SimpleStrat: Diversifying Language Model Generation with Stratification

• URL: http://arxiv.org/abs/2410.09038v2
• Date: Mon, 14 Oct 2024 17:32:26 GMT
• Title: SimpleStrat: Diversifying Language Model Generation with Stratification
• Authors: Justin Wong, Yury Orlovskiy, Michael Luo, Sanjit A. Seshia, Joseph E. Gonzalez,
• Abstract summary: Prior approaches rely on increasing temperature to increase diversity. We show this approach produces lower quality individual generations as temperature increases. We propose SimpleStrat, an alternative approach that uses the language model itself to partition the space into strata.
• Score: 26.933029655072488
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating diverse responses from large language models (LLMs) is crucial for applications such as planning/search and synthetic data generation, where diversity provides distinct answers across generations. Prior approaches rely on increasing temperature to increase diversity. However, contrary to popular belief, we show not only does this approach produce lower quality individual generations as temperature increases, but it depends on model's next-token probabilities being similar to the true distribution of answers. We propose SimpleStrat, an alternative approach that uses the language model itself to partition the space into strata. At inference, a random stratum is selected and a sample drawn from within the strata. To measure diversity, we introduce CoverageQA, a dataset of underspecified questions with multiple equally plausible answers, and assess diversity by measuring KL Divergence between the output distribution and uniform distribution over valid ground truth answers. As computing probability per response/solution for proprietary models is infeasible, we measure recall on ground truth solutions. Our evaluation show using SimpleStrat achieves higher recall by 0.05 compared to GPT-4o and 0.36 average reduction in KL Divergence compared to Llama 3.

Related papers

• DistPred: A Distribution-Free Probabilistic Inference Method for Regression and Forecasting [14.390842560217743]
  We propose a novel approach called DistPred for regression and forecasting tasks. We transform proper scoring rules that measure the discrepancy between the predicted distribution and the target distribution into a differentiable discrete form. This allows the model to sample numerous samples in a single forward pass to estimate the potential distribution of the response variable.
  arXiv  Detail & Related papers  (2024-06-17T10:33:00Z)
• Relaxed Quantile Regression: Prediction Intervals for Asymmetric Noise [51.87307904567702]
  Quantile regression is a leading approach for obtaining such intervals via the empirical estimation of quantiles in the distribution of outputs. We propose Relaxed Quantile Regression (RQR), a direct alternative to quantile regression based interval construction that removes this arbitrary constraint. We demonstrate that this added flexibility results in intervals with an improvement in desirable qualities.
  arXiv  Detail & Related papers  (2024-06-05T13:36:38Z)
• Estimating Unknown Population Sizes Using the Hypergeometric Distribution [1.03590082373586]
  We tackle the challenge of estimating discrete distributions when both the total population size and the sizes of its constituent categories are unknown. We develop our approach to account for a data generating process where the ground-truth is a mixture of distributions conditional on a continuous latent variable. Empirical data simulation demonstrates that our method outperforms other likelihood functions used to model count data.
  arXiv  Detail & Related papers  (2024-02-22T01:53:56Z)
• Optimal Multi-Distribution Learning [88.3008613028333]
  Multi-distribution learning seeks to learn a shared model that minimizes the worst-case risk across $k$ distinct data distributions. We propose a novel algorithm that yields an varepsilon-optimal randomized hypothesis with a sample complexity on the order of (d+k)/varepsilon2.
  arXiv  Detail & Related papers  (2023-12-08T16:06:29Z)
• Confidence-Based Model Selection: When to Take Shortcuts for Subpopulation Shifts [119.22672589020394]
  We propose COnfidence-baSed MOdel Selection (CosMoS), where model confidence can effectively guide model selection. We evaluate CosMoS on four datasets with spurious correlations, each with multiple test sets with varying levels of data distribution shift.
  arXiv  Detail & Related papers  (2023-06-19T18:48:15Z)
• Tailoring Language Generation Models under Total Variation Distance [55.89964205594829]
  The standard paradigm of neural language generation adopts maximum likelihood estimation (MLE) as the optimizing method. We develop practical bounds to apply it to language generation. We introduce the TaiLr objective that balances the tradeoff of estimating TVD.
  arXiv  Detail & Related papers  (2023-02-26T16:32:52Z)
• Learning Multivariate CDFs and Copulas using Tensor Factorization [39.24470798045442]
  Learning the multivariate distribution of data is a core challenge in statistics and machine learning. In this work, we aim to learn multivariate cumulative distribution functions (CDFs), as they can handle mixed random variables. We show that any grid sampled version of a joint CDF of mixed random variables admits a universal representation as a naive Bayes model. We demonstrate the superior performance of the proposed model in several synthetic and real datasets and applications including regression, sampling and data imputation.
  arXiv  Detail & Related papers  (2022-10-13T16:18:46Z)
• Walk for Learning: A Random Walk Approach for Federated Learning from Heterogeneous Data [17.978941229970886]
  We focus on Federated Learning (FL) as a canonical application. One of the main challenges of FL is the communication bottleneck between the nodes and the parameter server. We present an adaptive random walk learning algorithm.
  arXiv  Detail & Related papers  (2022-06-01T19:53:24Z)
• Multivariate Probabilistic Regression with Natural Gradient Boosting [63.58097881421937]
  We propose a Natural Gradient Boosting (NGBoost) approach based on nonparametrically modeling the conditional parameters of the multivariate predictive distribution. Our method is robust, works out-of-the-box without extensive tuning, is modular with respect to the assumed target distribution, and performs competitively in comparison to existing approaches.
  arXiv  Detail & Related papers  (2021-06-07T17:44:49Z)
• Nonlinear Distribution Regression for Remote Sensing Applications [6.664736150040092]
  In many remote sensing applications one wants to estimate variables or parameters of interest from observations. Standard algorithms such as neural networks, random forests or Gaussian processes are readily available to relate to the two. This paper introduces a nonlinear (kernel-based) method for distribution regression that solves the previous problems without making any assumption on the statistics of the grouped data.
  arXiv  Detail & Related papers  (2020-12-07T22:04:43Z)
• AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
  We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch. The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level. The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
  arXiv  Detail & Related papers  (2020-01-15T18:32:06Z)

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.