It's How You Ask: Gender-Associated Linguistic Bias in LLMs

• URL: http://arxiv.org/abs/2608.13328v1
• Date: Thu, 13 Aug 2026 14:54:23 GMT
• Title: It's How You Ask: Gender-Associated Linguistic Bias in LLMs
• Abstract summary: We show that when prompts contain linguistic features more commonly used by women, they elicit shorter, less sophisticated, and less formal responses.<n>Our work calls for upstream consideration of the influences of linguistic variation to mitigate disparate impacts of LLM-mediated workplace communication.
• Score: 3.2242349194283353
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Professional communication is increasingly mediated by LLMs - but do these models serve all users equally? We show that when prompts contain linguistic features more commonly used by women (hedges, tag questions, collective reference), they systematically elicit shorter, less sophisticated, and less formal responses across three document types and four models. These effects persist after controlling for prompt complexity and feature carry-over. Explicit gender cues like sign-off names are encoded in the same representational space as linguistic dialect - suggesting shared underlying mechanisms - yet linguistic register is far more influential, producing large, consistent effects where names produce none. Our results further reveal that post-hoc mitigation is challenging: because these patterns are culturally embedded and outside conscious control, users cannot easily avoid them through strategic self-presentation, and mechanistic analysis reveals that linguistic features are encoded in early transformer layers and entangled with other features. Our work calls for upstream consideration of the influences of linguistic variation to mitigate disparate impacts of LLM-mediated workplace communication.

Related papers

• Multilingual Language Models Encode Script Over Linguistic Structure [17.518899965837768]
  We investigate which linguistic properties - abstract language identity or surface-form cues - shape multilingual representations.<n> romanization induces near-disjoint representations that align with neither native-script inputs nor English, while word-order shuffling has limited effect on unit identity.<n>Our results suggest that multilingual LMs organize representations around surface form, with linguistic abstraction emerging gradually without collapsing into a unified interlingua.
  arXiv  Detail & Related papers  (2026-04-06T18:43:32Z)
• PragWorld: A Benchmark Evaluating LLMs' Local World Model under Minimal Linguistic Alterations and Conversational Dynamics [9.915303686933436]
  We evaluate the ability of language models (LMs) to encode and update their internal world model in dyadic conversations.<n>We show that LMs struggle to memorize crucial details, such as tracking entities under linguistic alterations to conversations.<n>We propose a dual-perspective interpretability framework which identifies transformer layers that are useful or harmful.
  arXiv  Detail & Related papers  (2025-11-17T06:17:17Z)
• Tracing Multilingual Representations in LLMs with Cross-Layer Transcoders [51.380449540006985]
  Large Language Models (LLMs) can process many languages, yet how they internally represent this diversity remains unclear.<n>Do they form shared multilingual representations with language-specific decoding, and if so, why does performance still favor the dominant training language?<n>We analyze their internal mechanisms using cross-layer transcoders (CLT) and attribution graphs.
  arXiv  Detail & Related papers  (2025-11-13T22:51:06Z)
• False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models [53.01170039144264]
  Subword tokenizers trained on multilingual corpora naturally produce overlapping tokens across languages.<n>Does token overlap facilitate cross-lingual transfer or instead introduce interference between languages?<n>We find that models with overlap outperform models with disjoint vocabularies.
  arXiv  Detail & Related papers  (2025-09-23T07:47:54Z)
• An Empirical Investigation of Gender Stereotype Representation in Large Language Models: The Italian Case [0.41942958779358674]
  This study examines in which manner Large Language Models shape responses to ungendered prompts, contributing to biased outputs.<n>The results highlight how content generated by LLMs can perpetuate stereotypes.<n>The presence of bias in AI-generated text can have significant implications in many fields, such as in the workplaces or in job selections.
  arXiv  Detail & Related papers  (2025-07-25T10:57:29Z)
• The Emergence of Abstract Thought in Large Language Models Beyond Any Language [95.50197866832772]
  Large language models (LLMs) function effectively across a diverse range of languages.<n>Preliminary studies observe that the hidden activations of LLMs often resemble English, even when responding to non-English prompts.<n>Recent results show strong multilingual performance, even surpassing English performance on specific tasks in other languages.
  arXiv  Detail & Related papers  (2025-06-11T16:00:54Z)
• Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models [49.16690802656554]
  We find that Multilingual factual models struggle to provide consistent responses to semantically equivalent prompts in different languages.<n>We propose a linear shortcut method that bypasses computations in the final layers, enhancing both prediction accuracy and cross-lingual consistency.
  arXiv  Detail & Related papers  (2025-04-05T19:43:10Z)
• Linguistic Blind Spots of Large Language Models [14.755831733659699]
  We study the performance of recent large language models (LLMs) on linguistic annotation tasks.<n>We find that recent LLMs show limited efficacy in addressing linguistic queries and often struggle with linguistically complex inputs.<n>Our results provide insights to inform future advancements in LLM design and development.
  arXiv  Detail & Related papers  (2025-03-25T01:47:13Z)
• Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies [75.85462924188076]
  Gender-inclusive NLP research has documented the harmful limitations of gender binary-centric large language models (LLM) We find that misgendering is significantly influenced by Byte-Pair (BPE) tokenization. We propose two techniques: (1) pronoun tokenization parity, a method to enforce consistent tokenization across gendered pronouns, and (2) utilizing pre-existing LLM pronoun knowledge to improve neopronoun proficiency.
  arXiv  Detail & Related papers  (2023-12-19T01:28:46Z)
• Let Models Speak Ciphers: Multiagent Debate through Embeddings [84.20336971784495]
  We introduce CIPHER (Communicative Inter-Model Protocol Through Embedding Representation) to address this issue. By deviating from natural language, CIPHER offers an advantage of encoding a broader spectrum of information without any modification to the model weights. This showcases the superiority and robustness of embeddings as an alternative "language" for communication among LLMs.
  arXiv  Detail & Related papers  (2023-10-10T03:06:38Z)
• Simple Linguistic Inferences of Large Language Models (LLMs): Blind Spots and Blinds [59.71218039095155]
  We evaluate language understanding capacities on simple inference tasks that most humans find trivial. We target (i) grammatically-specified entailments, (ii) premises with evidential adverbs of uncertainty, and (iii) monotonicity entailments. The models exhibit moderate to low performance on these evaluation sets.
  arXiv  Detail & Related papers  (2023-05-24T06:41:09Z)

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.