Evaluating how LLM annotations represent diverse views on contentious topics

• URL: http://arxiv.org/abs/2503.23243v1
• Date: Sat, 29 Mar 2025 22:53:15 GMT
• Title: Evaluating how LLM annotations represent diverse views on contentious topics
• Authors: Megan A. Brown, Shubham Atreja, Libby Hemphill, Patrick Y. Wu,
• Abstract summary: We show how generative large language models (LLMs) represent diverse viewpoints on contentious labeling tasks.<n>Our findings suggest that when using LLMs to annotate data, under-representing the views of particular groups is not a substantial concern.
• Score: 3.405231040967506
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Researchers have proposed the use of generative large language models (LLMs) to label data for both research and applied settings. This literature emphasizes the improved performance of LLMs relative to other natural language models, noting that LLMs typically outperform other models on standard metrics such as accuracy, precision, recall, and F1 score. However, previous literature has also highlighted the bias embedded in language models, particularly around contentious topics such as potentially toxic content. This bias could result in labels applied by LLMs that disproportionately align with majority groups over a more diverse set of viewpoints. In this paper, we evaluate how LLMs represent diverse viewpoints on these contentious tasks. Across four annotation tasks on four datasets, we show that LLMs do not show substantial disagreement with annotators on the basis of demographics. Instead, the model, prompt, and disagreement between human annotators on the labeling task are far more predictive of LLM agreement. Our findings suggest that when using LLMs to annotate data, under-representing the views of particular groups is not a substantial concern. We conclude with a discussion of the implications for researchers and practitioners.

Related papers

• Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision [50.45597801390757]
  Instruct-LF is a goal-oriented latent factor discovery system. It integrates instruction-following ability with statistical models to handle noisy datasets.
  arXiv  Detail & Related papers  (2025-02-21T02:03:08Z)
• Preference Leakage: A Contamination Problem in LLM-as-a-judge [69.96778498636071]
  Large Language Models (LLMs) as judges and LLM-based data synthesis have emerged as two fundamental LLM-driven data annotation methods.<n>In this work, we expose preference leakage, a contamination problem in LLM-as-a-judge caused by the relatedness between the synthetic data generators and LLM-based evaluators.
  arXiv  Detail & Related papers  (2025-02-03T17:13:03Z)
• The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs [21.97227334180969]
  "LLM-as-a-judge" paradigm employs Large Language Models as annotators and evaluators in tasks traditionally performed by humans. Despite their role in shaping study results and insights, there is no standard or rigorous procedure to determine whether LLMs can replace human annotators. We propose a novel statistical procedure -- the Alternative Annotator Test (alt-test) -- that requires only a modest subset of annotated examples to justify using LLM annotations.
  arXiv  Detail & Related papers  (2025-01-19T07:09:11Z)
• Hate Personified: Investigating the role of LLMs in content moderation [64.26243779985393]
  For subjective tasks such as hate detection, where people perceive hate differently, the Large Language Model's (LLM) ability to represent diverse groups is unclear. By including additional context in prompts, we analyze LLM's sensitivity to geographical priming, persona attributes, and numerical information to assess how well the needs of various groups are reflected.
  arXiv  Detail & Related papers  (2024-10-03T16:43:17Z)
• Examining the Influence of Political Bias on Large Language Model Performance in Stance Classification [5.8229466650067065]
  We investigate whether large language models (LLMs) exhibit a tendency to more accurately classify politically-charged stances. Our findings reveal a statistically significant difference in the performance of LLMs across various politically oriented stance classification tasks. LLMs have poorer stance classification accuracy when there is greater ambiguity in the target the statement is directed towards.
  arXiv  Detail & Related papers  (2024-07-25T01:11:38Z)
• SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
  Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM. We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
  arXiv  Detail & Related papers  (2024-07-16T04:41:58Z)
• Fairness in Large Language Models: A Taxonomic Survey [2.669847575321326]
  Large Language Models (LLMs) have demonstrated remarkable success across various domains.<n>Despite their promising performance in numerous real-world applications, most of these algorithms lack fairness considerations.
  arXiv  Detail & Related papers  (2024-03-31T22:22:53Z)
• Large Language Models: A Survey [66.39828929831017]
  Large Language Models (LLMs) have drawn a lot of attention due to their strong performance on a wide range of natural language tasks.<n>LLMs' ability of general-purpose language understanding and generation is acquired by training billions of model's parameters on massive amounts of text data.
  arXiv  Detail & Related papers  (2024-02-09T05:37:09Z)
• Are Large Language Models Reliable Judges? A Study on the Factuality Evaluation Capabilities of LLMs [8.526956860672698]
  Large Language Models (LLMs) have gained immense attention due to their notable emergent capabilities. This study investigates the potential of LLMs as reliable assessors of factual consistency in summaries generated by text-generation models.
  arXiv  Detail & Related papers  (2023-11-01T17:42:45Z)
• Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications [23.963586791210414]
  We show that large language models (LLMs) tend to inherit social biases from their training data which significantly impact their fairness in classification tasks. This observation emphasizes that the social biases are inherent within the LLMs themselves and inherited from their pretraining corpus.
  arXiv  Detail & Related papers  (2023-10-23T06:31:28Z)
• "Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters [97.11173801187816]
  Large Language Models (LLMs) have recently emerged as an effective tool to assist individuals in writing various types of content. This paper critically examines gender biases in LLM-generated reference letters.
  arXiv  Detail & Related papers  (2023-10-13T16:12:57Z)
• On Learning to Summarize with Large Language Models as References [101.79795027550959]
  Large language models (LLMs) are favored by human annotators over the original reference summaries in commonly used summarization datasets. We study an LLM-as-reference learning setting for smaller text summarization models to investigate whether their performance can be substantially improved.
  arXiv  Detail & Related papers  (2023-05-23T16:56:04Z)

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.