# Robust Pronoun Fidelity with English LLMs: Are they Reasoning, Repeating, or Just Biased?

arXiv: https://arxiv.org/abs/2404.03134 · HTML: https://mlsanity.com/paper/2404.03134/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 55 of its 81 references that are in the map.
- First posted on arXiv 4 Apr 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 55)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [The Flan Collection: Designing Data and Methods for Effective Instruction Tuning](https://mlsanity.com/paper/2301.13688/) (2023)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Are Emergent Abilities of Large Language Models a Mirage?](https://mlsanity.com/paper/2304.15004/) (2023)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Measuring Bias in Contextualized Word Representations](https://mlsanity.com/paper/1906.07337/) (2019)
- [Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them](https://mlsanity.com/paper/1903.03862/) (2019)
- [Gender Bias in Contextualized Word Embeddings](https://mlsanity.com/paper/1904.03310/) (2019)
- [Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models](https://mlsanity.com/paper/2402.14848/) (2024)
- [Intrinsic Bias Metrics Do Not Correlate with Application Bias](https://mlsanity.com/paper/2012.15859/) (2020)
- [Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks](https://mlsanity.com/paper/2305.10160/) (2023)
- [Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies](https://mlsanity.com/paper/2108.12084/) (2021)
- [Strategies for Structuring Story Generation](https://mlsanity.com/paper/1902.01109/) (2019)
- [Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?](https://mlsanity.com/paper/2207.10551/) (2022)
- [Context-Aware Neural Machine Translation Learns Anaphora Resolution](https://mlsanity.com/paper/1805.10163/) (2018)

## Built on by (most cited first, 17 of 17)

- [Holmes: A Benchmark to Assess the Linguistic Competence of Language Models](https://mlsanity.com/paper/2404.18923/) (2024)
- [Whose Facts Win? LLM Source Preferences under Knowledge Conflicts](https://mlsanity.com/paper/2601.03746/) (2026)
- [WinoPron: Revisiting English Winogender Schemas for Consistency, Coverage, and Grammatical Case](https://mlsanity.com/paper/2409.05653/) (2024)
- [Agree to Disagree? A Meta-Evaluation of LLM Misgendering](https://mlsanity.com/paper/2504.17075/) (2025)
- [Colombian Waitresses y Jueces canadienses: Gender and Country Biases in Occupation Recommendations from LLMs](https://mlsanity.com/paper/2505.02456/) (2025)
- [The Lou Dataset -- Exploring the Impact of Gender-Fair Language in German Text Classification](https://mlsanity.com/paper/2409.17929/) (2024)
- [NYT-Connections: A Deceptively Simple Text Classification Task that Stumps System-1 Thinkers](https://mlsanity.com/paper/2412.01621/) (2024)
- [Failure of contextual invariance in large language models](https://mlsanity.com/paper/2603.23485/) (2026)
- [Uncertainty Quantification for Evaluating Machine Translation Bias](https://mlsanity.com/paper/2507.18338/) (2025)
- [Adapting Psycholinguistic Research for LLMs: Gender-inclusive Language in a Coreference Context](https://mlsanity.com/paper/2502.13120/) (2025)
- [KG-Augmented Executable CoT for Mathematical Coding](https://mlsanity.com/paper/2508.04072/) (2025)
- [SLAyiNG: A Diverse and Community-validated Dataset of Queer Slang](https://mlsanity.com/paper/2509.17449/) (2025)
- [Decoding Partial Differential Equations: Cross-Modal Adaptation of Decoder-only Models to PDEs](https://mlsanity.com/paper/2510.05278/) (2025)
- [Teaching and Critiquing Conceptualization and Operationalization in NLP](https://mlsanity.com/paper/2512.18505/) (2025)
- [GRUFF: LLM Pronoun Fidelity, Reasoning, and Biases in German](https://mlsanity.com/paper/2605.30214/) (2026)
- [A Mechanistic Understanding of Pronoun Fidelity in LLMs](https://mlsanity.com/paper/2606.16407/) (2026)
- [Distinct dynamics of conceptual and referential disruptions in human reading and large language model processing](https://mlsanity.com/paper/2608.25999/) (2026)

## Abstract (arXiv)

Robust, faithful and harm-free pronoun use for individuals is an important goal for language model development as their use increases, but prior work tends to study only one or two of these characteristics at a time. To measure progress towards the combined goal, we introduce the task of pronoun fidelity: given a context introducing a co-referring entity and pronoun, the task is to reuse the correct pronoun later. We present RUFF, a carefully-designed dataset of over 5 million instances to measure robust pronoun fidelity in English, and we evaluate 37 model variants from nine popular families, across architectures (encoder-only, decoder-only and encoder-decoder) and scales (11M-70B parameters). When an individual is introduced with a pronoun, models can mostly faithfully reuse this pronoun in the next sentence, but they are significantly worse with she/her/her, singular they and neopronouns. Moreover, models are easily distracted by non-adversarial sentences discussing other people; even one sentence with a distractor pronoun causes accuracy to drop on average by 34 percentage points. Our results show that pronoun fidelity is not robust, in a simple, naturalistic setting where humans achieve nearly 100% accuracy. We encourage researchers to bridge the gaps we find and to carefully evaluate reasoning in settings where superficial repetition might inflate perceptions of model performance.