A Novel Interpretability Metric for Explaining Bias in Language Models: Applications on Multilingual Models from Southeast Asia

• URL: http://arxiv.org/abs/2410.15464v2
• Date: Thu, 24 Oct 2024 15:58:57 GMT
• Title: A Novel Interpretability Metric for Explaining Bias in Language Models: Applications on Multilingual Models from Southeast Asia
• Authors: Lance Calvin Lim Gamboa, Mark Lee,
• Abstract summary: We propose a novel metric to measure token-level contributions to biased behavior in pretrained language models (PLMs) Our results confirm the presence of sexist and homophobic bias in Southeast Asian PLMs. Interpretability and semantic analyses also reveal that PLM bias is strongly induced by words relating to crime, intimate relationships, and helping.
• Score: 0.3376269351435396
• License:
• Abstract: Work on bias in pretrained language models (PLMs) focuses on bias evaluation and mitigation and fails to tackle the question of bias attribution and explainability. We propose a novel metric, the $\textit{bias attribution score}$, which draws from information theory to measure token-level contributions to biased behavior in PLMs. We then demonstrate the utility of this metric by applying it on multilingual PLMs, including models from Southeast Asia which have not yet been thoroughly examined in bias evaluation literature. Our results confirm the presence of sexist and homophobic bias in Southeast Asian PLMs. Interpretability and semantic analyses also reveal that PLM bias is strongly induced by words relating to crime, intimate relationships, and helping among other discursive categories, suggesting that these are topics where PLMs strongly reproduce bias from pretraining data and where PLMs should be used with more caution.

Related papers

• Bridging the Fairness Gap: Enhancing Pre-trained Models with LLM-Generated Sentences [8.979854959662664]
  We propose enhancing fairness (Fair-Gender) in pre-trained language models (PLMs) by absorbing coherent, attribute-balanced, and semantically rich sentences. These sentences cannot be directly used for debiasing due to alignment issues and the risk of negative transfer. We address this by applying causal analysis to estimate causal effects, filtering out unaligned sentences, and identifying aligned ones for incorporation into PLMs.
  arXiv  Detail & Related papers  (2025-01-12T12:32:43Z)
• Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection [5.800102484016876]
  Large Language Models (LLMs) have been shown to exhibit various biases and stereotypes in their generated content. This paper presents a systematic framework grounded in social psychology theories to investigate explicit and implicit biases in LLMs.
  arXiv  Detail & Related papers  (2025-01-04T14:08:52Z)
• 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)
• 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)
• Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective [66.34066553400108]
  We conduct a rigorous evaluation of large language models' implicit bias towards certain demographics. Inspired by psychometric principles, we propose three attack approaches, i.e., Disguise, Deception, and Teaching. Our methods can elicit LLMs' inner bias more effectively than competitive baselines.
  arXiv  Detail & Related papers  (2024-06-20T06:42:08Z)
• Investigating Bias in LLM-Based Bias Detection: Disparities between LLMs and Human Perception [13.592532358127293]
  We investigate the presence and nature of bias within Large Language Models (LLMs) We probe whether LLMs exhibit biases, particularly in political bias prediction and text continuation tasks. We propose debiasing strategies, including prompt engineering and model fine-tuning.
  arXiv  Detail & Related papers  (2024-03-22T00:59:48Z)
• GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language Models [83.30078426829627]
  Large language models (LLMs) have gained popularity and are being widely adopted by a large user community. The existing evaluation methods have many constraints, and their results exhibit a limited degree of interpretability. We propose a bias evaluation framework named GPTBIAS that leverages the high performance of LLMs to assess bias in models.
  arXiv  Detail & Related papers  (2023-12-11T12:02:14Z)
• Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis [86.49858739347412]
  Large Language Models (LLMs) have sparked intense debate regarding the prevalence of bias in these models and its mitigation. We propose a prompt-based method for the extraction of confounding and mediating attributes which contribute to the decision process. We find that the observed disparate treatment can at least in part be attributed to confounding and mitigating attributes and model misalignment.
  arXiv  Detail & Related papers  (2023-11-15T00:02:25Z)
• Bias and Fairness in Large Language Models: A Survey [73.87651986156006]
  We present a comprehensive survey of bias evaluation and mitigation techniques for large language models (LLMs) We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing. We then unify the literature by proposing three intuitive, two for bias evaluation, and one for mitigation.
  arXiv  Detail & Related papers  (2023-09-02T00:32:55Z)
• Language-Agnostic Bias Detection in Language Models with Bias Probing [22.695872707061078]
  Pretrained language models (PLMs) are key components in NLP, but they contain strong social biases. We propose a bias probing technique called LABDet for evaluating social bias in PLMs with a robust and language-agnostic method. We find consistent patterns of nationality bias across monolingual PLMs in six languages that align with historical and political context.
  arXiv  Detail & Related papers  (2023-05-22T17:58:01Z)
• BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation [89.41378346080603]
  This work presents the first systematic study on the social bias in PLM-based metrics. We demonstrate that popular PLM-based metrics exhibit significantly higher social bias than traditional metrics on 6 sensitive attributes. In addition, we develop debiasing adapters that are injected into PLM layers, mitigating bias in PLM-based metrics while retaining high performance for evaluating text generation.
  arXiv  Detail & Related papers  (2022-10-14T08:24:11Z)

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.