A Baseline Analysis of Reward Models' Ability To Accurately Analyze Foundation Models Under Distribution Shift

• URL: http://arxiv.org/abs/2311.14743v7
• Date: Wed, 24 Jan 2024 12:08:34 GMT
• Title: A Baseline Analysis of Reward Models' Ability To Accurately Analyze Foundation Models Under Distribution Shift
• Authors: Will LeVine, Benjamin Pikus, Anthony Chen, Sean Hendryx
• Abstract summary: We evaluate how reward model performance is affected by distribution shift. We show novel calibration patterns and accuracy drops due to OOD prompts and responses. We adapt an OOD detection technique commonly used in classification to the reward model setting to detect these distribution shifts.
• Score: 2.2310395620011945
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Foundation models, specifically Large Language Models (LLMs), have lately gained wide-spread attention and adoption. Reinforcement Learning with Human Feedback (RLHF) involves training a reward model to capture desired behaviors, which is then used to align LLM's. These reward models are additionally used at inference-time to estimate LLM responses' adherence to those desired behaviors. However, there is little work measuring how robust these reward models are to distribution shifts. In this work, we evaluate how reward model performance - measured via accuracy and calibration (i.e. alignment between accuracy and confidence) - is affected by distribution shift. We show novel calibration patterns and accuracy drops due to OOD prompts and responses, and that the reward model is more sensitive to shifts in responses than prompts. Additionally, we adapt an OOD detection technique commonly used in classification to the reward model setting to detect these distribution shifts in prompts and responses.

Related papers

• Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems [54.4392552373835]
  Reward models (RMs) are crucial for the training and inference-time scaling up of large language models (LLMs) We propose agentic reward modeling, a reward system that combines reward models with verifiable correctness signals to provide reliable rewards. We conduct comprehensive experiments on existing reward model benchmarks and inference time best-of-n searches on real-world downstream tasks.
  arXiv  Detail & Related papers  (2025-02-26T17:19:12Z)
• Approximated Variational Bayesian Inverse Reinforcement Learning for Large Language Model Alignment [0.618727087412292]
  The alignment of large language models (LLMs) is crucial for generating helpful and harmless content. Existing approaches leverage preference-based human feedback data to learn the reward function. We propose a novel training objective, Approximated Variational Alignment (AVA), to perform LLM alignment through Approximated Variational Reward Learning (AVRIL)
  arXiv  Detail & Related papers  (2024-11-14T10:37:34Z)
• Quantile Regression for Distributional Reward Models in RLHF [1.8130068086063336]
  We introduce Quantile Reward Models (QRMs), a novel approach to reward modeling that learns a distribution over rewards instead of a single scalar value. Our method uses quantile regression to estimate a full, potentially multimodal distribution over preferences, providing a more powerful and nuanced representation of preferences. Our experimental results show that QRM outperforms comparable traditional point-estimate models on RewardBench.
  arXiv  Detail & Related papers  (2024-09-16T10:54:04Z)
• 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)
• Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
  Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
  arXiv  Detail & Related papers  (2024-02-13T11:25:20Z)
• 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)
• Distributionally Robust Post-hoc Classifiers under Prior Shifts [31.237674771958165]
  We investigate the problem of training models that are robust to shifts caused by changes in the distribution of class-priors or group-priors. We present an extremely lightweight post-hoc approach that performs scaling adjustments to predictions from a pre-trained model.
  arXiv  Detail & Related papers  (2023-09-16T00:54:57Z)
• How robust are pre-trained models to distribution shift? [82.08946007821184]
  We show how spurious correlations affect the performance of popular self-supervised learning (SSL) and auto-encoder based models (AE) We develop a novel evaluation scheme with the linear head trained on out-of-distribution (OOD) data, to isolate the performance of the pre-trained models from a potential bias of the linear head used for evaluation.
  arXiv  Detail & Related papers  (2022-06-17T16:18:28Z)
• Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations [97.91630330328815]
  We conduct a crowdsourcing study, where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews. We observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control.
  arXiv  Detail & Related papers  (2021-12-17T18:29:56Z)
• BEDS-Bench: Behavior of EHR-models under Distributional Shift--A Benchmark [21.040754460129854]
  We release BEDS-Bench, a benchmark for quantifying the behavior of ML models over EHR data under OOD settings. We evaluate several learning algorithms under BEDS-Bench and find that all of them show poor generalization performance under distributional shift in general.
  arXiv  Detail & Related papers  (2021-07-17T05:53:24Z)
• Models, Pixels, and Rewards: Evaluating Design Trade-offs in Visual Model-Based Reinforcement Learning [109.74041512359476]
  We study a number of design decisions for the predictive model in visual MBRL algorithms. We find that a range of design decisions that are often considered crucial, such as the use of latent spaces, have little effect on task performance. We show how this phenomenon is related to exploration and how some of the lower-scoring models on standard benchmarks will perform the same as the best-performing models when trained on the same training data.
  arXiv  Detail & Related papers  (2020-12-08T18:03:21Z)

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.