Speciesist Language and Nonhuman Animal Bias in English Masked Language Models

• URL: http://arxiv.org/abs/2203.05140v1
• Date: Thu, 10 Mar 2022 03:32:29 GMT
• Title: Speciesist Language and Nonhuman Animal Bias in English Masked Language Models
• Abstract summary: We analyze biases to nonhuman animals, i.e. speciesist bias, inherent in English Masked Language Models. Our code for reproducing the experiments will be made available on GitHub.
• Score: 14.373699429792687
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Various existing studies have analyzed what social biases are inherited by NLP models. These biases may directly or indirectly harm people, therefore previous studies have focused only on human attributes. If the social biases in NLP models can be indirectly harmful to humans involved, then the models can also indirectly harm nonhuman animals. However, until recently no research on social biases in NLP regarding nonhumans existed. In this paper, we analyze biases to nonhuman animals, i.e. speciesist bias, inherent in English Masked Language Models. We analyze this bias using template-based and corpus-extracted sentences which contain speciesist (or non-speciesist) language, to show that these models tend to associate harmful words with nonhuman animals. Our code for reproducing the experiments will be made available on GitHub.

Related papers

• Speciesism in AI: Evaluating Discrimination Against Animals in Large Language Models [0.0]
  We investigate whether large language models (LLMs) exhibit speciesist bias.<n>LLMs reliably detected speciesist statements but rarely condemned them.<n>We argue that expanding AI fairness and alignment frameworks to explicitly include non-human moral patients is essential.
  arXiv  Detail & Related papers  (2025-08-15T15:22:00Z)
• Surface Fairness, Deep Bias: A Comparative Study of Bias in Language Models [49.41113560646115]
  We investigate various proxy measures of bias in large language models (LLMs)<n>We find that evaluating models with pre-prompted personae on a multi-subject benchmark (MMLU) leads to negligible and mostly random differences in scores.<n>With the recent trend for LLM assistant memory and personalization, these problems open up from a different angle.
  arXiv  Detail & Related papers  (2025-06-12T08:47:40Z)
• Speciesism in Natural Language Processing Research [3.1077024712075794]
  The purpose of this study is to investigate whether there is speciesism, i.e., discrimination against nonhuman animals, in NLP research. The findings of this study suggest that speciesism exists within researchers, data, and models, respectively. Specifically, our survey and experiments show that (a) among NLP researchers, even those who study social bias in AI, do not recognize speciesism or speciesist bias; (b) among NLP data, speciesist bias is inherent in the data annotated in the datasets used to evaluate NLP models; (c) OpenAI GPTs, recent NLP models, exhibit
  arXiv  Detail & Related papers  (2024-10-18T06:09:41Z)
• Trying to be human: Linguistic traces of stochastic empathy in language models [0.2638512174804417]
  Large language models (LLMs) are crucial drivers behind the increased quality of computer-generated content. Our work tests how two important factors contribute to the human vs AI race: empathy and an incentive to appear human.
  arXiv  Detail & Related papers  (2024-10-02T15:46:40Z)
• Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Models [50.40276881893513]
  This study introduces Spoken Stereoset, a dataset specifically designed to evaluate social biases in Speech Large Language Models (SLLMs) By examining how different models respond to speech from diverse demographic groups, we aim to identify these biases. The findings indicate that while most models show minimal bias, some still exhibit slightly stereotypical or anti-stereotypical tendencies.
  arXiv  Detail & Related papers  (2024-08-14T16:55:06Z)
• The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models [78.69526166193236]
  Pre-trained Language models (PLMs) have been acknowledged to contain harmful information, such as social biases. We propose sc Social Bias Neurons to accurately pinpoint units (i.e., neurons) in a language model that can be attributed to undesirable behavior, such as social bias. As measured by prior metrics from StereoSet, our model achieves a higher degree of fairness while maintaining language modeling ability with low cost.
  arXiv  Detail & Related papers  (2024-06-14T15:41:06Z)
• White Men Lead, Black Women Help? Benchmarking Language Agency Social Biases in LLMs [58.27353205269664]
  Social biases can manifest in language agency. We introduce the novel Language Agency Bias Evaluation benchmark. We unveil language agency social biases in 3 recent Large Language Model (LLM)-generated content.
  arXiv  Detail & Related papers  (2024-04-16T12:27:54Z)
• What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations [62.91799637259657]
  Do large language models (LLMs) exhibit sociodemographic biases, even when they decline to respond? We study this research question by probing contextualized embeddings and exploring whether this bias is encoded in its latent representations. We propose a logistic Bradley-Terry probe which predicts word pair preferences of LLMs from the words' hidden vectors.
  arXiv  Detail & Related papers  (2023-11-30T18:53:13Z)
• Generative Language Models Exhibit Social Identity Biases [17.307292780517653]
  We investigate whether ingroup solidarity and outgroup hostility, fundamental social identity biases, are present in 56 large language models. We find that almost all foundational language models and some instruction fine-tuned models exhibit clear ingroup-positive and outgroup-negative associations when prompted to complete sentences. Our findings suggest that modern language models exhibit fundamental social identity biases to a similar degree as humans.
  arXiv  Detail & Related papers  (2023-10-24T13:17:40Z)
• The Neuro-Symbolic Inverse Planning Engine (NIPE): Modeling Probabilistic Social Inferences from Linguistic Inputs [50.32802502923367]
  We study the process of language driving and influencing social reasoning in a probabilistic goal inference domain. We propose a neuro-symbolic model that carries out goal inference from linguistic inputs of agent scenarios. Our model closely matches human response patterns and better predicts human judgements than using an LLM alone.
  arXiv  Detail & Related papers  (2023-06-25T19:38:01Z)
• On the Origins of Bias in NLP through the Lens of the Jim Code [1.256413718364189]
  We trace the biases in current natural language processing (NLP) models back to their origins in racism, sexism, and homophobia over the last 500 years. We show how the causes of the biases in the NLP pipeline are rooted in social issues.
  arXiv  Detail & Related papers  (2023-05-16T08:37:13Z)
• Speaking Multiple Languages Affects the Moral Bias of Language Models [70.94372902010232]
  Pre-trained multilingual language models (PMLMs) are commonly used when dealing with data from multiple languages and cross-lingual transfer. Do the models capture moral norms from English and impose them on other languages? Our experiments demonstrate that, indeed, PMLMs encode differing moral biases, but these do not necessarily correspond to cultural differences or commonalities in human opinions.
  arXiv  Detail & Related papers  (2022-11-14T20:08:54Z)
• Argument from Old Man's View: Assessing Social Bias in Argumentation [20.65183968971417]
  Social bias in language poses a problem with ethical impact for many NLP applications. Recent research has shown that machine learning models trained on respective data may not only adopt, but even amplify the bias. We study the existence of social biases in large English debate portals.
  arXiv  Detail & Related papers  (2020-11-24T10:39:44Z)
• A Framework for the Computational Linguistic Analysis of Dehumanization [52.735780962665814]
  We analyze discussions of LGBTQ people in the New York Times from 1986 to 2015. We find increasingly humanizing descriptions of LGBTQ people over time. The ability to analyze dehumanizing language at a large scale has implications for automatically detecting and understanding media bias as well as abusive language online.
  arXiv  Detail & Related papers  (2020-03-06T03:02:12Z)

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.