Test-Time Alignment via Hypothesis Reweighting

• URL: http://arxiv.org/abs/2412.08812v1
• Date: Wed, 11 Dec 2024 23:02:26 GMT
• Title: Test-Time Alignment via Hypothesis Reweighting
• Authors: Yoonho Lee, Jonathan Williams, Henrik Marklund, Archit Sharma, Eric Mitchell, Anikait Singh, Chelsea Finn,
• Abstract summary: Large pretrained models often struggle with underspecified tasks. We propose a novel framework to address the challenge of aligning models to test-time user intent.
• Score: 56.71167047381817
• License:
• Abstract: Large pretrained models often struggle with underspecified tasks -- situations where the training data does not fully define the desired behavior. For example, chatbots must handle diverse and often conflicting user preferences, requiring adaptability to various user needs. We propose a novel framework to address the general challenge of aligning models to test-time user intent, which is rarely fully specified during training. Our approach involves training an efficient ensemble, i.e., a single neural network with multiple prediction heads, each representing a different function consistent with the training data. Our main contribution is HyRe, a simple adaptation technique that dynamically reweights ensemble members at test time using a small set of labeled examples from the target distribution, which can be labeled in advance or actively queried from a larger unlabeled pool. By leveraging recent advances in scalable ensemble training, our method scales to large pretrained models, with computational costs comparable to fine-tuning a single model. We empirically validate HyRe in several underspecified scenarios, including personalization tasks and settings with distribution shifts. Additionally, with just five preference pairs from each target distribution, the same ensemble adapted via HyRe outperforms the prior state-of-the-art 2B-parameter reward model accuracy across 18 evaluation distributions.

Related papers

• Debiased Sample Selection for Combating Noisy Labels [24.296451733127956]
  We propose a noIse-Tolerant Expert Model (ITEM) for debiased learning in sample selection. Specifically, to mitigate the training bias, we design a robust network architecture that integrates with multiple experts. By training on the mixture of two class-discriminative mini-batches, the model mitigates the effect of the imbalanced training set.
  arXiv  Detail & Related papers  (2024-01-24T10:37:28Z)
• Universal Semi-supervised Model Adaptation via Collaborative Consistency Training [92.52892510093037]
  We introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA) We propose a collaborative consistency training framework that regularizes the prediction consistency between two models. Experimental results demonstrate the effectiveness of our method on several benchmark datasets.
  arXiv  Detail & Related papers  (2023-07-07T08:19:40Z)
• RanPAC: Random Projections and Pre-trained Models for Continual Learning [59.07316955610658]
  Continual learning (CL) aims to learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. We propose a concise and effective approach for CL with pre-trained models.
  arXiv  Detail & Related papers  (2023-07-05T12:49:02Z)
• LPT: Long-tailed Prompt Tuning for Image Classification [178.52948452353834]
  We introduce several trainable prompts into a frozen pretrained model to adapt it to long-tailed data. In phase 1, we train the shared prompt via supervised prompt tuning to adapt a pretrained model to the desired long-tailed domain. In phase 2, we use the learnt shared prompt as query to select a small best matched set for a group of similar samples.
  arXiv  Detail & Related papers  (2022-10-03T15:47:02Z)
• Lightweight Conditional Model Extrapolation for Streaming Data under Class-Prior Shift [27.806085423595334]
  We introduce LIMES, a new method for learning with non-stationary streaming data. We learn a single set of model parameters from which a specific classifier for any specific data distribution is derived. Experiments on a set of exemplary tasks using Twitter data show that LIMES achieves higher accuracy than alternative approaches.
  arXiv  Detail & Related papers  (2022-06-10T15:19:52Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Uncertainty Estimation for Language Reward Models [5.33024001730262]
  Language models can learn a range of capabilities from unsupervised training on text corpora. It is often easier for humans to choose between options than to provide labeled data, and prior work has achieved state-of-the-art performance by training a reward model from such preference comparisons. We seek to address these problems via uncertainty estimation, which can improve sample efficiency and robustness using active learning and risk-averse reinforcement learning.
  arXiv  Detail & Related papers  (2022-03-14T20:13:21Z)
• Adaptive Consistency Regularization for Semi-Supervised Transfer Learning [31.66745229673066]
  We consider semi-supervised learning and transfer learning jointly, leading to a more practical and competitive paradigm. To better exploit the value of both pre-trained weights and unlabeled target examples, we introduce adaptive consistency regularization. Our proposed adaptive consistency regularization outperforms state-of-the-art semi-supervised learning techniques such as Pseudo Label, Mean Teacher, and MixMatch.
  arXiv  Detail & Related papers  (2021-03-03T05:46:39Z)
• Deep Ensembles for Low-Data Transfer Learning [21.578470914935938]
  We study different ways of creating ensembles from pre-trained models. We show that the nature of pre-training itself is a performant source of diversity. We propose a practical algorithm that efficiently identifies a subset of pre-trained models for any downstream dataset.
  arXiv  Detail & Related papers  (2020-10-14T07:59:00Z)
• The Right Tool for the Job: Matching Model and Instance Complexities [62.95183777679024]
  As NLP models become larger, executing a trained model requires significant computational resources incurring monetary and environmental costs. We propose a modification to contextual representation fine-tuning which, during inference, allows for an early (and fast) "exit" We test our proposed modification on five different datasets in two tasks: three text classification datasets and two natural language inference benchmarks.
  arXiv  Detail & Related papers  (2020-04-16T04:28:08Z)

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.