Can Instruction Fine-Tuned Language Models Identify Social Bias through Prompting?

Omkar Dige, Jacob-Junqi Tian, David Emerson, Faiza Khan Khattak
7/19/2023
cs.CLcs.AIcs.CY

No confident code implementation found for this paper. 2 possible matches can be shown below.

Abstract

As the breadth and depth of language model applications continue to expand rapidly, it is increasingly important to build efficient frameworks for measuring and mitigating the learned or inherited social biases of these models. In this paper, we present our work on evaluating instruction fine-tuned language models' ability to identify bias through zero-shot prompting, including Chain-of-Thought (CoT) prompts. Across LLaMA and its two instruction fine-tuned versions, Alpaca 7B performs best on the bias identification task with an accuracy of 56.7%. We also demonstrate that scaling up LLM size and data diversity could lead to further performance gain. This is a work-in-progress presenting the first component of our bias mitigation framework. We will keep updating this work as we get more results.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Social Bias Evaluation for Large Language Models Requires Prompt Variations

89% match1 repo2024

Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection

88% match1 repo12025

Fine-Grained Bias Detection in LLM: Enhancing detection mechanisms for nuanced biases

88% match2025

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

88% match2024

BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs

87% match2024

Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models

87% match1 repo42024

Cite this paper

@article{dige2023instruction,
  title  = {Can Instruction Fine-Tuned Language Models Identify Social Bias through Prompting?},
  author = {Omkar Dige and Jacob-Junqi Tian and David Emerson and Faiza Khan Khattak},
  year   = {2023},
  eprint = {2307.10472},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.10472v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.10472.svg)](https://codeofpaper.com/paper/2307.10472)

Discussion