Probing as Quantifying the Inductive Bias of Pre-trained Representations
- URL: http://arxiv.org/abs/2110.08388v1
- Date: Fri, 15 Oct 2021 22:01:16 GMT
- Title: Probing as Quantifying the Inductive Bias of Pre-trained Representations
- Authors: Alexander Immer, Lucas Torroba Hennigen, Vincent Fortuin, Ryan
Cotterell
- Abstract summary: We present a novel framework for probing where the goal is to evaluate the inductive bias of representations for a particular task.
We apply our framework to a series of token-, arc-, and sentence-level tasks.
- Score: 99.93552997506438
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Pre-trained contextual representations have led to dramatic performance
improvements on a range of downstream tasks. This has motivated researchers to
quantify and understand the linguistic information encoded in them. In general,
this is done by probing, which consists of training a supervised model to
predict a linguistic property from said representations. Unfortunately, this
definition of probing has been subject to extensive criticism, and can lead to
paradoxical or counter-intuitive results. In this work, we present a novel
framework for probing where the goal is to evaluate the inductive bias of
representations for a particular task, and provide a practical avenue to do
this using Bayesian inference. We apply our framework to a series of token-,
arc-, and sentence-level tasks. Our results suggest that our framework solves
problems of previous approaches and that fastText can offer a better inductive
bias than BERT in certain situations.
Related papers
- Manual Verbalizer Enrichment for Few-Shot Text Classification [1.860409237919611]
acrshortmave is an approach for verbalizer construction by enrichment of class labels.
Our model achieves state-of-the-art results while using significantly fewer resources.
arXiv Detail & Related papers (2024-10-08T16:16:47Z) - How Interpretable are Reasoning Explanations from Prompting Large Language Models? [34.4659592398593]
We present a comprehensive and multifaceted evaluation of interpretability, examining not only faithfulness but also robustness and utility across commonsense reasoning benchmarks.
In addition, we introduce a simple interpretability alignment technique termed Self-Entailment-Alignment Chain-of-thought, that yields more than 70% improvements across multiple dimensions of interpretability.
arXiv Detail & Related papers (2024-02-19T06:11:28Z) - Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks [71.19560970717495]
Recent language models show impressive performance across a wide range of tasks.
Are these skills general and transferable, or specialized to specific tasks seen during pretraining?
We propose an evaluation framework based on "counterfactual" task variants that deviate from the default assumptions underlying standard tasks.
arXiv Detail & Related papers (2023-07-05T17:50:42Z) - Counterfactuals of Counterfactuals: a back-translation-inspired approach
to analyse counterfactual editors [3.4253416336476246]
We focus on the analysis of counterfactual, contrastive explanations.
We propose a new back translation-inspired evaluation methodology.
We show that by iteratively feeding the counterfactual to the explainer we can obtain valuable insights into the behaviour of both the predictor and the explainer models.
arXiv Detail & Related papers (2023-05-26T16:04:28Z) - Inverse Dynamics Pretraining Learns Good Representations for Multitask
Imitation [66.86987509942607]
We evaluate how such a paradigm should be done in imitation learning.
We consider a setting where the pretraining corpus consists of multitask demonstrations.
We argue that inverse dynamics modeling is well-suited to this setting.
arXiv Detail & Related papers (2023-05-26T14:40:46Z) - Fairness-guided Few-shot Prompting for Large Language Models [93.05624064699965]
In-context learning can suffer from high instability due to variations in training examples, example order, and prompt formats.
We introduce a metric to evaluate the predictive bias of a fixed prompt against labels or a given attributes.
We propose a novel search strategy based on the greedy search to identify the near-optimal prompt for improving the performance of in-context learning.
arXiv Detail & Related papers (2023-03-23T12:28:25Z) - A Latent-Variable Model for Intrinsic Probing [93.62808331764072]
We propose a novel latent-variable formulation for constructing intrinsic probes.
We find empirical evidence that pre-trained representations develop a cross-lingually entangled notion of morphosyntax.
arXiv Detail & Related papers (2022-01-20T15:01:12Z) - Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning [57.4036085386653]
We show that prompt-based models for sentence pair classification tasks still suffer from a common pitfall of adopting inferences based on lexical overlap.
We then show that adding a regularization that preserves pretraining weights is effective in mitigating this destructive tendency of few-shot finetuning.
arXiv Detail & Related papers (2021-09-09T10:10:29Z) - Improved Speech Representations with Multi-Target Autoregressive
Predictive Coding [23.424410568555547]
We extend the hypothesis that hidden states that can accurately predict future frames are a useful representation for many downstream tasks.
We propose an auxiliary objective that serves as a regularization to improve generalization of the future frame prediction task.
arXiv Detail & Related papers (2020-04-11T01:09:36Z)
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.