InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
- URL: http://arxiv.org/abs/2402.09345v4
- Date: Thu, 23 May 2024 06:39:53 GMT
- Title: InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
- Authors: Yuchun Miao, Sen Zhang, Liang Ding, Rong Bao, Lefei Zhang, Dacheng Tao,
- Abstract summary: Reward hacking, also termed reward overoptimization, remains a critical challenge.
We propose a framework for reward modeling, namely InfoRM, by introducing a variational information bottleneck objective.
We show that InfoRM's overoptimization detection mechanism is not only effective but also robust across a broad range of datasets.
- Score: 66.3072381478251
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Despite the success of reinforcement learning from human feedback (RLHF) in aligning language models with human values, reward hacking, also termed reward overoptimization, remains a critical challenge. This issue primarily arises from reward misgeneralization, where reward models (RMs) compute reward using spurious features that are irrelevant to human preferences. In this work, we tackle this problem from an information-theoretic perspective and propose a framework for reward modeling, namely InfoRM, by introducing a variational information bottleneck objective to filter out irrelevant information. Notably, we further identify a correlation between overoptimization and outliers in the IB latent space of InfoRM, establishing it as a promising tool for detecting reward overoptimization. Inspired by this finding, we propose the Cluster Separation Index (CSI), which quantifies deviations in the IB latent space, as an indicator of reward overoptimization to facilitate the development of online mitigation strategies. Extensive experiments on a wide range of settings and RM scales (70M, 440M, 1.4B, and 7B) demonstrate the effectiveness of InfoRM. Further analyses reveal that InfoRM's overoptimization detection mechanism is not only effective but also robust across a broad range of datasets, signifying a notable advancement in the field of RLHF. The code will be released upon acceptance.
Related papers
- Enhancing Adversarial Transferability via Information Bottleneck Constraints [18.363276470822427]
We propose a framework for performing black-box transferable adversarial attacks named IBTA.
To overcome the challenge of unoptimizable mutual information, we propose a simple and efficient mutual information lower bound (MILB) for approximating computation.
Our experiments on the ImageNet dataset well demonstrate the efficiency and scalability of IBTA and derived MILB.
arXiv Detail & Related papers (2024-06-08T17:25:31Z) - Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [90.4820014819937]
We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions.
Our experimental results demonstrate that when finetuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, SELM significantly boosts the performance on instruction-following benchmarks.
arXiv Detail & Related papers (2024-05-29T17:59:07Z) - Iterative Data Smoothing: Mitigating Reward Overfitting and
Overoptimization in RLHF [79.98542868281471]
Reinforcement Learning from Human Feedback (RLHF) is a technique that aligns language models closely with human-centric values.
It is observed that the performance of the reward model degrades after one epoch of training, and optimizing too much against the learned reward model eventually hinders the true objective.
This paper delves into these issues, leveraging the theoretical insights to design improved reward learning algorithm termed 'Iterative Data Smoothing' (IDS)
arXiv Detail & Related papers (2024-01-29T17:43:42Z) - Secrets of RLHF in Large Language Models Part II: Reward Modeling [134.97964938009588]
We introduce a series of novel methods to mitigate the influence of incorrect and ambiguous preferences in the dataset.
We also introduce contrastive learning to enhance the ability of reward models to distinguish between chosen and rejected responses.
arXiv Detail & Related papers (2024-01-11T17:56:59Z) - REBEL: A Regularization-Based Solution for Reward Overoptimization in Robotic Reinforcement Learning from Human Feedback [61.54791065013767]
A misalignment between the reward function and user intentions, values, or social norms can be catastrophic in the real world.
Current methods to mitigate this misalignment work by learning reward functions from human preferences.
We propose a novel concept of reward regularization within the robotic RLHF framework.
arXiv Detail & Related papers (2023-12-22T04:56:37Z) - Augmenting Unsupervised Reinforcement Learning with Self-Reference [63.68018737038331]
Humans possess the ability to draw on past experiences explicitly when learning new tasks.
We propose the Self-Reference (SR) approach, an add-on module explicitly designed to leverage historical information.
Our approach achieves state-of-the-art results in terms of Interquartile Mean (IQM) performance and Optimality Gap reduction on the Unsupervised Reinforcement Learning Benchmark.
arXiv Detail & Related papers (2023-11-16T09:07:34Z) - The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from
Human Feedback [5.037876196534672]
Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) more capable in complex settings.
In this paper, we illustrate the causes of this issue, reviewing relevant literature from model-based reinforcement learning, and argue for solutions.
arXiv Detail & Related papers (2023-10-31T21:52:41Z) - Active Feature Acquisition with Generative Surrogate Models [11.655069211977464]
In this work, we consider models that perform active feature acquisition (AFA) and query the environment for unobserved features.
Our work reformulates the Markov decision process (MDP) that underlies the AFA problem as a generative modeling task.
We propose learning a generative surrogate model ( GSM) that captures the dependencies among input features to assess potential information gain from acquisitions.
arXiv Detail & Related papers (2020-10-06T02:10:06Z)
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.