AI ethics evidence index Search
Source-linked daily record
Evidence record 11361 · automatically gathered

Investigating first-language bias in LLM-based automated essay scoring: A cross-prompt evaluation of an open-weight AI-model on TOEFL essays

This study examines the cross-prompt generalization and first-language (L1) scoring effects of a LoRA-adapted open-weight large language model (Gemma-3-27B-it) applied to automated essay scoring. Using the identical model and inference configuration reported in "AiAWE: An Open-Source LLM Automated Writing Evaluation System Using LoRA-Adapted Instruction-Tuned Models" (Gayed, 2026), which was fine-tuned on 480 argumentative essays from two prompts, we evaluate scoring accuracy on the full TOEFL11

Record details

Published: 16 July 2026
Source: arXiv
Category: Research
Topics: Bias & fairness · Finance, VC & PE
Retrieved: 18 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Same publisher byline · Shared topic: Bias & fairness

Investigating first-language bias in LLM-based automated essay scoring: A cross-prompt evaluation of an open-weight AI-model on TOEFL essays

arXiv cs.CY · 17 July 2026

Shared topic: Bias & fairness · Shared topic: Finance, VC & PE

Hindsight: Similarity-Based Analytics for Mars Rover Drive Retrieval

arXiv cs.HC · 17 July 2026

Shared topic: Bias & fairness · Shared topic: Finance, VC & PE

Can Induced Emotion Bias LLM Behaviors in Sequential Decision Making?

arXiv cs.AI · 14 July 2026

Shared topic: Bias & fairness · Shared topic: Finance, VC & PE

Neutralizing Structural Inequality in the Nigerian FinTech Sector

arXiv cs.CY · 14 July 2026

Shared topic: Bias & fairness · Shared topic: Finance, VC & PE

AI-Powered Browsers Are Broadly Accurate News Summarizers That Reduce Political Bias and Negative Affect

arXiv · 21 July 2026

Shared topic: Bias & fairness · Shared topic: Finance, VC & PE

Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs

arXiv · 21 July 2026

How to cite this record

ethics.ai (16 July 2026), “Investigating first-language bias in LLM-based automated essay scoring: A cross-prompt evaluation of an open-weight AI-model on TOEFL essays,” evidence record 11361, https://ethics.ai/record/11361 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.