Whose Emotions and Moral Sentiments Do Language Models Reflect?

• URL: http://arxiv.org/abs/2402.11114v2
• Date: Mon, 17 Jun 2024 23:41:37 GMT
• Title: Whose Emotions and Moral Sentiments Do Language Models Reflect?
• Authors: Zihao He, Siyi Guo, Ashwin Rao, Kristina Lerman,
• Abstract summary: Language models (LMs) are known to represent the perspectives of some social groups better than others. We find significant misalignment of LMs with both ideological groups. Even after steering the LMs towards specific ideological perspectives, the misalignment and liberal tendencies of the model persist.
• Score: 5.4547979989237225
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Language models (LMs) are known to represent the perspectives of some social groups better than others, which may impact their performance, especially on subjective tasks such as content moderation and hate speech detection. To explore how LMs represent different perspectives, existing research focused on positional alignment, i.e., how closely the models mimic the opinions and stances of different groups, e.g., liberals or conservatives. However, human communication also encompasses emotional and moral dimensions. We define the problem of affective alignment, which measures how LMs' emotional and moral tone represents those of different groups. By comparing the affect of responses generated by 36 LMs to the affect of Twitter messages, we observe significant misalignment of LMs with both ideological groups. This misalignment is larger than the partisan divide in the U.S. Even after steering the LMs towards specific ideological perspectives, the misalignment and liberal tendencies of the model persist, suggesting a systemic bias within LMs.

Related papers

• Large Language Models Reflect the Ideology of their Creators [73.25935570218375]
  Large language models (LLMs) are trained on vast amounts of data to generate natural language. We uncover notable diversity in the ideological stance exhibited across different LLMs and languages.
  arXiv  Detail & Related papers  (2024-10-24T04:02:30Z)
• Evaluating Large Language Model Biases in Persona-Steered Generation [26.92498998306013]
  We show that large language models (LLMs) are 9.7% less steerable towards incongruous personas than congruous ones. Models that are fine-tuned with Reinforcement Learning from Human Feedback (RLHF) are more steerable, especially towards stances associated with political liberals and women.
  arXiv  Detail & Related papers  (2024-05-30T17:06:03Z)
• Whose Side Are You On? Investigating the Political Stance of Large Language Models [56.883423489203786]
  We investigate the political orientation of Large Language Models (LLMs) across a spectrum of eight polarizing topics. Our investigation delves into the political alignment of LLMs across a spectrum of eight polarizing topics, spanning from abortion to LGBTQ issues. The findings suggest that users should be mindful when crafting queries, and exercise caution in selecting neutral prompt language.
  arXiv  Detail & Related papers  (2024-03-15T04:02:24Z)
• Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models [61.45529177682614]
  We challenge the prevailing constrained evaluation paradigm for values and opinions in large language models. We show that models give substantively different answers when not forced. We distill these findings into recommendations and open challenges in evaluating values and opinions in LLMs.
  arXiv  Detail & Related papers  (2024-02-26T18:00:49Z)
• MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks [49.60689355674541]
  A rich literature in cognitive science has studied people's causal and moral intuitions. This work has revealed a number of factors that systematically influence people's judgments. We test whether large language models (LLMs) make causal and moral judgments about text-based scenarios that align with human participants.
  arXiv  Detail & Related papers  (2023-10-30T15:57:32Z)
• Moral Foundations of Large Language Models [6.6445242437134455]
  Moral foundations theory (MFT) is a psychological assessment tool that decomposes human moral reasoning into five factors. As large language models (LLMs) are trained on datasets collected from the internet, they may reflect the biases that are present in such corpora. This paper uses MFT as a lens to analyze whether popular LLMs have acquired a bias towards a particular set of moral values.
  arXiv  Detail & Related papers  (2023-10-23T20:05:37Z)
• The Face of Populism: Examining Differences in Facial Emotional Expressions of Political Leaders Using Machine Learning [50.24983453990065]
  We use a deep-learning approach to process a sample of 220 YouTube videos of political leaders from 15 different countries. We observe statistically significant differences in the average score of negative emotions between groups of leaders with varying degrees of populist rhetoric.
  arXiv  Detail & Related papers  (2023-04-19T18:32:49Z)
• Whose Opinions Do Language Models Reflect? [88.35520051971538]
  We investigate the opinions reflected by language models (LMs) by leveraging high-quality public opinion polls and their associated human responses. We find substantial misalignment between the views reflected by current LMs and those of US demographic groups. Our analysis confirms prior observations about the left-leaning tendencies of some human feedback-tuned LMs.
  arXiv  Detail & Related papers  (2023-03-30T17:17:08Z)
• CommunityLM: Probing Partisan Worldviews from Language Models [11.782896991259001]
  We use a framework that probes community-specific responses to the same survey questions using community language models CommunityLM. In our framework we identify committed partisan members for each community on Twitter and fine-tune LMs on the tweets authored by them. We then assess the worldviews of the two groups using prompt-based probing of their corresponding LMs.
  arXiv  Detail & Related papers  (2022-09-15T05:52:29Z)

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.