$\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases

• URL: http://arxiv.org/abs/2406.06887v4
• Date: Sat, 12 Oct 2024 06:09:18 GMT
• Title: $\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases
• Authors: Dylan Zhang, Shizhe Diao, Xueyan Zou, Hao Peng,
• Abstract summary: We propose PLUM, an on-policy $textbfP$reference $textbfL$earning framework A$textbfu$gmented with test cases for code L$textbfM$ s. PLUM levitates the need to train reward models, allowing for large scale on-policy and online preference data collation. We show PLUM's benefits are consistent across various widely-used code LMs even they have been well-trained with SFT.
• Score: 28.791570350483816
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Preference learning provides a promising solution to address the limitations of supervised fine-tuning (SFT) for code language models, where the model is not explicitly trained to differentiate between correct and incorrect code. Recent findings demonstrate that on-policy data is the key to successful preference learning, where the preference data is collected using the same policy LM being trained. Inspired by this, we propose PLUM, an on-policy $\textbf{P}$reference $\textbf{L}$earning framework A$\textbf{u}$gmented with test cases for code L$\textbf{M}$ s. The framework operates in three key stages: (1) automatic generation of test cases from natural language instructions, (2) creation of a preference data by evaluating candidate code solutions sampled from the policy, which can then be used to (3) train the policy LM. PLUM levitates the need to train reward models, allowing for large scale on-policy and online preference data collation. PLUM is evaluated on both standard benchmarks (HumanEval, MBPP) and more challenging ones (LiveCodeBench), delivering substantial improvements over original SFT'ed models and other execution-feedback-driven approaches. We show PLUM's benefits are consistent across various widely-used code LMs even they have been well-trained with SFT. For example, PLUM increases pass rates by up to 4.8% on average on standard benchmarks and 11.8% on LiveCodeBench, demonstrating its effectiveness and generalizability. We also demonstrate the benefits of on-policy and online preference learning by comprehensive experimentation.

Related papers

• Accelerating RL for LLM Reasoning with Optimal Advantage Regression [52.0792918455501]
  We propose a novel two-stage policy optimization framework that directly approximates the optimal advantage function.<n>$A$*-PO achieves competitive performance across a wide range of mathematical reasoning benchmarks.<n>It reduces training time by up to 2$times$ and peak memory usage by over 30% compared to PPO, GRPO, and REBEL.
  arXiv  Detail & Related papers  (2025-05-27T03:58:50Z)
• Soft Policy Optimization: Online Off-Policy RL for Sequence Models [42.95110169230739]
  Post-training of language models is almost exclusively done using on-policy methods such as PPO. SPO is a simple, scalable and principled Soft RL method for sequence model policies that can learn from arbitrary online and offline trajectories.
  arXiv  Detail & Related papers  (2025-03-07T14:23:40Z)
• Best Policy Learning from Trajectory Preference Feedback [15.799929216215672]
  We address the problem of best policy identification in preference-based reinforcement learning (PbRL) We propose Posterior Sampling for Preference Learning ($mathsfPSPL$), a novel algorithm inspired by Top-Two Thompson Sampling. We provide the first theoretical guarantees for PbRL in this setting, establishing an upper bound on the simple Bayesian regret.
  arXiv  Detail & Related papers  (2025-01-31T03:55:10Z)
• Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion [44.95386817008473]
  We introduce Contrastive Policy Gradient, or CoPG, a simple and mathematically principled new RL algorithm that can estimate the optimal policy even from off-policy data. We show this approach to generalize the direct alignment method IPO (identity preference optimization) and classic policy gradient. We experiment with the proposed CoPG on a toy bandit problem to illustrate its properties, as well as for finetuning LLMs on a summarization task.
  arXiv  Detail & Related papers  (2024-06-27T14:03:49Z)
• Value Augmented Sampling for Language Model Alignment and Personalization [39.070662999014836]
  We present a new framework for reward optimization, Value Augmented Sampling (VAS) VAS solves for the optimal reward-maximizing policy without co-training the policy and the value function. Our algorithm unlocks the new capability of composing several rewards and controlling the extent of each one during deployment time.
  arXiv  Detail & Related papers  (2024-05-10T17:59:04Z)
• Fine-Tuning Language Models with Reward Learning on Policy [68.70065254564642]
  Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. Despite its popularity, (fixed) reward models may suffer from inaccurate off-distribution. We propose reward learning on policy (RLP), an unsupervised framework that refines a reward model using policy samples to keep it on-distribution.
  arXiv  Detail & Related papers  (2024-03-28T10:02:10Z)
• Generalizing Reward Modeling for Out-of-Distribution Preference Learning [3.9160947065896803]
  Preference learning with large language models (LLMs) aims to align the LLMs' generations with human preferences. Due to the difficulty of obtaining human feedback, discretely training reward models for every encountered distribution is challenging. This work addresses OOD PL by optimizing a general reward model through a meta-learning approach.
  arXiv  Detail & Related papers  (2024-02-22T18:20:33Z)
• Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning [54.682106515794864]
  offline reinforcement learning (RL) aims to find a near-optimal policy using pre-collected datasets. This paper introduces $textbfLanguage Models for $textbfMo$tion Control ($textbfLaMo$), a general framework based on Decision Transformers to use pre-trained Language Models (LMs) for offline RL. Empirical results indicate $textbfLaMo$ achieves state-of-the-art performance in sparse-reward tasks.
  arXiv  Detail & Related papers  (2023-10-31T16:24:17Z)
• Large Language Model-Aware In-Context Learning for Code Generation [75.68709482932903]
  Large language models (LLMs) have shown impressive in-context learning (ICL) ability in code generation. We propose a novel learning-based selection approach named LAIL (LLM-Aware In-context Learning) for code generation.
  arXiv  Detail & Related papers  (2023-10-15T06:12:58Z)
• Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization [90.9780151608281]
  In-sample learning (IQL) improves the policy by quantile regression using only data samples. We make a key finding that the in-sample learning paradigm arises under the textitImplicit Value Regularization (IVR) framework. We propose two practical algorithms, Sparse $Q$-learning (EQL) and Exponential $Q$-learning (EQL), which adopt the same value regularization used in existing works.
  arXiv  Detail & Related papers  (2023-03-28T08:30:01Z)
• $k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference [75.08572535009276]
  In-Context Learning (ICL) formulates target tasks as prompt completion conditioned on in-context demonstrations. $k$NN Prompting first queries LLM with training data for distributed representations, then predicts test instances by simply referring to nearest neighbors. It significantly outperforms state-of-the-art calibration-based methods under comparable few-shot scenario.
  arXiv  Detail & Related papers  (2023-03-24T06:16:29Z)
• An Experimental Design Perspective on Model-Based Reinforcement Learning [73.37942845983417]
  In practical applications of RL, it is expensive to observe state transitions from the environment. We propose an acquisition function that quantifies how much information a state-action pair would provide about the optimal solution to a Markov decision process.
  arXiv  Detail & Related papers  (2021-12-09T23:13:57Z)

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.