Yu, Xiang Chen, Subrata Mitra, Nedim Lipka,
- Abstract summary: We present a framework for fine-tuning large language models (LLMs) using heterogeneous feedback.
First, we combine the heterogeneous feedback data into a single supervision format, compatible with methods like SFT and RLHF.
Next, given this unified feedback dataset, we extract a high-quality and diverse subset to obtain performance increases.
- Score: 69.51729152929413
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large language models (LLMs) have been applied to a wide range of tasks, including text summarization, web navigation, and chatbots. They have benefitted from supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) following an unsupervised pretraining. These datasets can be difficult to collect, limited in scope, and vary in sample quality. Additionally, datasets can vary extensively in supervision format, from numerical to binary as well as multi-dimensional with many different values. We present a framework for fine-tuning LLMs using heterogeneous feedback, which has two main components. First, we combine the heterogeneous feedback data into a single supervision format, compatible with methods like SFT and RLHF. Next, given this unified feedback dataset, we extract a high-quality and diverse subset to obtain performance increases potentially exceeding the full dataset. We conduct extensive experiments to understand the effectiveness of these techniques for incorporating heterogeneous feedback, and demonstrate improvements from using a high-quality and diverse subset of the data. We find that our framework is able to improve models in multiple areas simultaneously, such as in instruction following and bias reduction.
Related papers
- Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data [36.277423093218275]
We study the role of data diversity in enhancing the overall abilities of large language models (LLMs)
We propose a new method that gives the LLM a dual identity: an output model to cognitively probe and select data based on diversity reward, as well as an input model to be tuned with the selected data.
arXiv Detail & Related papers (2025-02-05T17:21:01Z) - Empowering Large Language Models in Wireless Communication: A Novel Dataset and Fine-Tuning Framework [81.29965270493238]
We develop a specialized dataset aimed at enhancing the evaluation and fine-tuning of large language models (LLMs) for wireless communication applications.
The dataset includes a diverse set of multi-hop questions, including true/false and multiple-choice types, spanning varying difficulty levels from easy to hard.
We introduce a Pointwise V-Information (PVI) based fine-tuning method, providing a detailed theoretical analysis and justification for its use in quantifying the information content of training data.
arXiv Detail & Related papers (2025-01-16T16:19:53Z) - Learning to Summarize from LLM-generated Feedback [18.937441310579164]
This work explores using LLM-generated feedback to improve summary quality by aligning the summaries with human preferences for faithfulness, completeness, and conciseness.
Our experiments show how feedback quality, dimensionality, and granularity influence preference learning.
We introduce SummLlama3-8b, a model that outperforms the nearly 10x larger Llama3-70b-instruct in generating human-preferred summaries.
arXiv Detail & Related papers (2024-10-17T01:01:09Z) - Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models [49.439311430360284]
We introduce a novel data synthesis method inspired by contrastive learning and image difference captioning.
Our key idea involves challenging the model to discern both matching and distinct elements.
We leverage this generated dataset to fine-tune state-of-the-art (SOTA) MLLMs.
arXiv Detail & Related papers (2024-08-08T17:10:16Z) - Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning [47.02160072880698]
We introduce a self-evolving mechanism that allows the model itself to actively sample subsets that are equally or even more effective.
The key to our data sampling technique lies in the enhancement of diversity in the chosen subsets.
Extensive experiments across three datasets and benchmarks demonstrate the effectiveness of DiverseEvol.
arXiv Detail & Related papers (2023-11-14T14:10:40Z) - How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition [64.86360698067764]
This study focuses on the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during supervised fine-tuning.
Our experiments reveal that distinct capabilities scale differently and larger models generally show superior performance with same amount of data.
Our findings suggest the amount of composition data influences performance more than the composition ratio.
arXiv Detail & Related papers (2023-10-09T07:56:16Z) - StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized
Image-Dialogue Data [129.92449761766025]
We propose a novel data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning.
This approach harnesses the power of generative models, marrying the abilities of ChatGPT and text-to-image generative models.
Our research includes comprehensive experiments conducted on various datasets.
arXiv Detail & Related papers (2023-08-20T12:43:52Z) - SDA: Improving Text Generation with Self Data Augmentation [88.24594090105899]
We propose to improve the standard maximum likelihood estimation (MLE) paradigm by incorporating a self-imitation-learning phase for automatic data augmentation.
Unlike most existing sentence-level augmentation strategies, our method is more general and could be easily adapted to any MLE-based training procedure.
arXiv Detail & Related papers (2021-01-02T01:15:57Z)
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.