Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models

• URL: http://arxiv.org/abs/2406.13542v3
• Date: Thu, 18 Jul 2024 09:00:23 GMT
• Title: Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models
• Authors: Guanting Dong, Keming Lu, Chengpeng Li, Tingyu Xia, Bowen Yu, Chang Zhou, Jingren Zhou,
• Abstract summary: We introduce AutoIF, the first scalable and reliable method for automatically generating instruction-following training data. AutoIF transforms the validation of instruction-following data quality into code verification.
• Score: 54.14602121129874
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: One core capability of large language models (LLMs) is to follow natural language instructions. However, the issue of automatically constructing high-quality training data to enhance the complex instruction-following abilities of LLMs without manual annotation remains unresolved. In this paper, we introduce AutoIF, the first scalable and reliable method for automatically generating instruction-following training data. AutoIF transforms the validation of instruction-following data quality into code verification, requiring LLMs to generate instructions, the corresponding code to check the correctness of the instruction responses, and unit test samples to verify the code's correctness. Then, execution feedback-based rejection sampling can generate data for Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) training. AutoIF achieves significant improvements across three training algorithms, SFT, Offline DPO, and Online DPO, when applied to the top open-source LLMs, Qwen2 and LLaMA3, in self-alignment and strong-to-weak distillation settings. Our code is publicly available at https://github.com/QwenLM/AutoIF.

Related papers

• Training LLMs to Better Self-Debug and Explain Code [36.604898865514365]
  We propose a training framework that significantly improves self-sourcedging capability of LLMs. We propose an automated pipeline to collect a high-quality dataset for code explanation and refinement. We perform supervised fine-tuning (SFT) and further reinforcement learning (RL) on both success and failure trajectories with a novel reward design.
  arXiv  Detail & Related papers  (2024-05-28T23:20:24Z)
• CodecLM: Aligning Language Models with Tailored Synthetic Data [51.59223474427153]
  We introduce CodecLM, a framework for adaptively generating high-quality synthetic data for instruction-following abilities. We first encode seed instructions into metadata, which are concise keywords generated on-the-fly to capture the target instruction distribution. We also introduce Self-Rubrics and Contrastive Filtering during decoding to tailor data-efficient samples.
  arXiv  Detail & Related papers  (2024-04-08T21:15:36Z)
• Fine-Tuning and Prompt Engineering for Large Language Models-based Code Review Automation [4.941630596191807]
  Fine-tuning and prompting are common approaches to leveraging Large Language Models (LLMs) for code review automation. We use model fine-tuning and inference techniques (i.e., zero-shot learning, few-shot learning and persona) on LLMs-based code review automation. Our results show that GPT-3.5 with zero-shot learning achieves 73.17% -74.23% higher EM than the Guo et al.'s approach.
  arXiv  Detail & Related papers  (2024-02-01T03:10:26Z)
• Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models [52.98743860365194]
  We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN) At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself. This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents.
  arXiv  Detail & Related papers  (2024-01-02T18:53:13Z)
• Tuna: Instruction Tuning using Feedback from Large Language Models [74.04950416204551]
  We propose finetuning an instruction-tuned large language model using our novel textitprobabilistic ranking and textitcontextual ranking approaches. Probabilistic ranking enables the instruction-tuned model to inherit the relative rankings of high-quality and low-quality responses from the teacher LLM. On the other hand, learning with contextual ranking allows the model to refine its own response distribution using the contextual understanding ability of stronger LLMs.
  arXiv  Detail & Related papers  (2023-10-20T09:55:06Z)
• 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)
• SelfEvolve: A Code Evolution Framework via Large Language Models [5.6607714367826105]
  Large language models (LLMs) have already revolutionized code generation, after being pretrained on publicly available code data. We propose a novel two-step pipeline, called autoknow, that leverages LLMs as both knowledge providers and self-reflective programmers. We evaluate autoknowon three code generation datasets, including DS-1000 for data science code, HumanEval for software engineering code, and TransCoder for C++-to-Python translation.
  arXiv  Detail & Related papers  (2023-06-05T14:12:46Z)
• Coarse-Tuning Models of Code with Reinforcement Learning Feedback [0.0]
  Large Language Models (LLMs) pre-trained on code have emerged as the dominant approach to program synthesis. We propose RLCF, that further trains a pre-trained LLM via reinforcement learning, using feedback from a grounding function that scores the quality of the code.
  arXiv  Detail & Related papers  (2023-05-25T22:09:08Z)
• LeTI: Learning to Generate from Textual Interactions [60.425769582343506]
  We explore LMs' potential to learn from textual interactions (LETI) that not only check their correctness with binary labels but also pinpoint and explain errors in their outputs through textual feedback. Our focus is the code generation task, where the model produces code based on natural language instructions. LETI iteratively fine-tunes the model, using the objective LM, on a concatenation of natural language instructions, LM-generated programs, and textual feedback.
  arXiv  Detail & Related papers  (2023-05-17T15:53:31Z)

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.