# Cultural Fidelity in English-to-Hindi Translation: A Preservation-Fluency Frontier for Gender Recoverability

arXiv: https://arxiv.org/abs/2605.27654 · HTML: https://mlsanity.com/paper/2605.27654/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 23 references that are in the map.
- First posted on arXiv 26 May 2026.

## Builds on (most cited first, 20 of 20)

- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Evaluating Gender Bias in Machine Translation](https://mlsanity.com/paper/1906.00591/) (2019)
- [IndicTrans2: Towards High-Quality and Accessible Machine Translation Models for all 22 Scheduled Indian Languages](https://mlsanity.com/paper/2305.16307/) (2023)
- [Gender Bias in Machine Translation](https://mlsanity.com/paper/2104.06001/) (2021)
- [Getting Gender Right in Neural Machine Translation](https://mlsanity.com/paper/1909.05088/) (2019)
- [Benchmarking Machine Translation with Cultural Awareness](https://mlsanity.com/paper/2305.14328/) (2023)
- [Mitigating Gender Bias in Machine Translation with Target Gender Annotations](https://mlsanity.com/paper/2010.06203/) (2020)
- [Neural Machine Translation Doesn't Translate Gender Coreference Right Unless You Make It](https://mlsanity.com/paper/2010.05332/) (2020)
- [MT-GenEval: A Counterfactual and Contextual Dataset for Evaluating Gender Accuracy in Machine Translation](https://mlsanity.com/paper/2211.01355/) (2022)
- [First the worst: Finding better gender translations during beam search](https://mlsanity.com/paper/2104.07429/) (2021)
- [Filling Gender & Number Gaps in Neural Machine Translation with Black-box Context Injection](https://mlsanity.com/paper/1903.03467/) (2019)
- [Evaluating Gender Bias in Hindi-English Machine Translation](https://mlsanity.com/paper/2106.08680/) (2021)
- [A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation](https://mlsanity.com/paper/2310.12127/) (2023)
- [Akal Badi ya Bias: An Exploratory Study of Gender Bias in Hindi Language Technology](https://mlsanity.com/paper/2405.06346/) (2024)
- [Translating Across Cultures: LLMs for Intralingual Cultural Adaptation](https://mlsanity.com/paper/2406.14504/) (2024)
- [The power of Prompts: Evaluating and Mitigating Gender Bias in MT with LLMs](https://mlsanity.com/paper/2407.18786/) (2024)
- [Mitigating Gender Stereotypes in Hindi and Marathi](https://mlsanity.com/paper/2205.05901/) (2022)
- [MiTTenS: A Dataset for Evaluating Gender Mistranslation](https://mlsanity.com/paper/2401.06935/) (2024)
- [Gender Inflected or Bias Inflicted: On Using Grammatical Gender Cues for Bias Evaluation in Machine Translation](https://mlsanity.com/paper/2311.03767/) (2023)

## Abstract (arXiv)

Generative translation systems are cultural technologies because they decide how socially meaningful cues are rendered within culturally specific grammatical systems. We study one concrete notion of successful cultural translation: when an English source explicitly encodes gender, an English-to-Hindi translation should preserve the recoverability of that cue unless the source itself is ambiguous. We evaluate this criterion on a 37,345-instance benchmark spanning twelve categories and show that five systems frequently erase gender through ergative and honorific constructions. We then introduce two mechanism-aware inference-time interventions. The first, the Source-Aware Reranker (SAR), prefers candidates that avoid gender-neutralizing syntax. The second, the Phenomenon-Aware Reranker (PAR), preserves gender through targeted lexical marking even when ergative syntax remains. Across GPT-4o-mini and Sarvam, PAR improves target-subset accuracy from 11.07% to 54.47% and from 15.99% to 49.66%, respectively. Human evaluation shows that PAR increases gender preservation from 10.3% to 81.3%, but reduces mean fluency from 4.36 to 3.37. These findings place the two interventions on a preservation and fluency frontier rather than supporting a single dominant solution, and show how culturally situated generation can require explicit tradeoffs among fidelity, fluency, and stylistic naturalness.