Disagreeing Rationales: Rethinking Classification and Explainability Evaluation in Hate Speech Detection
This paper investigates human disagreement in token-level rationale annotations for hate speech detection, a dimension less studied than label disagreement. The authors unify diverse models, training strategies, loss functions, and evaluation metrics under a single protocol, systematically comparing hard and soft label/rationale representation spaces. Results show that both hard and soft metrics favor softer representations, suggesting that soft supervision better captures human reasoning variation in subjective NLP tasks. The work calls for rethinking evaluation frameworks for classification and explainability in subjective NLP.
Related guides (2)
Related events (8)
When Does Demographic Information Help? Data and Modeling Regimes for Perspective-Aware Hate Speech Detection
This paper investigates when demographic features improve hate speech detection models that account for annotator perspectives, finding that gains are not universal but depend on specific data and modeling conditions. The authors identify that demographic information helps most in regimes with low training disagreement, high test disagreement, sufficient training data, and strong demographic overlap between train and test sets. They introduce a gated demographic residual model that selectively applies demographic adjustments to text-only predictions, demonstrating effectiveness on high-disagreement and low-confidence examples using the MHS and POPQUORN datasets. The work cautions against assuming demographic features are universally beneficial in subjective NLP tasks.
LLMs fail to consistently simulate demographic perspective-taking in hate speech annotation
A new arXiv paper evaluates whether persona-conditioned LLMs can replicate how different demographic groups perceive hate speech, testing three dimensions: inter-group disagreement, in-group sensitivity, and vicarious prediction. No model consistently captures all three dimensions, and performance is highly model-dependent rather than emerging reliably from identity prompts alone. Vicarious prompting with Llama 3.1 provides the closest approximation to human disagreement patterns across demographic axes. The findings have implications for using LLMs as proxies for diverse human annotators in content moderation tasks.
Interaction SSD: Modeling Annotator Identity Effects on Hate Speech Semantic Gradients
This paper introduces Interaction SSD, an extension of Supervised Semantic Differential that tests how semantic meaning varies across moderating variables such as annotator group identity. Applied to the UC Berkeley Measuring Hate Speech corpus, the method detects that annotator racial identity significantly moderates hate-speech judgments, with a shared gradient distinguishing dehumanizing hostility from counter-speech and an interaction gradient revealing group-linked differences in predictive semantic cues. The approach makes moderated meaning-outcome relationships statistically testable and interpretable through standard SSD tooling.
Annotated dataset for enthymeme detection in political tweets with disagreement-aware training
Researchers present a dataset of 1,482 politically controversial tweets annotated by five annotators for enthymemes — arguments with unstated premises or conclusions — designed to study label variation rather than eliminate it. Annotation guidelines are grounded in Walton's argumentation schemes, and the paper includes a complexity analysis of cognitive load in the task. Preliminary experiments show that models trained on annotator disagreement outperform those trained on hard majority-vote labels, suggesting value in preserving annotation disagreement for subjective NLP tasks.
Can Foundation Models Label Data Like Humans?
This Hugging Face blog post examines whether foundation models can serve as substitutes for human annotators in RLHF data labeling pipelines. It investigates the reliability and quality of model-generated preference labels compared to human-generated ones, with implications for scalable oversight and alignment research. The analysis is framed around the Open LLM Leaderboard and RLHF methodology.
WhoSaidIt: Human-LLM Collaborative Annotation for Multilingual Speaker-Attribute Classification
This paper proposes a human-LLM collaborative re-annotation framework for stabilizing noisy multilingual speaker-attribute labels under resource constraints. LLMs surface recurring annotation rationales through iterative expert interaction, combined with disagreement-focused sampling for targeted re-annotation. The resulting WhoSaidIt dataset covers nine speaker-attribute labels across multiple languages. Benchmarking of recent LLMs reveals substantial cross-lingual annotation divergence and highlights both capabilities and limitations of LLMs in this classification task.
Evaluating Language Model Bias with 🤗 Evaluate
This Hugging Face blog post introduces tooling and methodology for evaluating bias in language models using the Evaluate library. It covers bias measurement approaches and how practitioners can apply them to assess fairness properties of LLMs. The post is oriented toward applied practitioners working with open-source models.
Text Analytics Evaluation Framework: Benchmarking LLMs on Social Media NLP Tasks
Researchers introduce a 470-question evaluation framework to assess LLM performance on aggregated social media text, applied to Twitter datasets across sentiment analysis, hate speech detection, and emotion recognition. Results show performance degrades substantially as input scale exceeds 500 instances, particularly for open-weights models on numerical tasks. Multi-label and target-dependent scenarios also show notable performance drops, and task complexity progressively erodes accuracy from basic semantic identification to comparison and counting operations. The findings point to architectural bottlenecks in current LLMs for rigorous quantitative analysis over large text collections.