Newest papers

Effects of Model Scale and Quantization on Social Bias and Abstention in Question Answering

Kuniko Paxton, Ifeoluwa Wuraola, Dhavalkumar Thakker · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29657 · cited by 0 works (OpenAlex) · open-access PDF

Russian

Развертывание небольших и квантизированных языковых моделей в ограниченных ресурсами настройках вызывает важный вопрос справедливости: когда сжатая модель производит меньше предвзятых ответов, отражает ли это более справедливое поведение или большее воздержание? Мы изучаем эту проблему в вопросе ответа (QA) с использованием базового показателя BBQ в нескольких размерах моделей и настройках квантизации от Qwen3, Gemma-3 и SmolLM2. Мы также изучаем, остаются ли наблюдаемые тенденции стабильными в альтернативных формулировках проб и когда опция «Неизвестное» удаляется в условиях принудительного выбора. Наши результаты показывают, что более крупные модели достигли более высокой точности QA, но предвзятость не показала простой тенденции масштабирования и к

Machine translation (Meta M2M100); the English original follows.

Abstract

The deployment of small and quantized language models in resource-constrained settings raises an important fairness question: when a compressed model produces fewer biased responses, does this reflect fairer behavior or greater abstention? We study this problem in Question Answering (QA) using the BBQ benchmark across multiple model sizes and quantization settings from Qwen3, Gemma-3, and SmolLM2. We also examine whether the observed trends remain stable across alternative prompt formulations and when the ``Unknown'' option is removed in a forced-choice setting. Our results show that larger models achieved higher QA accuracy, but bias showed no simple scaling trend and quantization effects varied across configurations. Notably, 20 of the 26 configurations with fewer biased responses also show increased over-abstention, indicating that lower observed bias can partly reflect greater abstention. These findings show that lower observed bias can partly reflect greater abstention, and that fairness evaluation should consider biased responses, abstention, prompt formulation, and answer-option design jointly.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Quantization (signal processing), Scaling, Question answering, Econometrics, Computer science, Psychology

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29657, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange