LMD3: Language Model Data Density Dependence

• URL: http://arxiv.org/abs/2405.06331v1
• Date: Fri, 10 May 2024 09:03:27 GMT
• Title: LMD3: Language Model Data Density Dependence
• Authors: John Kirchenbauer, Garrett Honke, Gowthami Somepalli, Jonas Geiping, Daphne Ippolito, Katherine Lee, Tom Goldstein, David Andre,
• Abstract summary: We develop a methodology for analyzing language model task performance at the individual example level based on training data density estimation. Experiments with paraphrasing as a controlled intervention on finetuning data demonstrate that increasing the support in the training distribution for specific test queries results in a measurable increase in density. We conclude that our framework can provide statistical evidence of the dependence of a target model's predictions on subsets of its training data.
• Score: 78.76731603461832
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We develop a methodology for analyzing language model task performance at the individual example level based on training data density estimation. Experiments with paraphrasing as a controlled intervention on finetuning data demonstrate that increasing the support in the training distribution for specific test queries results in a measurable increase in density, which is also a significant predictor of the performance increase caused by the intervention. Experiments with pretraining data demonstrate that we can explain a significant fraction of the variance in model perplexity via density measurements. We conclude that our framework can provide statistical evidence of the dependence of a target model's predictions on subsets of its training data, and can more generally be used to characterize the support (or lack thereof) in the training data for a given test task.

Related papers

• Towards a Theoretical Understanding of Memorization in Diffusion Models [76.85077961718875]
  Diffusion probabilistic models (DPMs) are being employed as mainstream models for Generative Artificial Intelligence (GenAI) We provide a theoretical understanding of memorization in both conditional and unconditional DPMs under the assumption of model convergence. We propose a novel data extraction method named textbfSurrogate condItional Data Extraction (SIDE) that leverages a time-dependent classifier trained on the generated data as a surrogate condition to extract training data from unconditional DPMs.
  arXiv  Detail & Related papers  (2024-10-03T13:17:06Z)
• In-Context Probing Approximates Influence Function for Data Valuation [16.404477234171733]
  We show that data valuation through in-context probing approximates influence functions for selecting training data. Our empirical findings show that in-context probing and gradient-based influence frameworks are similar in how they rank training data.
  arXiv  Detail & Related papers  (2024-07-17T02:06:56Z)
• Extracting Training Data from Unconditional Diffusion Models [76.85077961718875]
  diffusion probabilistic models (DPMs) are being employed as mainstream models for generative artificial intelligence (AI) We aim to establish a theoretical understanding of memorization in DPMs with 1) a memorization metric for theoretical analysis, 2) an analysis of conditional memorization with informative and random labels, and 3) two better evaluation metrics for measuring memorization. Based on the theoretical analysis, we propose a novel data extraction method called textbfSurrogate condItional Data Extraction (SIDE) that leverages a trained on generated data as a surrogate condition to extract training data directly from unconditional diffusion models.
  arXiv  Detail & Related papers  (2024-06-18T16:20:12Z)
• The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes [30.30769701138665]
  We introduce and explore the Mirrored Influence Hypothesis, highlighting a reciprocal nature of influence between training and test data. Specifically, it suggests that evaluating the influence of training data on test predictions can be reformulated as an equivalent, yet inverse problem. We introduce a new method for estimating the influence of training data, which requires calculating gradients for specific test samples, paired with a forward pass for each training point.
  arXiv  Detail & Related papers  (2024-02-14T03:43:05Z)
• Training Data Attribution for Diffusion Models [1.1733780065300188]
  We propose a novel solution that reveals how training data influence the output of diffusion models through the use of ensembles. In our approach individual models in an encoded ensemble are trained on carefully engineered splits of the overall training data to permit the identification of influential training examples. The resulting model ensembles enable efficient ablation of training data influence, allowing us to assess the impact of training data on model outputs.
  arXiv  Detail & Related papers  (2023-06-03T18:36:12Z)
• Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions [59.284907093349425]
  Large amounts of training data are one of the major reasons for the high performance of state-of-the-art NLP models. We provide a language for describing how training data influences predictions, through a causal framework. Our framework bypasses the need to retrain expensive models and allows us to estimate causal effects based on observational data alone.
  arXiv  Detail & Related papers  (2022-07-28T17:36:24Z)
• Data-SUITE: Data-centric identification of in-distribution incongruous examples [81.21462458089142]
  Data-SUITE is a data-centric framework to identify incongruous regions of in-distribution (ID) data. We empirically validate Data-SUITE's performance and coverage guarantees.
  arXiv  Detail & Related papers  (2022-02-17T18:58:31Z)
• Training Data Leakage Analysis in Language Models [6.843491191969066]
  We introduce a methodology that investigates identifying the user content in the training data that could be leaked under a strong and realistic threat model. We propose two metrics to quantify user-level data leakage by measuring a model's ability to produce unique sentence fragments within training data.
  arXiv  Detail & Related papers  (2021-01-14T00:57:32Z)
• Unsupervised neural adaptation model based on optimal transport for spoken language identification [54.96267179988487]
  Due to the mismatch of statistical distributions of acoustic speech between training and testing sets, the performance of spoken language identification (SLID) could be drastically degraded. We propose an unsupervised neural adaptation model to deal with the distribution mismatch problem for SLID.
  arXiv  Detail & Related papers  (2020-12-24T07:37:19Z)

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.