Retrieval-Augmented Fine-Tuning With Preference Optimization For Visual Program Generation

• URL: http://arxiv.org/abs/2502.16529v1
• Date: Sun, 23 Feb 2025 10:27:44 GMT
• Title: Retrieval-Augmented Fine-Tuning With Preference Optimization For Visual Program Generation
• Authors: Deokhyung Kang, Jeonghun Cho, Yejin Jeon, Sunbin Jang, Minsub Lee, Jawoon Cho, Gary Geunbae Lee,
• Abstract summary: We propose a two-stage training strategy to enhance visual programming languages (VPLs) generation.<n>First, we employ retrieval-augmented fine-tuning to leverage the repetitive use of subroutines commonly seen in industrial VPLs.<n>Second, we apply direct preference optimization (DPO) to further guide the model toward accurate outputs.
• Score: 3.271964502485636
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual programming languages (VPLs) allow users to create programs through graphical interfaces, which results in easier accessibility and their widespread usage in various domains. To further enhance this accessibility, recent research has focused on generating VPL code from user instructions using large language models (LLMs). Specifically, by employing prompting-based methods, these studies have shown promising results. Nevertheless, such approaches can be less effective for industrial VPLs such as Ladder Diagram (LD). LD is a pivotal language used in industrial automation processes and involves extensive domain-specific configurations, which are difficult to capture in a single prompt. In this work, we demonstrate that training-based methods outperform prompting-based methods for LD generation accuracy, even with smaller backbone models. Building on these findings, we propose a two-stage training strategy to further enhance VPL generation. First, we employ retrieval-augmented fine-tuning to leverage the repetitive use of subroutines commonly seen in industrial VPLs. Second, we apply direct preference optimization (DPO) to further guide the model toward accurate outputs, using systematically generated preference pairs through graph editing operations. Extensive experiments on real-world LD data demonstrate that our approach improves program-level accuracy by over 10% compared to supervised fine-tuning, which highlights its potential to advance industrial automation.

Related papers

• Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning [4.762390044282733]
  Large Language Models (LLMs) have demonstrated their exceptional performance in various complex code generation tasks.<n>To mitigate such requirements, model pruning techniques are used to create more compact models with significantly fewer parameters.<n>In this work, we explore the idea of efficiently deriving coding-specific sub-models through unstructured pruning.
  arXiv  Detail & Related papers  (2025-01-09T14:00:01Z)
• Aligning CodeLLMs with Direct Preference Optimization [44.34483822102872]
  This work first identifies that the commonly used PPO algorithm may be suboptimal for the alignment of CodeLLM. Based on only preference data pairs, DPO can render the model rank data automatically, giving rise to a fine-grained rewarding pattern. Studies show that our method significantly improves the performance of existing CodeLLMs on benchmarks such as MBPP and HumanEval.
  arXiv  Detail & Related papers  (2024-10-24T09:36:13Z)
• Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval Augmented Generation [13.120801609024147]
  retrieval augmented generation (RAG) has been shown to enhance factuality of large language model (LLM) outputs. RAG inputs are more complex than most datasets used for training NLI models. We introduce Automatic Generative Domain Adaptation (Auto-GDA) to enable unsupervised domain adaptation.
  arXiv  Detail & Related papers  (2024-10-04T14:21:27Z)
• The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities [0.35998666903987897]
  This report examines the fine-tuning of Large Language Models (LLMs) It outlines the historical evolution of LLMs from traditional Natural Language Processing (NLP) models to their pivotal role in AI. The report introduces a structured seven-stage pipeline for fine-tuning LLMs.
  arXiv  Detail & Related papers  (2024-08-23T14:48:02Z)
• ITERTL: An Iterative Framework for Fine-tuning LLMs for RTL Code Generation [9.409062607311528]
  Large language models (LLMs) have demonstrated excellent performance, inspiring researchers to explore their use in automating register transfer level (RTL) code generation. Existing approaches to fine-tune LLMs for RTL generation typically are conducted on fixed datasets. We introduce an iterative training paradigm named ITERTL to mitigate these issues. Our model outperforms GPT4 and state-of-the-art (SOTA) open-source models, achieving remarkable 53.8% pass@1 rate on VerilogEval-human benchmark.
  arXiv  Detail & Related papers  (2024-06-28T01:44:57Z)
• Aligning Language Models with Demonstrated Feedback [58.834937450242975]
  Demonstration ITerated Task Optimization (DITTO) directly aligns language model outputs to a user's demonstrated behaviors. We evaluate DITTO's ability to learn fine-grained style and task alignment across domains such as news articles, emails, and blog posts.
  arXiv  Detail & Related papers  (2024-06-02T23:13:56Z)
• AXOLOTL: Fairness through Assisted Self-Debiasing of Large Language Model Outputs [20.772266479533776]
  AXOLOTL is a novel post-processing framework that operates agnostically across tasks and models. It identifies biases, proposes resolutions, and guides the model to self-debias its outputs. This approach minimizes computational costs and preserves model performance.
  arXiv  Detail & Related papers  (2024-03-01T00:02:37Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
  We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model to generate an auxiliary directional stimulus prompt for each input instance.
  arXiv  Detail & Related papers  (2023-02-22T17:44:15Z)
• Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Study [76.52997424694767]
  We present an in-depth empirical study of keyphrase extraction and keyphrase generation using pre-trained language models. We show that PLMs have competitive high-resource performance and state-of-the-art low-resource performance. Further results show that in-domain BERT-like PLMs can be used to build strong and data-efficient keyphrase generation models.
  arXiv  Detail & Related papers  (2022-12-20T13:20:21Z)
• 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)
• DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks [88.62288327934499]
  We propose a novel augmentation method with language models trained on the linearized labeled sentences. Our method is applicable to both supervised and semi-supervised settings.
  arXiv  Detail & Related papers  (2020-11-03T07:49:15Z)

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.