The Hrunting of AI: Where and How to Improve English Dialectal Fairness

• URL: http://arxiv.org/abs/2603.15187v1
• Date: Mon, 16 Mar 2026 12:24:43 GMT
• Title: The Hrunting of AI: Where and How to Improve English Dialectal Fairness
• Abstract summary: Yorkshire, Geordie, and Cornish are three rarely-studied English dialects.<n>We find that human-human agreement when determining LLM generation quality directly impacts LLM-as-a-judge performance.
• Score: 13.11272455685601
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: It is known that large language models (LLMs) underperform in English dialects, and that improving them is difficult due to data scarcity. In this work we investigate how quality and availability impact the feasibility of improving LLMs in this context. For this, we evaluate three rarely-studied English dialects (Yorkshire, Geordie, and Cornish), plus African-American Vernacular English, and West Frisian as control. We find that human-human agreement when determining LLM generation quality directly impacts LLM-as-a-judge performance. That is, LLM-human agreement mimics the human-human agreement pattern, and so do metrics such as accuracy. It is an issue because LLM-human agreement measures an LLM's alignment with the human consensus; and hence raises questions about the feasibility of improving LLM performance in locales where low populations induce low agreement. We also note that fine-tuning does not eradicate, and might amplify, this pattern in English dialects. But also find encouraging signals, such as some LLMs' ability to generate high-quality data, thus enabling scalability. We argue that data must be carefully evaluated to ensure fair and inclusive LLM improvement; and, in the presence of scarcity, new tools are needed to handle the pattern found.

Related papers

• No Free Labels: Limitations of LLM-as-a-Judge Without Human Grounding [3.1674468740431396]
  We evaluate how well LLM Judges can grade whether a given response to a conversational question is correct.<n>We source questions from a combination of existing datasets and a novel, challenging benchmark (BFF-Bench) created for this analysis.<n>We show that providing a weaker judge with higher quality references reaches better agreement with human annotators than a stronger judge.
  arXiv  Detail & Related papers  (2025-03-07T00:42:08Z)
• Disparities in LLM Reasoning Accuracy and Explanations: A Case Study on African American English [66.97110551643722]
  We investigate dialectal disparities in Large Language Models (LLMs) reasoning tasks.<n>We find that LLMs produce less accurate responses and simpler reasoning chains and explanations for AAE inputs.<n>These findings highlight systematic differences in how LLMs process and reason about different language varieties.
  arXiv  Detail & Related papers  (2025-03-06T05:15:34Z)
• HumT DumT: Measuring and controlling human-like language in LLMs [29.82328120944693]
  Human-like language might improve user experience, but might also lead to deception, overreliance, and stereotyping.<n>We introduce HumT, metrics for human-like tone and other dimensions of social perceptions in text data based on relative probabilities from an LLM.<n>We introduce DumT, a method using HumT to systematically control and reduce the degree of human-like tone while preserving model performance.
  arXiv  Detail & Related papers  (2025-02-18T20:04:09Z)
• The Strong Pull of Prior Knowledge in Large Language Models and Its Impact on Emotion Recognition [74.04775677110179]
  In-context Learning (ICL) has emerged as a powerful paradigm for performing natural language tasks with Large Language Models (LLM) We show that LLMs have strong yet inconsistent priors in emotion recognition that ossify their predictions. Our results suggest that caution is needed when using ICL with larger LLMs for affect-centered tasks outside their pre-training domain.
  arXiv  Detail & Related papers  (2024-03-25T19:07:32Z)
• AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations [52.43593893122206]
  Alignedcot is an in-context learning technique for invoking Large Language Models. It achieves consistent and correct step-wise prompts in zero-shot scenarios. We conduct experiments on mathematical reasoning and commonsense reasoning.
  arXiv  Detail & Related papers  (2023-11-22T17:24:21Z)
• Are Large Language Models Temporally Grounded? [38.481606493496514]
  We provide Large language models (LLMs) with textual narratives. We probe them with respect to their common-sense knowledge of the structure and duration of events. We evaluate state-of-the-art LLMs on three tasks reflecting these abilities.
  arXiv  Detail & Related papers  (2023-11-14T18:57:15Z)
• Large Language Models: The Need for Nuance in Current Debates and a Pragmatic Perspective on Understanding [1.3654846342364308]
  Large Language Models (LLMs) are unparalleled in their ability to generate grammatically correct, fluent text. This position paper critically assesses three points recurring in critiques of LLM capacities. We outline a pragmatic perspective on the issue of real' understanding and intentionality in LLMs.
  arXiv  Detail & Related papers  (2023-10-30T15:51:04Z)
• CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation [94.59630161324013]
  We propose CoAnnotating, a novel paradigm for Human-LLM co-annotation of unstructured texts at scale. Our empirical study shows CoAnnotating to be an effective means to allocate work from results on different datasets, with up to 21% performance improvement over random baseline.
  arXiv  Detail & Related papers  (2023-10-24T08:56:49Z)
• Let Models Speak Ciphers: Multiagent Debate through Embeddings [84.20336971784495]
  We introduce CIPHER (Communicative Inter-Model Protocol Through Embedding Representation) to address this issue. By deviating from natural language, CIPHER offers an advantage of encoding a broader spectrum of information without any modification to the model weights. This showcases the superiority and robustness of embeddings as an alternative "language" for communication among LLMs.
  arXiv  Detail & Related papers  (2023-10-10T03:06:38Z)
• Can Large Language Models Capture Dissenting Human Voices? [7.668954669688971]
  Large language models (LLMs) have shown impressive achievements in solving a broad range of tasks. We evaluate the performance and alignment of LLM distribution with humans using two different techniques. We show LLMs exhibit limited ability in solving NLI tasks and simultaneously fail to capture human disagreement distribution.
  arXiv  Detail & Related papers  (2023-05-23T07:55:34Z)
• Can Large Language Models Transform Computational Social Science? [79.62471267510963]
  Large Language Models (LLMs) are capable of performing many language processing tasks zero-shot (without training data) This work provides a road map for using LLMs as Computational Social Science tools.
  arXiv  Detail & Related papers  (2023-04-12T17:33:28Z)

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.