MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies

• URL: http://arxiv.org/abs/2305.16958v2
• Date: Sun, 26 May 2024 20:24:55 GMT
• Title: MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies
• Authors: Shiyue Zhang, Shijie Wu, Ozan Irsoy, Steven Lu, Mohit Bansal, Mark Dredze, David Rosenberg,
• Abstract summary: Autoregressive language models are trained by minimizing the cross-entropy of the model distribution Q relative to the data distribution P. We propose learning with MixCE, an objective that mixes the forward and reverse cross-entropies. We show that the resulting models yield better generated text without complex decoding strategies.
• Score: 80.82897149158853
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autoregressive language models are trained by minimizing the cross-entropy of the model distribution Q relative to the data distribution P -- that is, minimizing the forward cross-entropy, which is equivalent to maximum likelihood estimation (MLE). We have observed that models trained in this way may "over-generalize", in the sense that they produce non-human-like text. Moreover, we believe that reverse cross-entropy, i.e., the cross-entropy of P relative to Q, is a better reflection of how a human would evaluate text generated by a model. Hence, we propose learning with MixCE, an objective that mixes the forward and reverse cross-entropies. We evaluate models trained with this objective on synthetic data settings (where P is known) and real data, and show that the resulting models yield better generated text without complex decoding strategies. Our code and models are publicly available at https://github.com/bloomberg/mixce-acl2023

Related papers

• Human Guided Learning of Transparent Regression Models [4.592493651895646]
  We present a human-in-the-loop (HIL) approach to permutation regression. The model is a gradient boosted regression model that incorporates simple human-understandable constraints. The approach, HuGuR, lets a human explore the search space of such transparent regression models.
  arXiv  Detail & Related papers  (2025-02-21T23:15:12Z)
• 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)
• Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines [74.42485647685272]
  We focus on Generative Masked Language Models (GMLMs) We train a model to fit conditional probabilities of the data distribution via masking, which are subsequently used as inputs to a Markov Chain to draw samples from the model. We adapt the T5 model for iteratively-refined parallel decoding, achieving 2-3x speedup in machine translation with minimal sacrifice in quality.
  arXiv  Detail & Related papers  (2024-07-22T18:00:00Z)
• Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences [20.629333587044012]
  We study the impact of data curation on iterated retraining of generative models. We prove that, if the data is curated according to a reward model, the expected reward of the iterative retraining procedure is maximized.
  arXiv  Detail & Related papers  (2024-06-12T21:28:28Z)
• Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoders [22.77397537980102]
  We show that we can compute a deterministic, model-agnostic posterior approximation (MAPA) of the true model's posterior. We present preliminary results on low-dimensional synthetic data that (1) MAPA captures the trend of the true posterior, and (2) our MAPA-based inference performs better density estimation with less computation than baselines.
  arXiv  Detail & Related papers  (2024-03-13T20:16:21Z)
• Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models [115.501751261878]
  Fine-tuning language models(LMs) on human-generated data remains a prevalent practice. We investigate whether we can go beyond human data on tasks where we have access to scalar feedback. We find that ReST$EM$ scales favorably with model size and significantly surpasses fine-tuning only on human data.
  arXiv  Detail & Related papers  (2023-12-11T18:17:43Z)
• Learning from aggregated data with a maximum entropy model [73.63512438583375]
  We show how a new model, similar to a logistic regression, may be learned from aggregated data only by approximating the unobserved feature distribution with a maximum entropy hypothesis. We present empirical evidence on several public datasets that the model learned this way can achieve performances comparable to those of a logistic model trained with the full unaggregated data.
  arXiv  Detail & Related papers  (2022-10-05T09:17:27Z)
• Mismatched No More: Joint Model-Policy Optimization for Model-Based RL [172.37829823752364]
  We propose a single objective for jointly training the model and the policy, such that updates to either component increases a lower bound on expected return. Our objective is a global lower bound on expected return, and this bound becomes tight under certain assumptions. The resulting algorithm (MnM) is conceptually similar to a GAN.
  arXiv  Detail & Related papers  (2021-10-06T13:43:27Z)
• Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose? [0.2836066255205732]
  We contribute to micro-data model-based reinforcement learning (MBRL) by rigorously comparing popular generative models. We find that on an environment that requires multimodal posterior predictives, mixture density nets outperform all other models by a large margin. We also found that deterministic models are on par, in fact they consistently (although non-significantly) outperform their probabilistic counterparts.
  arXiv  Detail & Related papers  (2021-07-24T11:38:25Z)
• Aligned Cross Entropy for Non-Autoregressive Machine Translation [120.15069387374717]
  We propose aligned cross entropy (AXE) as an alternative loss function for training of non-autoregressive models. AXE-based training of conditional masked language models (CMLMs) substantially improves performance on major WMT benchmarks.
  arXiv  Detail & Related papers  (2020-04-03T16:24:47Z)

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.