Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach

• URL: http://arxiv.org/abs/2412.11679v1
• Date: Mon, 16 Dec 2024 11:38:23 GMT
• Title: Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach
• Authors: Daiki Shirafuji, Makoto Takenaka, Shinya Taguchi,
• Abstract summary: We propose the Bias Vector'' method for the mitigation of these LM biases. The three main steps of our approach involve: (1) continual training the pre-trained LMs on biased data using masked language modeling; (2) constructing the Bias Vector as the difference between the weights of the biased LMs and those of pre-trained LMs; and (3) subtracting the Bias Vector from the weights of the pre-trained LMs for debiasing.
• Score: 0.4915744683251149
• License:
• Abstract: The use of language models (LMs) has increased considerably in recent years, and the biases and stereotypes in training data that are reflected in the LM outputs are causing social problems. In this paper, inspired by the task arithmetic, we propose the ``Bias Vector'' method for the mitigation of these LM biases. The Bias Vector method does not require manually created debiasing data. The three main steps of our approach involve: (1) continual training the pre-trained LMs on biased data using masked language modeling; (2) constructing the Bias Vector as the difference between the weights of the biased LMs and those of pre-trained LMs; and (3) subtracting the Bias Vector from the weights of the pre-trained LMs for debiasing. We evaluated the Bias Vector method on the SEAT across three LMs and confirmed an average improvement of 0.177 points. We demonstrated that the Bias Vector method does not degrade the LM performance on downstream tasks in the GLUE benchmark. In addition, we examined the impact of scaling factors, which control the magnitudes of Bias Vectors, with effect sizes on the SEAT and conducted a comprehensive evaluation of our debiased LMs across both the SEAT and GLUE benchmarks.

Related papers

• How far can bias go? -- Tracing bias from pretraining data to alignment [54.51310112013655]
  This study examines the correlation between gender-occupation bias in pre-training data and their manifestation in LLMs. Our findings reveal that biases present in pre-training data are amplified in model outputs.
  arXiv  Detail & Related papers  (2024-11-28T16:20:25Z)
• Post-hoc Reward Calibration: A Case Study on Length Bias [28.266675778940133]
  Reward models (RMs) can develop biases by exploiting spurious correlations in their training data. These biases can lead to incorrect output rankings, sub-optimal model evaluations, and the amplification of undesirable behaviours. This paper addresses the challenge of correcting such biases without additional data and training.
  arXiv  Detail & Related papers  (2024-09-25T22:30:42Z)
• REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning [18.064064773660174]
  We introduce REFINE-LM, a debiasing method that uses reinforcement learning to handle different types of biases without any fine-tuning. By training a simple model on top of the word probability distribution of a LM, our bias reinforcement learning method enables model debiasing without human annotations. Experiments conducted on a wide range of models, including several LMs, show that our method significantly reduces stereotypical biases while preserving LMs performance.
  arXiv  Detail & Related papers  (2024-08-18T14:08:31Z)
• CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models [58.57987316300529]
  Large Language Models (LLMs) are increasingly deployed to handle various natural language processing (NLP) tasks. To evaluate the biases exhibited by LLMs, researchers have recently proposed a variety of datasets. We propose CEB, a Compositional Evaluation Benchmark that covers different types of bias across different social groups and tasks.
  arXiv  Detail & Related papers  (2024-07-02T16:31:37Z)
• Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement [75.7148545929689]
  Large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others. We formally define LLM's self-bias - the tendency to favor its own generation. We analyze six LLMs on translation, constrained text generation, and mathematical reasoning tasks.
  arXiv  Detail & Related papers  (2024-02-18T03:10:39Z)
• Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models [7.089534153472173]
  We propose a null-input prompting method to calibrate intrinsic bias encoded in pre-trained language models. Our method significantly improves zero/few-shot learning performance of LMs for both in-context learning and prompt-based fine-tuning.
  arXiv  Detail & Related papers  (2024-02-15T22:54:24Z)
• The Gaps between Pre-train and Downstream Settings in Bias Evaluation and Debiasing [74.7319697510621]
  In-Context Learning (ICL) induces smaller changes to PLMs compared to FT-based debiasing methods. ICL-based debiasing methods show a higher correlation between intrinsic and extrinsic bias scores compared to FT-based methods.
  arXiv  Detail & Related papers  (2024-01-16T17:15:08Z)
• Self-Supervised Position Debiasing for Large Language Models [39.261233221850155]
  We propose a self-supervised position debiasing (SOD) framework to mitigate position bias for large language models (LLMs) Experiments on eight datasets and five tasks show that SOD consistently outperforms existing methods in mitigating three types of position biases.
  arXiv  Detail & Related papers  (2024-01-02T14:12:41Z)
• Debiasing Algorithm through Model Adaptation [5.482673673984126]
  We perform causal analysis to identify problematic model components and discover that mid-upper feed-forward layers are most prone to convey bias. Based on the analysis results, we intervene in the model by applying a linear projection to the weight matrices of these layers. Our titular method, DAMA, significantly decreases bias as measured by diverse metrics while maintaining the model's performance on downstream tasks.
  arXiv  Detail & Related papers  (2023-10-29T05:50:03Z)
• Making Pre-trained Language Models both Task-solvers and Self-calibrators [52.98858650625623]
  Pre-trained language models (PLMs) serve as backbones for various real-world systems. Previous work shows that introducing an extra calibration task can mitigate this issue. We propose a training algorithm LM-TOAST to tackle the challenges.
  arXiv  Detail & Related papers  (2023-07-21T02:51:41Z)
• Language Model Prior for Low-Resource Neural Machine Translation [85.55729693003829]
  We propose a novel approach to incorporate a LM as prior in a neural translation model (TM) We add a regularization term, which pushes the output distributions of the TM to be probable under the LM prior. Results on two low-resource machine translation datasets show clear improvements even with limited monolingual data.
  arXiv  Detail & Related papers  (2020-04-30T16:29:56Z)

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.