# Both Direct and Indirect Evidence Contribute to Dative Alternation Preferences in Language Models

arXiv: https://arxiv.org/abs/2503.20850 · HTML: https://mlsanity.com/paper/2503.20850/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 26 Mar 2025.

## Builds on (most cited first, 14 of 14)

- [Language Models Learn Rare Phenomena from Less Rare Phenomena: The Case of the Missing AANNs](https://mlsanity.com/paper/2403.19827/) (2024)
- [minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models](https://mlsanity.com/paper/2203.13112/) (2022)
- [How Linguistics Learned to Stop Worrying and Love the Language Models](https://mlsanity.com/paper/2501.17047/) (2025)
- [Filtered Corpus Training (FiCT) Shows that Language Models can Generalize from Indirect Evidence](https://mlsanity.com/paper/2405.15750/) (2024)
- [Mission: Impossible Language Models](https://mlsanity.com/paper/2401.06416/) (2024)
- [Language Models Use Monotonicity to Assess NPI Licensing](https://mlsanity.com/paper/2105.13818/) (2021)
- [Is Child-Directed Speech Effective Training Data for Language Models?](https://mlsanity.com/paper/2408.03617/) (2024)
- [Can Language Models Learn Typologically Implausible Languages?](https://mlsanity.com/paper/2502.12317/) (2025)
- [Investigating representations of verb bias in neural language models](https://mlsanity.com/paper/2010.02375/) (2020)
- [In-Contextual Gender Bias Suppression for Large Language Models](https://mlsanity.com/paper/2309.07251/) (2023)
- [Manipulating language models' training data to study syntactic constraint learning: the case of English passivization](https://mlsanity.com/paper/2407.04593/) (2024)
- [A systematic framework for generating novel experimental hypotheses from language models](https://mlsanity.com/paper/2408.05086/) (2024)
- [Can Language Models Induce Grammatical Knowledge from Indirect Evidence?](https://mlsanity.com/paper/2410.06022/) (2024)
- [Language Models Largely Exhibit Human-like Constituent Ordering Preferences](https://mlsanity.com/paper/2502.05670/) (2025)

## Built on by (most cited first, 18 of 18)

- [Unpacking Let Alone: Human-Scale Models Generalize to a Rare Construction in Form but not Meaning](https://mlsanity.com/paper/2506.04408/) (2025)
- [An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift](https://mlsanity.com/paper/2601.05882/) (2026)
- [On the Interpretability of Whisper Encodings Using Sparse Autoencoders](https://mlsanity.com/paper/2605.12225/) (2026)
- [Function Words as Statistical Cues for Language Learning](https://mlsanity.com/paper/2601.21191/) (2026)
- [A Unified Assessment of the Poverty of the Stimulus Argument for Neural Language Models](https://mlsanity.com/paper/2602.09992/) (2026)
- [Cross-Modal Taxonomic Generalization in (Vision-) Language Models](https://mlsanity.com/paper/2603.07474/) (2026)
- [Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs](https://mlsanity.com/paper/2605.23039/) (2026)
- [Language models as tools for investigating the distinction between possible and impossible natural languages](https://mlsanity.com/paper/2512.09394/) (2025)
- [Large language models have learned to use language](https://mlsanity.com/paper/2512.12447/) (2025)
- [Large language models are not about natural language](https://mlsanity.com/paper/2512.13441/) (2025)
- [Linguists should learn to love speech-based deep learning models](https://mlsanity.com/paper/2512.14506/) (2025)
- [Are Language Models Models?](https://mlsanity.com/paper/2601.10421/) (2026)
- [Across the Levels of Analysis: Explaining Predictive Processing in Humans Requires More Than Machine-Estimated Probabilities](https://mlsanity.com/paper/2604.09466/) (2026)
- [You Can't Fight in Here! This is BBS!](https://mlsanity.com/paper/2604.09501/) (2026)
- [Targeted Linguistic Analysis of Sign Language Models with Minimal Translation Pairs](https://mlsanity.com/paper/2604.27232/) (2026)
- [Not-So-Strange Love: Language Models and Generative Linguistic Theories are More Compatible than They Appear](https://mlsanity.com/paper/2605.10061/) (2026)
- [The Holistic Storage of Verb+Up Phrases in Text-based and Audio-based Language Models](https://mlsanity.com/paper/2606.13993/) (2026)
- [Disentangling Statistical Preemption from Entrenchment in Language Models' Avoidance of Overgeneralization](https://mlsanity.com/paper/2609.01794/) (2026)

## Abstract (arXiv)

Language models (LMs) tend to show human-like preferences on a number of syntactic phenomena, but the extent to which these are attributable to direct exposure to the phenomena or more general properties of language is unclear. We explore this with the English dative alternation (DO: "gave Y the X" vs. PO: "gave the X to Y"), using a controlled rearing paradigm wherein we iteratively train small LMs on systematically manipulated input. We focus on two properties that affect the choice of alternant: length and animacy. Both properties are directly present in datives but also reflect more global tendencies for shorter elements to precede longer ones and animates to precede inanimates. First, by manipulating and ablating datives for these biases in the input, we show that direct evidence of length and animacy matters, but easy-first preferences persist even without such evidence. Then, using LMs trained on systematically perturbed datasets to manipulate global length effects (re-linearizing sentences globally while preserving dependency structure), we find that dative preferences can emerge from indirect evidence. We conclude that LMs' emergent syntactic preferences come from a mix of direct and indirect sources.