Efficient Controlled Language Generation with Low-Rank Autoregressive Reward Models

• URL: http://arxiv.org/abs/2407.04615v2
• Date: Tue, 1 Oct 2024 09:23:32 GMT
• Title: Efficient Controlled Language Generation with Low-Rank Autoregressive Reward Models
• Authors: Sergey Troshin, Vlad Niculae, Antske Fokkens,
• Abstract summary: We revisit the reward augmented decoding (RAD) approach to control the generation from a language model using the scores from a task-specific reward model. We show that RAD is designed to support high flexibility when representing the reward matrices, which leads to a higher computational costs during decoding. Motivated by this, we propose a simpler but more efficient low-rank parametrization of the reward model enabling fast and effective guided decoding.
• Score: 13.38174941551702
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language models trained on large amounts of data are known to produce inappropriate content in some cases and require careful tuning to be used in the real world. We revisit the reward augmented decoding (RAD) approach to control the generation from a language model using the scores from a task-specific reward model. We investigate the training objective of RAD, and reformulate it as a task of learning a reward matrix. We show that RAD is designed to support high flexibility when representing the reward matrices, which leads to a higher computational costs during decoding. However, we demonstrate that RAD does not use its full flexibility. Motivated by this, we propose a simpler but more efficient low-rank parametrization of the reward model enabling fast and effective guided decoding. For the detoxification and sentiment control tasks, we show that our low-rank reward model performs on par with the more flexible RAD parametrization, while requiring only a single reward model call per generated token.

Related papers

• HAF-RM: A Hybrid Alignment Framework for Reward Model Training [51.59246299566669]
  We propose a hybrid alignment framework HaF-RM for reward model training. It offers a principled and effective approach to enhancing the performance and alignment of reward models.
  arXiv  Detail & Related papers  (2024-07-04T23:26:56Z)
• RewardBench: Evaluating Reward Models for Language Modeling [100.28366840977966]
  We present RewardBench, a benchmark dataset and code-base for evaluation of reward models. The dataset is a collection of prompt-chosen-rejected trios spanning chat, reasoning, and safety. On the RewardBench leaderboard, we evaluate reward models trained with a variety of methods.
  arXiv  Detail & Related papers  (2024-03-20T17:49:54Z)
• Dense Reward for Free in Reinforcement Learning from Human Feedback [64.92448888346125]
  We leverage the fact that the reward model contains more information than just its scalar output. We use these attention weights to redistribute the reward along the whole completion. Empirically, we show that it stabilises training, accelerates the rate of learning, and, in practical cases, may lead to better local optima.
  arXiv  Detail & Related papers  (2024-02-01T17:10:35Z)
• Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint [104.53687944498155]
  Reinforcement learning (RL) has been widely used in training large language models (LLMs) We propose a new RL method named RLMEC that incorporates a generative model as the reward model. Based on the generative reward model, we design the token-level RL objective for training and an imitation-based regularization for stabilizing RL process.
  arXiv  Detail & Related papers  (2024-01-11T17:58:41Z)
• Let's Reinforce Step by Step [10.65244642965387]
  We use Reinforcement Learning from Human Feedback to shape model reasoning processes. Our results show that the fine-grained reward provided by PRM-based methods enhances accuracy on simple mathematical reasoning. We also show the critical role reward aggregation functions play in model performance.
  arXiv  Detail & Related papers  (2023-11-10T01:35:51Z)
• Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model [47.722856876213946]
  Reward-Augmented Decoding (RAD) is a text generation procedure that uses a small unidirectional reward model to encourage a language model to generate text that has certain properties. By using a unidirectional reward model, RAD can cache activations from prior generation steps to decrease computational overhead.
  arXiv  Detail & Related papers  (2023-10-14T07:19:47Z)
• CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning [92.36705236706678]
  "CodeRL" is a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning. During inference, we introduce a new generation procedure with a critical sampling strategy. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives.
  arXiv  Detail & Related papers  (2022-07-05T02:42:15Z)

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.