Self-Supervised Position Debiasing for Large Language Models
- URL: http://arxiv.org/abs/2401.01218v3
- Date: Sat, 29 Jun 2024 05:20:09 GMT
- Title: Self-Supervised Position Debiasing for Large Language Models
- Authors: Zhongkun Liu, Zheng Chen, Mengqi Zhang, Zhaochun Ren, Pengjie Ren, Zhumin Chen,
- Abstract summary: 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.
- Score: 39.261233221850155
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Fine-tuning has been demonstrated to be an effective method to improve the domain performance of large language models (LLMs). However, LLMs might fit the dataset bias and shortcuts for prediction, leading to poor generation performance. Previous works have proven that LLMs are prone to exhibit position bias, i.e., leveraging information positioned at the beginning or end, or specific positional cues within the input. Existing debiasing methods for LLMs require external bias knowledge or annotated non-biased samples, which is lacking for position debiasing and impractical in reality. In this work, we propose a self-supervised position debiasing (SOD) framework to mitigate position bias for LLMs. SOD leverages unsupervised responses from pre-trained LLMs for debiasing without relying on any external knowledge. To improve the quality of unsupervised responses, we propose an objective alignment (OAM) module to prune these responses. Experiments on eight datasets and five tasks show that SOD consistently outperforms existing methods in mitigating three types of position biases. Besides, SOD achieves this by sacrificing only a small performance on biased samples, which is general and effective. To facilitate the reproducibility of the results, we share the code of all methods and datasets on https://github.com/LZKSKY/SOD.
Related papers
- BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization [0.0]
Large Language Models (LLMs) have become pivotal in advancing natural language processing, yet their potential to perpetuate biases poses significant concerns.
This paper introduces a new framework employing Direct Preference Optimization (DPO) to mitigate gender, racial, and religious biases in English text.
By developing a loss function that favors less biased over biased completions, our approach cultivates a preference for respectful and non-discriminatory language.
arXiv Detail & Related papers (2024-07-18T22:32:20Z) - Are Large Language Models Strategic Decision Makers? A Study of Performance and Bias in Two-Player Non-Zero-Sum Games [56.70628673595041]
Large Language Models (LLMs) have been increasingly used in real-world settings, yet their strategic abilities remain largely unexplored.
We investigate LLMs' behaviour in strategic games, Stag Hunt and Prisoner Dilemma, analyzing performance variations under different settings and prompts.
Our results show that the tested state-of-the-art LLMs exhibit at least one of the following systematic biases: (1) positional bias, (2) payoff bias, or (3) behavioural bias.
arXiv Detail & Related papers (2024-07-05T12:30:02Z) - UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation [12.04811490937078]
We investigate how feedforward neural networks (FFNs) and attention heads result in the bias of large language models (LLMs)
To mitigate these biases, we introduce UniBias, an inference-only method that effectively identifies and eliminates biased FFN vectors and attention heads.
arXiv Detail & Related papers (2024-05-31T03:59:15Z) - Position-Aware Parameter Efficient Fine-Tuning Approach for Reducing Positional Bias in LLMs [18.832135309689736]
Recent advances in large language models (LLMs) have enhanced their ability to process long input contexts.
Recent studies show a positional bias in LLMs, demonstrating varying performance depending on the location of useful information.
We develop a Position-Aware PAPEFT approach which is composed of a data augmentation technique and an efficient parameter adapter.
arXiv Detail & Related papers (2024-04-01T19:04:17Z) - Steering LLMs Towards Unbiased Responses: A Causality-Guided Debiasing
Framework [20.753141804841]
Large language models (LLMs) can easily generate biased and discriminative responses.
This paper focuses on social bias, tackling the association between demographic information and LLM outputs.
arXiv Detail & Related papers (2024-03-13T17:46:28Z) - Debiasing Multimodal Large Language Models [61.6896704217147]
Large Vision-Language Models (LVLMs) have become indispensable tools in computer vision and natural language processing.
Our investigation reveals a noteworthy bias in the generated content, where the output is primarily influenced by the underlying Large Language Models (LLMs) prior to the input image.
To rectify these biases and redirect the model's focus toward vision information, we introduce two simple, training-free strategies.
arXiv Detail & Related papers (2024-03-08T12:35:07Z) - ChatGPT Based Data Augmentation for Improved Parameter-Efficient
Debiasing of LLMs [69.27030571729392]
Large Language models (LLMs) exhibit harmful social biases.
This work introduces a novel approach utilizing ChatGPT to generate synthetic training data.
arXiv Detail & Related papers (2024-02-19T01:28:48Z) - 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) - 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)
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.