Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination

• URL: http://arxiv.org/abs/2311.09627v2
• Date: Wed, 5 Jun 2024 05:49:19 GMT
• Title: Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination
• Authors: Nakyeong Yang, Taegwan Kang, Jungkyu Choi, Honglak Lee, Kyomin Jung,
• Abstract summary: We propose a novel and practical bias mitigation method, CRISPR, to eliminate bias neurons of language models in instruction-following settings. CRISPR automatically determines biased outputs and categorizes neurons that affect the biased outputs as bias neurons using an explainability method. Experimental results demonstrate the effectiveness of our method in mitigating biases under zero-shot instruction-following settings without losing the model's task performance and existing knowledge.
• Score: 54.865941973768905
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Instruction-following language models often show undesirable biases. These undesirable biases may be accelerated in the real-world usage of language models, where a wide range of instructions is used through zero-shot example prompting. To solve this problem, we first define the bias neuron, which significantly affects biased outputs, and prove its existence empirically. Furthermore, we propose a novel and practical bias mitigation method, CRISPR, to eliminate bias neurons of language models in instruction-following settings. CRISPR automatically determines biased outputs and categorizes neurons that affect the biased outputs as bias neurons using an explainability method. Experimental results demonstrate the effectiveness of our method in mitigating biases under zero-shot instruction-following settings without losing the model's task performance and existing knowledge. The experimental results reveal the generalizability of our method as it shows robustness under various instructions and datasets. Surprisingly, our method can mitigate the bias in language models by eliminating only a few neurons (at least three).

Related papers

• The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models [78.69526166193236]
  Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases. We propose sc Social Bias Neurons to accurately pinpoint units (i.e., neurons) in a language model that can be attributed to undesirable behavior, such as social bias. As measured by prior metrics from StereoSet, our model achieves a higher degree of fairness while maintaining language modeling ability with low cost.
  arXiv  Detail & Related papers  (2024-06-14T15:41:06Z)
• Projective Methods for Mitigating Gender Bias in Pre-trained Language Models [10.418595661963062]
  Projective methods are fast to implement, use a small number of saved parameters, and make no updates to the existing model parameters. We find that projective methods can be effective at both intrinsic bias and downstream bias mitigation, but that the two outcomes are not necessarily correlated.
  arXiv  Detail & Related papers  (2024-03-27T17:49:31Z)
• Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes [73.12947922129261]
  We leverage the zero-shot capabilities of large language models to reduce stereotyping. We show that self-debiasing can significantly reduce the degree of stereotyping across nine different social groups. We hope this work opens inquiry into other zero-shot techniques for bias mitigation.
  arXiv  Detail & Related papers  (2024-02-03T01:40:11Z)
• Fast Model Debias with Machine Unlearning [54.32026474971696]
  Deep neural networks might behave in a biased manner in many real-world scenarios. Existing debiasing methods suffer from high costs in bias labeling or model re-training. We propose a fast model debiasing framework (FMD) which offers an efficient approach to identify, evaluate and remove biases.
  arXiv  Detail & Related papers  (2023-10-19T08:10:57Z)
• Feature-Level Debiased Natural Language Understanding [86.8751772146264]
  Existing natural language understanding (NLU) models often rely on dataset biases to achieve high performance on specific datasets. We propose debiasing contrastive learning (DCT) to mitigate biased latent features and neglect the dynamic nature of bias. DCT outperforms state-of-the-art baselines on out-of-distribution datasets while maintaining in-distribution performance.
  arXiv  Detail & Related papers  (2022-12-11T06:16:14Z)
• Learning Debiased Models with Dynamic Gradient Alignment and Bias-conflicting Sample Mining [39.00256193731365]
  Deep neural networks notoriously suffer from dataset biases which are detrimental to model robustness, generalization and fairness. We propose a two-stage debiasing scheme to combat against the intractable unknown biases.
  arXiv  Detail & Related papers  (2021-11-25T14:50:10Z)
• Debiasing Methods in Natural Language Understanding Make Bias More Accessible [28.877572447481683]
  Recent debiasing methods in natural language understanding (NLU) improve performance on such datasets by pressuring models into making unbiased predictions. We propose a general probing-based framework that allows for post-hoc interpretation of biases in language models. We show that, counter-intuitively, the more a language model is pushed towards a debiased regime, the more bias is actually encoded in its inner representations.
  arXiv  Detail & Related papers  (2021-09-09T08:28:22Z)
• A Generative Approach for Mitigating Structural Biases in Natural Language Inference [24.44419010439227]
  In this work, we reformulate the NLI task as a generative task, where a model is conditioned on the biased subset of the input and the label. We show that this approach is highly robust to large amounts of bias. We find that generative models are difficult to train and they generally perform worse than discriminative baselines.
  arXiv  Detail & Related papers  (2021-08-31T17:59:45Z)
• Learning from others' mistakes: Avoiding dataset biases without modeling them [111.17078939377313]
  State-of-the-art natural language processing (NLP) models often learn to model dataset biases and surface form correlations instead of features that target the intended task. Previous work has demonstrated effective methods to circumvent these issues when knowledge of the bias is available. We show a method for training models that learn to ignore these problematic correlations.
  arXiv  Detail & Related papers  (2020-12-02T16:10:54Z)

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.