Dialectal Toxicity Detection: Evaluating LLM-as-a-Judge Consistency Across Language Varieties

• URL: http://arxiv.org/abs/2411.10954v1
• Date: Sun, 17 Nov 2024 03:53:24 GMT
• Title: Dialectal Toxicity Detection: Evaluating LLM-as-a-Judge Consistency Across Language Varieties
• Authors: Fahim Faisal, Md Mushfiqur Rahman, Antonios Anastasopoulos,
• Abstract summary: There has been little systematic study on how dialectal differences affect toxicity detection by modern LLMs. We create a multi-dialect dataset through synthetic transformations and human-assisted translations, covering 10 language clusters and 60 varieties. We then evaluated three LLMs on their ability to assess toxicity across multilingual, dialectal, and LLM-human consistency.
• Score: 23.777874316083984
• License:
• Abstract: There has been little systematic study on how dialectal differences affect toxicity detection by modern LLMs. Furthermore, although using LLMs as evaluators ("LLM-as-a-judge") is a growing research area, their sensitivity to dialectal nuances is still underexplored and requires more focused attention. In this paper, we address these gaps through a comprehensive toxicity evaluation of LLMs across diverse dialects. We create a multi-dialect dataset through synthetic transformations and human-assisted translations, covering 10 language clusters and 60 varieties. We then evaluated three LLMs on their ability to assess toxicity across multilingual, dialectal, and LLM-human consistency. Our findings show that LLMs are sensitive in handling both multilingual and dialectal variations. However, if we have to rank the consistency, the weakest area is LLM-human agreement, followed by dialectal consistency. Code repository: \url{https://github.com/ffaisal93/dialect_toxicity_llm_judge}

Related papers

• Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection [10.129235204880443]
  We evaluate the impact of different prompt languages and augmented translation data for the task in non-English contexts. We discuss the impact of the inherent bias in LLMs and the datasets in the mispredictions related to sensitive topics.
  arXiv  Detail & Related papers  (2024-10-21T04:08:16Z)
• 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)
• Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models [62.91524967852552]
  Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora. But can these models relate corresponding concepts across languages, effectively being crosslingual? This study evaluates six state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• Detecting Hallucinations in Large Language Model Generation: A Token Probability Approach [0.0]
  Large Language Models (LLMs) produce inaccurate outputs, also known as hallucinations. This paper introduces a supervised learning approach employing only four numerical features derived from tokens and vocabulary probabilities obtained from other evaluators. The method yields promising results, surpassing state-of-the-art outcomes in multiple tasks across three different benchmarks.
  arXiv  Detail & Related papers  (2024-05-30T03:00:47Z)
• FAC$^2$E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition [56.76951887823882]
  Large language models (LLMs) are primarily evaluated by overall performance on various text understanding and generation tasks. We present FAC$2$E, a framework for Fine-grAined and Cognition-grounded LLMs' Capability Evaluation.
  arXiv  Detail & Related papers  (2024-02-29T21:05:37Z)
• Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models [117.20416338476856]
  Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. We propose a novel detection method, language activation probability entropy (LAPE), to identify language-specific neurons within LLMs. Our findings indicate that LLMs' proficiency in processing a particular language is predominantly due to a small subset of neurons.
  arXiv  Detail & Related papers  (2024-02-26T09:36:05Z)
• Unveiling Linguistic Regions in Large Language Models [49.298360366468934]
  Large Language Models (LLMs) have demonstrated considerable cross-lingual alignment and generalization ability. This paper conducts several investigations on the linguistic competence of LLMs.
  arXiv  Detail & Related papers  (2024-02-22T16:56:13Z)
• Comparing Hallucination Detection Metrics for Multilingual Generation [62.97224994631494]
  This paper assesses how well various factual hallucination detection metrics identify hallucinations in generated biographical summaries across languages. We compare how well automatic metrics correlate to each other and whether they agree with human judgments of factuality. Our analysis reveals that while the lexical metrics are ineffective, NLI-based metrics perform well, correlating with human annotations in many settings and often outperforming supervised models.
  arXiv  Detail & Related papers  (2024-02-16T08:10:34Z)
• Beware of Words: Evaluating the Lexical Diversity of Conversational LLMs using ChatGPT as Case Study [3.0059120458540383]
  We consider the evaluation of the lexical richness of the text generated by conversational Large Language Models (LLMs) and how it depends on the model parameters. The results show how lexical richness depends on the version of ChatGPT and some of its parameters, such as the presence penalty, or on the role assigned to the model.
  arXiv  Detail & Related papers  (2024-02-11T13:41:17Z)
• Systematic Rectification of Language Models via Dead-end Analysis [34.37598463459319]
  Large language models (LLM) can be pushed to generate toxic discourses. Here, we center detoxification on the probability that the finished discourse is ultimately considered toxic. Our approach, called rectification, utilizes a separate but significantly smaller model for detoxification.
  arXiv  Detail & Related papers  (2023-02-27T17:47:53Z)

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.