Horizon-Length Prediction: Advancing Fill-in-the-Middle Capabilities for Code Generation with Lookahead Planning

• URL: http://arxiv.org/abs/2410.03103v1
• Date: Fri, 4 Oct 2024 02:53:52 GMT
• Title: Horizon-Length Prediction: Advancing Fill-in-the-Middle Capabilities for Code Generation with Lookahead Planning
• Authors: Yifeng Ding, Hantian Ding, Shiqi Wang, Qing Sun, Varun Kumar, Zijian Wang,
• Abstract summary: We propose Horizon-Length Prediction (HLP), a novel training objective that teaches models to predict the number of remaining middle tokens at each step. HLP significantly improves FIM performance by up to 24% relatively on diverse benchmarks, across file-level and repository-level, and without resorting to unrealistic post-processing methods.
• Score: 17.01133761213624
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fill-in-the-Middle (FIM) has become integral to code language models, enabling generation of missing code given both left and right contexts. However, the current FIM training paradigm, which reorders original training sequences and then performs regular next-token prediction (NTP), often leads to models struggling to generate content that aligns smoothly with the surrounding context. Crucially, while existing works rely on rule-based post-processing to circumvent this weakness, such methods are not practically usable in open-domain code completion tasks as they depend on restrictive, dataset-specific assumptions (e.g., generating the same number of lines as in the ground truth). Moreover, model performance on FIM tasks deteriorates significantly without these unrealistic assumptions. We hypothesize that NTP alone is insufficient for models to learn effective planning conditioned on the distant right context, a critical factor for successful code infilling. To overcome this, we propose Horizon-Length Prediction (HLP), a novel training objective that teaches models to predict the number of remaining middle tokens (i.e., horizon length) at each step. HLP advances FIM with lookahead planning, enabling models to inherently learn infilling boundaries for arbitrary left and right contexts without relying on dataset-specific post-processing. Our evaluation across different models and sizes shows that HLP significantly improves FIM performance by up to 24% relatively on diverse benchmarks, across file-level and repository-level, and without resorting to unrealistic post-processing methods. Furthermore, the enhanced planning capability gained through HLP boosts model performance on code reasoning. Importantly, HLP only incurs negligible training overhead and no additional inference cost, ensuring its practicality for real-world scenarios.

Related papers

• LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training [2.762397703396293]
  Loss Prediction Loss with Gradient Norm (LPLgrad) is designed to quantify model uncertainty effectively and improve the accuracy of image classification tasks. LPLgrad operates in two distinct phases: (i) em Training Phase aims to predict the loss for input features by jointly training a main model and an auxiliary model. This dual-model approach enhances the ability to extract complex input features and learn intrinsic patterns from the data effectively.
  arXiv  Detail & Related papers  (2024-11-20T18:12:59Z)
• Boosting Lossless Speculative Decoding via Feature Sampling and Partial Alignment Distillation [8.046705062670096]
  Lossless speculative decoding accelerates target large language model inference. We propose FSPAD (Feature Sampling and Partial Alignment Distillation for Lossless Speculative Decoding) to boost speculative decoding. Our experiments include both greedy and non-greedy decoding on the largest and smallest models from the Vicuna and LLaMA3-Instruct series.
  arXiv  Detail & Related papers  (2024-08-28T06:28:01Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation [105.23631749213729]
  We propose a novel method for unsupervised pre-training in low-data regimes. Inspired by the recently successful prompting technique, we introduce a new method, Unsupervised Pre-training with Language-Vision Prompts. We show that our method can converge faster and perform better than CNN-based models in low-data regimes.
  arXiv  Detail & Related papers  (2024-05-22T06:48:43Z)
• Rethinking the Starting Point: Collaborative Pre-Training for Federated Downstream Tasks [21.842345900168525]
  CoPreFL is a model-agnostic meta-learning (MAML) procedure that tailors the global model to closely mimic heterogeneous and unseen FL scenarios. Our MAML procedure incorporates performance variance into the meta-objective function, balancing performance across clients. We demonstrate that CoPreFL obtains significant improvements in both average accuracy and variance across arbitrary downstream FL tasks.
  arXiv  Detail & Related papers  (2024-02-03T17:58:43Z)
• Amortizing intractable inference in large language models [56.92471123778389]
  We use amortized Bayesian inference to sample from intractable posterior distributions. We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
  arXiv  Detail & Related papers  (2023-10-06T16:36:08Z)
• A Meta-Learning Approach to Predicting Performance and Data Requirements [163.4412093478316]
  We propose an approach to estimate the number of samples required for a model to reach a target performance. We find that the power law, the de facto principle to estimate model performance, leads to large error when using a small dataset. We introduce a novel piecewise power law (PPL) that handles the two data differently.
  arXiv  Detail & Related papers  (2023-03-02T21:48:22Z)
• Aligned Multi-Task Gaussian Process [12.903751268469696]
  Multi-task learning requires accurate identification of the correlations between tasks. Traditional multi-task models do not account for this and subsequent errors in correlation estimation will result in poor predictive performance. We introduce a method that automatically accounts for temporal misalignment in a unified generative model that improves predictive performance.
  arXiv  Detail & Related papers  (2021-10-29T13:18:13Z)
• Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning [61.32992639292889]
  Fine-tuning of pre-trained transformer models has become the standard approach for solving common NLP tasks. We introduce a new scoring method that casts a plausibility ranking task in a full-text format. We show that our method provides a much more stable training phase across random restarts.
  arXiv  Detail & Related papers  (2020-04-29T10:54:40Z)
• Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
  A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-02-27T10:22:17Z)

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.