Dialectic Preference Bias in Large Language Models
Bibliographic record
Abstract
Dialectic preference is an often overlooked language model's (LLM) bias against marginalized groups. It can be observed When LLMs output reflects or promotes unfair preferences or prejudices towards particular dialects or linguistic variations. Such bias may lead the model to favor certain ways of speaking or writing, which can disadvantage speakers of marginalized dialects. Such bias can perpetuate social biases and inequalities, affecting how people interact with and are supported by AI technologies. In this preliminary study, we analyze dialectic preference bias for Standard American English (SAE) compared to African American English (AAE) using the sentiment classification task on Claude 3 Haiku, Phi-3-medium, and LLaMa 3.1 8b. We find a greater tendency to classify AAE sentiments as negative, especially in LLaMa 3.1 8b, compared to other models, demonstrating the presence of dialectic preference bias. This work highlights the importance of addressing dialectic language-based biases in LLMs to reach inclusive and equitable LLMs. We plan to extend this study to more dialects and larger language models.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.009 | 0.042 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".