Identifying and Mitigating Gender Cues in Academic Recommendation Letters: An Interpretability Case Study

• URL: http://arxiv.org/abs/2604.12337v1
• Date: Tue, 14 Apr 2026 06:19:35 GMT
• Title: Identifying and Mitigating Gender Cues in Academic Recommendation Letters: An Interpretability Case Study
• Abstract summary: Letters of recommendation (LoRs) can carry patterns of implicitly gendered language that can influence downstream decisions.<n>In this work, we investigate the extent to which Transformer-based encoder models can infer the gender of applicants in academic LoRs submitted to an U.S. medical-residency program.
• Score: 3.7181065265645814
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Letters of recommendation (LoRs) can carry patterns of implicitly gendered language that can inadvertently influence downstream decisions, e.g. in hiring and admissions. In this work, we investigate the extent to which Transformer-based encoder models as well as Large Language Models (LLMs) can infer the gender of applicants in academic LoRs submitted to an U.S. medical-residency program after explicit identifiers like names and pronouns are de-gendered. While using three models (DistilBERT, RoBERTa, and Llama 2) to classify the gender of anonymized and de-gendered LoRs, significant gender leakage was observed as evident from up to 68% classification accuracy. Text interpretation methods, like TF-IDF and SHAP, demonstrate that certain linguistic patterns are strong proxies for gender, e.g. "emotional'' and "humanitarian'' are commonly associated with LoRs from female applicants. As an experiment in creating truly gender-neutral LoRs, these implicit gender cues were remove resulting in a drop of up to 5.5% accuracy and 2.7% macro $F_1$ score on re-training the classifiers. However, applicant gender prediction still remains better than chance. In this case study, our findings highlight that 1) LoRs contain gender-identifying cues that are hard to remove and may activate bias in decision-making and 2) while our technical framework may be a concrete step toward fairer academic and professional evaluations, future work is needed to interrogate the role that gender plays in LoR review. Taken together, our findings motivate upstream auditing of evaluative text in real-world academic letters of recommendation as a necessary complement to model-level fairness interventions.

Related papers

• Benchmarking Educational LLMs with Analytics: A Case Study on Gender Bias in Feedback [0.06951558137930917]
  This article presents an embedding-based benchmarking framework to detect bias in large language models (LLMs)<n>Using 600 authentic student essays from the AES 2.0 corpus, we constructed controlled counterfactuals along two dimensions.<n>We investigated six representative LLMs (i.e. GPT-5 mini, GPT-4o mini, DeepSeek-R1, DeepSeek-R1-Qwen, Gemini 2.5 Pro, Llama-3-8B)<n>In all models, implicit manipulations reliably induced larger semantic shifts for male-female counterfactuals than for female-male.
  arXiv  Detail & Related papers  (2025-11-11T13:28:44Z)
• GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models [73.23743278545321]
  Large language models (LLMs) have exhibited remarkable capabilities in natural language generation, but have also been observed to magnify societal biases.<n>GenderCARE is a comprehensive framework that encompasses innovative Criteria, bias Assessment, Reduction techniques, and Evaluation metrics.
  arXiv  Detail & Related papers  (2024-08-22T15:35:46Z)
• Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words [85.48043537327258]
  Existing machine translation gender bias evaluations are primarily focused on male and female genders. This study presents a benchmark AmbGIMT (Gender-Inclusive Machine Translation with Ambiguous attitude words) We propose a novel process to evaluate gender bias based on the Emotional Attitude Score (EAS), which is used to quantify ambiguous attitude words.
  arXiv  Detail & Related papers  (2024-07-23T08:13:51Z)
• Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation [64.79319733514266]
  Large Language Models (LLMs) can generate biased and toxic responses. We propose a conditional text generation mechanism without the need for predefined gender phrases and stereotypes.
  arXiv  Detail & Related papers  (2023-11-01T05:31:46Z)
• VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution [80.57383975987676]
  VisoGender is a novel dataset for benchmarking gender bias in vision-language models. We focus on occupation-related biases within a hegemonic system of binary gender, inspired by Winograd and Winogender schemas. We benchmark several state-of-the-art vision-language models and find that they demonstrate bias in resolving binary gender in complex scenes.
  arXiv  Detail & Related papers  (2023-06-21T17:59:51Z)
• Professional Presentation and Projected Power: A Case Study of Implicit Gender Information in English CVs [8.947168670095326]
  This paper investigates the framing of skills and background in CVs of self-identified men and women. We introduce a data set of 1.8K authentic, English-language, CVs from the US, covering 16 occupations.
  arXiv  Detail & Related papers  (2022-11-17T23:26:52Z)
• Towards Understanding Gender-Seniority Compound Bias in Natural Language Generation [64.65911758042914]
  We investigate how seniority impacts the degree of gender bias exhibited in pretrained neural generation models. Our results show that GPT-2 amplifies bias by considering women as junior and men as senior more often than the ground truth in both domains. These results suggest that NLP applications built using GPT-2 may harm women in professional capacities.
  arXiv  Detail & Related papers  (2022-05-19T20:05:02Z)
• Gendered Language in Resumes and its Implications for Algorithmic Bias in Hiring [0.0]
  We train a series of models to classify the gender of the applicant. We investigate whether it is possible to obfuscate gender from resumes. We find that there is a significant amount of gendered information in resumes even after obfuscation.
  arXiv  Detail & Related papers  (2021-12-16T14:26:36Z)
• Multi-Dimensional Gender Bias Classification [67.65551687580552]
  Machine learning models can inadvertently learn socially undesirable patterns when training on gender biased text. We propose a general framework that decomposes gender bias in text along several pragmatic and semantic dimensions. Using this fine-grained framework, we automatically annotate eight large scale datasets with gender information.
  arXiv  Detail & Related papers  (2020-05-01T21:23:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.