course/pr_1021/en/chapter1/9.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Bias and limitations&quot;,&quot;local&quot;:&quot;bias-and-limitations&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}">
		<link href="/docs/course/pr_1021/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/course/pr_1021/en/_app/immutable/entry/start.3d2e2978.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/en/_app/immutable/chunks/scheduler.37c15a92.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/en/_app/immutable/chunks/singletons.7a9af56d.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/en/_app/immutable/chunks/index.18351ede.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/en/_app/immutable/chunks/paths.692f56cf.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/en/_app/immutable/entry/app.d60bb0c9.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/en/_app/immutable/chunks/index.7cb9c9b8.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/en/_app/immutable/nodes/0.bbc29778.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/en/_app/immutable/nodes/13.6eb85ee6.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/en/_app/immutable/chunks/CodeBlock.abae2786.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/en/_app/immutable/chunks/CourseFloatingBanner.df82c153.js">
		<link rel="modulepreload" href="/docs/course/pr_1021/en/_app/immutable/chunks/getInferenceSnippets.a2135f3c.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Bias and limitations&quot;,&quot;local&quot;:&quot;bias-and-limitations&quot;,&quot;sections&quot;:[],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>  <h1 class="relative group"><a id="bias-and-limitations" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#bias-and-limitations"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Bias and limitations</span></h1>  <div class="flex space-x-1 absolute z-10 right-0 top-0"><a href="https://discuss.huggingface.co/t/chapter-1-questions" target="_blank"><img alt="Ask a Question" class="!m-0" src="https://img.shields.io/badge/Ask%20a%20question-ffcb4c.svg?logo=data:image/svg+xml;base64,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"></a> <a href="https://colab.research.google.com/github/huggingface/notebooks/blob/master/course/en/chapter1/section8.ipynb" target="_blank"><img alt="Open In Colab" class="!m-0" src="https://colab.research.google.com/assets/colab-badge.svg"></a> <a href="https://studiolab.sagemaker.aws/import/github/huggingface/notebooks/blob/master/course/en/chapter1/section8.ipynb" target="_blank"><img alt="Open In Studio Lab" class="!m-0" src="https://studiolab.sagemaker.aws/studiolab.svg"></a></div> <p data-svelte-h="svelte-1q5fkuw">If your intent is to use a pretrained model or a fine-tuned version in production, please be aware that, while these models are powerful tools, they come with limitations. The biggest of these is that, to enable pretraining on large amounts of data, researchers often scrape all the content they can find, taking the best as well as the worst of what is available on the internet.</p> <p data-svelte-h="svelte-lenr95">To give a quick illustration, let’s go back the example of a <code>fill-mask</code> pipeline with the BERT model:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> pipeline

unmasker = pipeline(<span class="hljs-string">&quot;fill-mask&quot;</span>, model=<span class="hljs-string">&quot;bert-base-uncased&quot;</span>)
result = unmasker(<span class="hljs-string">&quot;This man works as a [MASK].&quot;</span>)
<span class="hljs-built_in">print</span>([r[<span class="hljs-string">&quot;token_str&quot;</span>] <span class="hljs-keyword">for</span> r <span class="hljs-keyword">in</span> result])

result = unmasker(<span class="hljs-string">&quot;This woman works as a [MASK].&quot;</span>)
<span class="hljs-built_in">print</span>([r[<span class="hljs-string">&quot;token_str&quot;</span>] <span class="hljs-keyword">for</span> r <span class="hljs-keyword">in</span> result])<!-- HTML_TAG_END --></pre></div> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START -->[<span class="hljs-string">&#x27;lawyer&#x27;</span>, <span class="hljs-string">&#x27;carpenter&#x27;</span>, <span class="hljs-string">&#x27;doctor&#x27;</span>, <span class="hljs-string">&#x27;waiter&#x27;</span>, <span class="hljs-string">&#x27;mechanic&#x27;</span>]
[<span class="hljs-string">&#x27;nurse&#x27;</span>, <span class="hljs-string">&#x27;waitress&#x27;</span>, <span class="hljs-string">&#x27;teacher&#x27;</span>, <span class="hljs-string">&#x27;maid&#x27;</span>, <span class="hljs-string">&#x27;prostitute&#x27;</span>]<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-heqc6c">When asked to fill in the missing word in these two sentences, the model gives only one gender-free answer (waiter/waitress). The others are work occupations usually associated with one specific gender — and yes, prostitute ended up in the top 5 possibilities the model associates with “woman” and “work.” This happens even though BERT is one of the rare Transformer models not built by scraping data from all over the internet, but rather using apparently neutral data (it’s trained on the <a href="https://huggingface.co/datasets/wikipedia" rel="nofollow">English Wikipedia</a> and <a href="https://huggingface.co/datasets/bookcorpus" rel="nofollow">BookCorpus</a> datasets).</p> <p data-svelte-h="svelte-u698k">When you use these tools, you therefore need to keep in the back of your mind that the original model you are using could very easily generate sexist, racist, or homophobic content. Fine-tuning the model on your data won’t make this intrinsic bias disappear.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/course/blob/main/chapters/en/chapter1/9.mdx" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span> <span data-svelte-h="svelte-1dajgef"><span class="underline ml-1.5">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_engvle = {
						assets: "/docs/course/pr_1021/en",
						base: "/docs/course/pr_1021/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/course/pr_1021/en/_app/immutable/entry/start.3d2e2978.js"),
						import("/docs/course/pr_1021/en/_app/immutable/entry/app.d60bb0c9.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 13],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>