paper-with-me

Papers

Beyond Overcorrection: Evaluating Diversity in T2I Models with DivBench

2025-07-02 · Felix Friedrich, Thiemo Ganesha Welsch, Manuel Brack, Patrick Schramowski, Kristian Kersting arxiv

Current diversification strategies for text-to-image (T2I) models often ignore contextual appropriateness, leading to over-diversification where demographic attributes are modified even when explicitly specified in prompts. This paper introduces DIVBENCH, a benchmark and evaluation framework for measuring both under- and over-diversification in T2I generation. Through systematic evaluation of state-of-the-art T2I models, we find that while most models exhibit limited diversity, many diversification approaches overcorrect by inappropriately altering contextually-specified attributes. We demonstrate that context-aware methods, particularly LLM-guided FairDiffusion and prompt rewriting, can already effectively address under-diversity while avoiding over-diversification, achieving a better balance between representation and semantic fidelity.

📄 PDF Abstract BibTeX arXiv:2507.03015

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Generating Diverse Translation with Perturbed kNN-MT

2024-02-14 · Yuto Nishida, Makoto Morishita, Hidetaka Kamigaito, Taro Watanabe

Generating multiple translation candidates would enable users to choose the one that satisfies their needs. Although there has been work on diversified generation, there exists room for improving the diversity mainly bec…

DiversityMachine TranslationTranslation

Alirector: Alignment-Enhanced Chinese Grammatical Error Corrector

2024-02-07 · Haihui Yang, Xiaojun Quan

Chinese grammatical error correction (CGEC) faces serious overcorrection challenges when employing autoregressive generative models such as sequence-to-sequence (Seq2Seq) models and decoder-only large language models (LL…

DecoderGrammatical Error CorrectionSentence

Evaluating Prompting Strategies for Grammatical Error Correction Based on Language Proficiency

2024-02-24 · Min Zeng, Jiexin Kuang, Mengyang Qiu, Jayoung Song 외

The writing examples of English language learners may be different from those of native speakers. Given that there is a significant differences in second language (L2) learners' error types by their proficiency levels, t…

Grammatical Error Correction

Leveraging What's Overfixed: Post-Correction via LLM Grammatical Error Overcorrection

2025-09-25 · Taehee Park, Heejin Do, Gary Geunbae Lee arxiv

Robust supervised fine-tuned small Language Models (sLMs) often show high reliability but tend to undercorrect. They achieve high precision at the cost of low recall. Conversely, Large Language Models (LLMs) often show t…

Grammatical Error Correction

Evaluating GPT-3.5 and GPT-4 on Grammatical Error Correction for Brazilian Portuguese

2023-06-27 · Maria Carolina Penteado, Fábio Perez

We investigate the effectiveness of GPT-3.5 and GPT-4, two large language models, as Grammatical Error Correction (GEC) tools for Brazilian Portuguese and compare their performance against Microsoft Word and Google Docs.…

Grammatical Error Correction