A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation

• URL: http://arxiv.org/abs/2407.02742v1
• Date: Wed, 3 Jul 2024 01:28:51 GMT
• Title: A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation
• Authors: Nastaran Bassamzadeh, Chhaya Methani,
• Abstract summary: We present optimizations for using Retrieval Augmented Generation (or RAG) with Large Language Models (LLMs) for DSL generation. Our results showed that the fine-tuned model scored the best on code similarity metric. We conclude that an optimized RAG model can match the quality of fine-tuned models and offer advantages for new, unseen APIs.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Natural Language to Code Generation has made significant progress in recent years with the advent of Large Language Models(LLMs). While generation for general-purpose languages like C, C++, and Python has improved significantly, LLMs struggle with custom function names in Domain Specific Languages or DSLs. This leads to higher hallucination rates and syntax errors, specially for DSLs having a high number of custom function names. Additionally, constant updates to function names add to the challenge as LLMs need to stay up-to-date. In this paper, we present optimizations for using Retrieval Augmented Generation (or RAG) with LLMs for DSL generation along with an ablation study comparing these strategies. We generated a train as well as test dataset with a DSL to represent automation tasks across roughly 700 APIs in public domain. We used the training dataset to fine-tune a Codex model for this DSL. Our results showed that the fine-tuned model scored the best on code similarity metric. With our RAG optimizations, we achieved parity for similarity metric. The compilation rate, however, showed that both the models still got the syntax wrong many times, with RAG-based method being 2 pts better. Conversely, hallucination rate for RAG model lagged by 1 pt for API names and by 2 pts for API parameter keys. We conclude that an optimized RAG model can match the quality of fine-tuned models and offer advantages for new, unseen APIs.

Related papers

• Less is More: Making Smaller Language Models Competent Subgraph Retrievers for Multi-hop KGQA [51.3033125256716]
  We model the subgraph retrieval task as a conditional generation task handled by small language models. Our base generative subgraph retrieval model, consisting of only 220M parameters, competitive retrieval performance compared to state-of-the-art models. Our largest 3B model, when plugged with an LLM reader, sets new SOTA end-to-end performance on both the WebQSP and CWQ benchmarks.
  arXiv  Detail & Related papers  (2024-10-08T15:22:36Z)
• ToolACE: Winning the Points of LLM Function Calling [139.07157814653638]
  ToolACE is an automatic agentic pipeline designed to generate accurate, complex, and diverse tool-learning data. We demonstrate that models trained on our synthesized data, even with only 8B parameters, achieve state-of-the-art performance on the Berkeley Function-Calling Leaderboard.
  arXiv  Detail & Related papers  (2024-09-02T03:19:56Z)
• Plan with Code: Comparing approaches for robust NL to DSL generation [0.0]
  Planning in code is considered a more reliable approach for many orchestration tasks. This paper focuses on workflow automation in RPA (Robotic Process Automation) domain as a special case of task planning.
  arXiv  Detail & Related papers  (2024-08-15T04:29:33Z)
• ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets [106.7760874400261]
  This paper presents ML-SUPERB2.0, which is a new benchmark for evaluating pre-trained SSL and supervised speech models. We find performance improvements over the setup of ML-SUPERB, but performance depends on the downstream model design. Also, we find large performance differences between languages and datasets, suggesting the need for more targeted approaches.
  arXiv  Detail & Related papers  (2024-06-12T21:01:26Z)
• Scaling Sparse Fine-Tuning to Large Language Models [67.59697720719672]
  Large Language Models (LLMs) are difficult to fully fine-tune due to their sheer number of parameters. We propose SpIEL, a novel sparse finetuning method which maintains an array of parameter indices and the deltas of these parameters relative to their pretrained values. We show that SpIEL is superior to popular parameter-efficient fine-tuning methods like LoRA in terms of performance and comparable in terms of run time.
  arXiv  Detail & Related papers  (2024-01-29T18:43:49Z)
• Reinforcement Learning for Optimizing RAG for Domain Chatbots [4.12484724941528]
  This paper describes a RAG-based approach for building a bot that answers user's queries using Frequently Asked Questions (FAQ) data. We train an in-house retrieval embedding model using infoNCE loss, and experimental results demonstrate that the in-house model works significantly better than the well-known general-purpose public embedding model. We propose a policy-based model external to the RAG, which interacts with the RAG pipeline through policy actions and updates the policy to optimize the cost.
  arXiv  Detail & Related papers  (2024-01-10T02:57:20Z)
• MLLM-DataEngine: An Iterative Refinement Approach for MLLM [62.30753425449056]
  We propose a novel closed-loop system that bridges data generation, model training, and evaluation. Within each loop, the MLLM-DataEngine first analyze the weakness of the model based on the evaluation results. For targeting, we propose an Adaptive Bad-case Sampling module, which adjusts the ratio of different types of data. For quality, we resort to GPT-4 to generate high-quality data with each given data type.
  arXiv  Detail & Related papers  (2023-08-25T01:41:04Z)
• On the Effectiveness of Pretrained Models for API Learning [8.788509467038743]
  Developers frequently use APIs to implement certain functionalities, such as parsing Excel Files, reading and writing text files line by line, etc. Developers can greatly benefit from automatic API usage sequence generation based on natural language queries for building applications in a faster and cleaner manner. Existing approaches utilize information retrieval models to search for matching API sequences given a query or use RNN-based encoder-decoder to generate API sequences.
  arXiv  Detail & Related papers  (2022-04-05T20:33:24Z)
• WARP: Word-level Adversarial ReProgramming [13.08689221166729]
  In many applications it is preferable to tune much smaller sets of parameters, so that the majority of parameters can be shared across multiple tasks. We present an alternative approach based on adversarial reprogramming, which extends earlier work on automatic prompt generation. We show that this approach outperforms other methods with a similar number of trainable parameters on SST-2 and MNLI datasets.
  arXiv  Detail & Related papers  (2021-01-01T00:41:03Z)
• Multi-layer Optimizations for End-to-End Data Analytics [71.05611866288196]
  We introduce Iterative Functional Aggregate Queries (IFAQ), a framework that realizes an alternative approach. IFAQ treats the feature extraction query and the learning task as one program given in the IFAQ's domain-specific language. We show that a Scala implementation of IFAQ can outperform mlpack, Scikit, and specialization by several orders of magnitude for linear regression and regression tree models over several relational datasets.
  arXiv  Detail & Related papers  (2020-01-10T16:14:44Z)

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.